In vitro experiments measuring percentage cell death in three genotypes of cells.

Description

These data are from in vitro measurements of death of host cells (measured as percentage of total cells) after infection with three different strains of a pathogenic bacterium, from five independent experiments. The three strains are three levels within the fixed factor Genotype. The five independent experiments are levels within the random variable Experiment. These data can be analysed using linear mixed effects modelling. These data are from Goddard et al, Cell Rep, 2019 (doi:10.1016/j.celrep.2019年03月10日0).

Usage

data_1w_death

Format

data.frame: 15 obs. of 3 variables.

Experiment

Experiment - a random factor with 5 levels "Exp_1","Exp_2"...

Genotype

Genotypes - a fixed factor with 3 levels: "WT","KO_1","KO_2".

Death

Numerical dependent variable indicating percentage cell death.

Data from two-way ANOVA with randomised block design of treatments of strains of mice.

Description

Data from Festing, ILAR Journal (2014) 55, 472–476 (doi:10.1093/ilar/ilu045). These data are suitable for two-way linear mixed effects modelling. The activity of GST (numerical dependent variable) was measured in 4 strains of mice (levels with the fixed factor Strain) either treated or controls (levels within the fixed factor Treatment). Once mouse each was used in two randomised blocks, which is the random factor (Block).

Usage

data_2w_Festing

Format

data.frame: 16 obs. of 4 variables:

Block

A random factor with 2 levels "A" and "B".

Treatment

A fixed factor with 2 levels: "Control" & "Treated"

Strain

A fixed factor with 4 levels: "129Ola", "A/J", "NIH" & "BALB/C"

GST

Numerical dependent variable indicating GST activity measurement

In vitro measurement of percentage cell death - two-way ANOVA design with repeated measures, and randomised blocks.

Description

These are measurements of death of infected host cells (as percentage of total cells) upon infection with two strains of bacteria, measured at two time points, in 6 independent experiments. These data repeated-measures data suitable for two-way linear mixed effects modelling with experiment and subjects as random factors.

Usage

data_2w_Tdeath

Format

data.frame: 24 obs. of 6 variables:

Experiment

A random factor with 6 levels "e1", "e2"...

Time

A fixed factor with 2 levels: "t100" & "t300".

Time2

A numeric column that allows plotting data on a quantitative "Time" axis. The "Time" column has "factor" type values that should be used for the ANOVA..

Genotype

A fixed factor with 2 levels that we want to compare "WT" & "KO".

Subject

A random factor with 12 levels: "s1", "s2"... These are cell culture wells that were measured at two time points, and indicate "subjects" that underwent repeated-measures within each of 6 experiments. Subject IDs for WT and KO are unique and clearly indicate different wells.

PI

Numerical dependent variable indicating propidium iodide dye uptake as a measure of cell death. These are percentage of dead cells out of total cells plated.

Hierarchical data from 25 subjects either treated or not at 5 hospitals - two-way ANOVA design with repeated measures.

Description

An example dataset on measurements of blood cholesterol levels measured in 5 subjects measured before and after receiving a Drug. Five patients each were recruited at 5 hospitals (a-e), so that there are 25 different subjects (1-25) measured twice. Data are from Micro/Immuno Stats

Usage

data_cholesterol

Format

tibble: 30 obs. of 3 variables:

Hospital

Factor with 5 levels (a-e), representing different hospitals where subjects were recruited.

Subject

A factor with 25 levels denoting individuals on whom measurements were made twice.

Treatment

A factor with 2 levels indicating when measurements were made, i.e. before and after drug.

Cholesterol

Numerical dependent variable indicating measured doubling time in min.

Doubling time of E.coli measured by 10 students three independent times.

Description

An example dataset showing measurements of E. coli doubling times (in min) measured by 10 different students in 3 independent experiments each. Note that Experiments are just called Exp1-Exp3 even though Exp1 of any of the students are not connected in anyway - this will confuse R! Data are from Micro/Immuno Stats

Usage

data_doubling_time

Format

tibble: 30 obs. of 3 variables:

Student

Factor with 10 levels, representing different students.

Experiment

A factor with 3 levels representing independent experiments.

Doubling_time

Numerical dependent variable indicating measured doubling time in min.

Matched data from two groups where difference between them is consistent.

Description

An example dataset for paired difference Student's t test. These are bodyweight (Mass) in grams of same mice left untreated or treated, which are two groups to be compared. The data are in a longtable format, and the two groups are levels within the factor "Condition". The Subject column lists ID of matched mice that were measured without and with treatment. These data are from Sanchez-Garrido et al, Sci Signal, 2018 (doi:10.1126/scisignal.aat6903).

Usage

data_t_pdiff

Format

data.frame: 20 obs. of 3 variables:

Subject

Factor with 10 levels, denoted by capital letters, representing individuals or subjects.

Condition

A fixed factor with 2 levels: "Untreated" & "Treated".

Mass

Numerical dependent variable indicating body mass of mice

Matched data from two groups where ratio between them is consistent.

Description

An example dataset for paired ratio Student's t test. These are Cytokine measurements by ELISA (in ng/ml) from 33 independent in vitro experiments performed on two Genotypes that we want to compare. The data are in a longtable format, and the two groups are levels within the factor "Genotype". The Experiment column lists ID of matched experiments.

Usage

data_t_pratio

Format

data.frame: 66 obs. of 3 variables:

Genotype

Factor with 2 levels, representing genotypes to be compared ("WT" & "KO").

Experiment

A random factor with 33 levels representing independent experiments, denoted as "Exp_1", "Exp_2"...

Cytokine

Numerical dependent variable indicating cytokine measured by ELISA.

Time-series data on zooplankton in lake Menon.

Description

A subset of data from (Lathro RC, 2000) (doi:10.6073/pasta/ec3d0186753985147d4f283252388e05) provided by the Wisconsin Department of Natural Resources

Usage

data_zooplankton

Format

tibble: 1127 obs. of 8 variables:

day

Numeric integer variable.

year

Numeric integer variable of years during which data were collected.

lake

This data is for lake Menon; data for other others not included in this subset.

taxon

Names of zooplankton taxa as factor of 8 levels.

density

Numeric values of density of measurements.

density_adj

Numeric values of adjusted density .

min_density

Numeric values of minimum densities.

desnsity_scaled

Numeric value of scaled density.

ANOVA table from a generalised additive model (gam)

Description

One of two functions for fitting generalised additive models (gam) with the mgcv package. It will use the gam() function in mgcv for ANOVA designs with up to two categorical fixed factors (with two or more levels; Fixed_Factor), and exactly one factor is a continuous variable (e.g. time), which is called Smooth_Factor.

1. ga_model

2. ga_anova

Usage

ga_anova(
 data,
 Y_value,
 Fixed_Factor,
 Smooth_Factor,
 Random_Factor = NULL,
 Nodes = NULL,
 ...
)

Arguments

Details

A smooth function is fitted with factor-wise smooth basis function (⁠by = ⁠). A default value for number of nodes (the argument k in gam) may work, but a specific number can be provided using the Nodes argument. The model is fit using the REML method. When two categorical fixed factors are provided, an interaction term is included for main effects and smooth basis functions.

If a Random_Factor is also provided, it is fitted using bs = "re" smooth.

Value

ANOVA table of class "anova" and "data.frame".

Examples

#with zooplankton data
ga_anova(data = data_zooplankton,
Y_value = "log(density_adj)",
Fixed_Factor = "taxon",
Smooth_Factor = "day")

Fit a generalised additive model (gam)

Description

One of two functions for fitting generalised additive models (gam) with the mgcv package. It will use the gam() function in mgcv for ANOVA designs with up to two categorical fixed factors (with two or more levels; Fixed_Factor), and exactly one factor is a continuous variable (e.g. time), which is called Smooth_Factor.

1. ga_model

2. ga_anova

A smooth function is fitted with factor-wise smooth basis function (⁠by = ⁠). A default value for number of nodes (the argument k in gam) may work, but a specific number can be provided using the Nodes argument. The model is fit using the REML method. When two categorical fixed factors are provided, an interaction term is included for main effects and smooth basis functions.

Usage

ga_model(
 data,
 Y_value,
 Fixed_Factor,
 Smooth_Factor,
 Random_Factor = NULL,
 Nodes = "NULL",
 ...
)

Arguments

Details

If a Random_Factor is also provided, it is fitted using bs = "re" smooth.

Value

This function gives a generalised additive model object of class "gam", "lm" and "glm".

Examples

#fit a model with zooplankton data
z1 <- ga_model(data = data_zooplankton,
Y_value = "log(density_adj)",
Fixed_Factor = "taxon",
Smooth_Factor = "day")

Get graf internal

Description

Function to make grafify colour scheme. Thank you Dr Simon.

Usage

get_graf_colours(...)

Arguments

Details

To visualise grafify colours use plot_grafify_palette.

Value

This function returns names and hexcodes of colours in grafify as a character vector.

Call grafify palettes for scale & fill functions

Description

graf_col_palette and graf_col_palette_default functions generate colours for grafify scale functions. graf_col_palette picks sequential colours when the number of discrete colours needed is less than that in the palette. This is the default for grafify with ColoSeq = TRUE. If the number of colours required is more than that in the discrete palette, it fills intervening colours using the colorRampPalette[grDevices] function.

Usage

graf_col_palette(palette = "okabe_ito", reverse = FALSE, ...)

Arguments

Details

graf_col_palette_default picks the most distant colours within the palette, rather than in the sequence they are in the palette, when the number of colours required is less than that in the palette.

Colour order can be reversed in both functions.

When only one colour discreet is required, and you want to reverse the colour palette, ColSeq should be set to FALSE.

Value

This generates required number of sequential colours from the chosen grafify palette when called by scale functions of ggplot2.

Call grafify palettes for scale & fill functions

Description

graf_col_palette and graf_col_palette_default functions generate colours for grafify scale functions. graf_col_palette picks sequential colours when the number of discrete colours needed is less than that in the palette. This is the default for grafify with ColoSeq = TRUE. If the number of colours required is more than that in the discrete palette, it fills intervening colours using the colorRampPalette[grDevices] function.

Usage

graf_col_palette_default(palette = "okabe_ito", reverse = FALSE, ...)

Arguments

Details

graf_col_palette_default picks the most distant colours within the palette, rather than in the sequence they are in the palette, when the number of colours required is less than that in the palette.

Colour order can be reversed in both functions.

When only one colour discreet is required, and you want to reverse the colour palette, ColSeq should be set to FALSE.

Value

This generates required number of distant colours from the chosen grafify palette when called by scale functions of ggplot2.

List of hexcodes of colours in grafify palettes

Description

To visualise these colours use plot_grafify_palette. okabe_ito, bright, contrast, dark, light, muted, pale, vibrant, yello_conti from Paul Tol's colours (also see khroma package). Zesty, Pastel, Elegant from this link. Colour hexcodes for fishy, kelly, r4, safe, OrBl_div, PrGn_div, blue_conti, grey_conti taken from cols4all:c4a_gui package. All schemes are colour blind-friendly.

Usage

graf_colours

Format

An object of class character of length 154.

Value

This is a character vector with names and hexcodes of colours used by palette functions. It is used by get_graf_colours to generate palettes.

List of palettes available in grafify package

Description

To visualise these colours use plot_grafify_palette.

Usage

graf_palettes

Format

An object of class list of length 18.

Value

This function returns a list of palettes in grafify with names and hexcodes of colours in those palettes. Names of palettes available are as follows:

Categorical/discreet palettes:

• okabe_ito

• bright

• contrast

• dark

• kelly

• light

• muted

• pale

• r4

• safe

• vibrant

Sequential quantitative palettes:

• grey_conti

• blue_conti

• yellow_conti

Divergent quantitative palettes:

• OrBl_div

• PrGn_div

Make one-way or two-way independent group or randomised block design data.

Description

The make_1way_data , make_1way_rb_data , make_2way_data and make_2way_rb_data functions generate independent or randomised block (rb) design data of one-way or two-way designs.

Usage

make_1way_data(Group_means, Num_obs, Residual_SD)

Arguments

Details

Random variates from the normal distribution based on user provided mean and SD provided are generated. For independent designs, the Residual_SD argument is used to set expected residual SD from the linear model. Exp_SD is used to set experiment-to-experiment SD, that will be assigned to the random factor for rb designs.

Num_exp sets the number of independent measurements per group.

For one-way designs, the user provides Group_means as a vector. Number of levels are recognised based on number of means. For two-way designs, two vectors are to be provided by the user containing means of levels of a second factor. Number of means in both vectors should be the same. These functions can only handle balanced designs, i.e. same number of observations in all groups.

The output is a data frame with one or two columns denoting the fixed factor with levels that match the number of means entered. For rb data, the column for RandFac denotes levels of the blocking factor. The quantitative response variables are in the numeric Values column.

Value

This function produces a data.frame object containing simulated data.

Examples

#Basic usage with three levels within Factor_X, 
#20 observations in each group, with residual SD 15
one_independent_tab <- make_1way_data(c(350, 250, 100), 15, 20)
str(one_independent_tab)
head(one_independent_tab)

Make one-way or two-way independent group or randomised block design data.

Description

The make_1way_data , make_1way_rb_data , make_2way_data and make_2way_rb_data functions generate independent or randomised block (rb) design data of one-way or two-way designs.

Usage

make_1way_rb_data(Group_means, Num_exp, Exp_SD, Residual_SD)

Arguments

Details

Random variates from the normal distribution based on user provided mean and SD provided are generated. For independent designs, the Residual_SD argument is used to set expected residual SD from the linear model. Exp_SD is used to set experiment-to-experiment SD, that will be assigned to the random factor for rb designs.

Num_exp sets the number of independent measurements per group.

For one-way designs, the user provides Group_means as a vector. Number of levels are recognised based on number of means. For two-way designs, two vectors are to be provided by the user containing means of levels of a second factor. Number of means in both vectors should be the same. These functions can only handle balanced designs, i.e. same number of observations in all groups.

The output is a data frame with one or two columns denoting the fixed factor with levels that match the number of means entered. For rb data, the column for RandFac denotes levels of the blocking factor. The quantitative response variables are in the numeric Values column.

Value

This function produces a data.frame object containing simulated data.

Examples

#Basic usage with two levels within FactorX2, 
#20 experiments with inter-experiment SD 20, and residual SD 15
two_rb_tab <- make_2way_rb_data(c(100, 20), c(200, 300), 20, 20, 15)
str(two_rb_tab)
head(two_rb_tab)

Make one-way or two-way independent group or randomised block design data.

Description

The make_1way_data , make_1way_rb_data , make_2way_data and make_2way_rb_data functions generate independent or randomised block (rb) design data of one-way or two-way designs.

Usage

make_2way_data(Group_1_means, Group_2_means, Num_obs, Residual_SD)

Arguments

Details

Random variates from the normal distribution based on user provided mean and SD provided are generated. For independent designs, the Residual_SD argument is used to set expected residual SD from the linear model. Exp_SD is used to set experiment-to-experiment SD, that will be assigned to the random factor for rb designs.

Num_obs sets the number of independent measurements per group.

For one-way designs, the user provides Group_means as a vector. Number of levels are recognised based on number of means. For two-way designs, two vectors are to be provided by the user containing means of levels of a second factor. Number of means in both vectors should be the same. These functions can only handle balanced designs, i.e. same number of observations in all groups.

The output is a data frame with one or two columns denoting the fixed factor with levels that match the number of means entered. For rb data, the column for RandFac denotes levels of the blocking factor. The quantitative response variables are in the numeric Values column.

Value

This function produces a data.frame object containing simulated data.

Examples

#Basic usage with two levels within FactorX2, 20 observations in each group, with residual SD 15
two_independent_tab <- make_2way_data(c(100, 20), c(200, 300), 20, 15)
#Four levels with 5 observations and residual SD 5
two_independent_tab <- make_2way_data(c(100, 20, 1500, 20), c(150, 5, 1450, 25), 5, 5)

Make one-way or two-way independent group or randomised block design data.

Description

The make_1way_data , make_1way_rb_data , make_2way_data and make_2way_rb_data functions generate independent or randomised block (rb) design data of one-way or two-way designs.

Usage

make_2way_rb_data(Group1_means, Group2_means, Num_exp, Exp_SD, Residual_SD)

Arguments

Details

Random variates from the normal distribution based on user provided mean and SD provided are generated. For independent designs, the Residual_SD argument is used to set expected residual SD from the linear model. Exp_SD is used to set experiment-to-experiment SD, that will be assigned to the random factor (RandFac) for rb designs.

Num_exp sets the number of independent measurements per group.

For one-way designs, the user provides Group_means as a vector. Number of levels are recognised based on number of means. For two-way designs, two vectors are to be provided by the user containing means of levels of a second factor. Number of means in both vectors should be the same. These functions can only handle balanced designs, i.e. same number of observations in all groups.

The output is a data frame with one or two columns denoting the fixed factor with levels that match the number of means entered. For rb data, the column for RandFac denotes levels of the blocking factor. The quantitative response variables are in the numeric Values column.

Value

This function produces a data.frame object containing simulated data.

Examples

#Basic usage with two levels within FactorX2, 
#20 experiments with inter-experiment SD 20, and residual SD 15
two_rb_tab <- make_2way_rb_data(c(100, 20), c(200, 300), 20, 20, 15)
str(two_rb_tab)
head(two_rb_tab)

ANOVA table from linear mixed effects analysis.

Description

One of four related functions for mixed effects analyses (based on lmer and as_lmerModLmerTest ) to get a linear model for downstream steps, or an ANOVA table.

1. mixed_model

2. mixed_anova

3. mixed_model_slopes

4. mixed_anova_slopes.

Usage

mixed_anova(
 data,
 Y_value,
 Fixed_Factor,
 Random_Factor,
 Df_method = "Kenward-Roger",
 SS_method = "II",
 AvgRF = TRUE,
 Formula = NULL,
 ...
)

Arguments

Details

These functions require a data table, one dependent variable (Y_value), one or more independent variables (Fixed_Factor), and at least one random factor (Random_Factor). These should match names of variables in the long-format data table exactly. Since v5.0.0, if AvgRF = TRUE, the response variable is averaged over levels of the fixed and random factors (to collapse replicate observations) and reduce the number of denominator degrees of freedom. If you do not want to do this, set AvgRF = FALSE.

Outputs of mixed_model and mixed_model_slopes can be used for post-hoc comparisons with posthoc_Pairwise , posthoc_Levelwise , posthoc_vsRef , posthoc_Trends_Pairwise , posthoc_Trends_Levelwise and posthoc_Trends_vsRef or with emmeans .

More than one fixed factors can be provided as a vector (e.g. c("A", "B")). A full model with interaction term is fitted. This means when Y_value = Y, Fixed_factor = c("A", "B"), Random_factor = "R" are entered as arguments, these are passed on as Y ~ A*B + (1|R) (which is equivalent to Y ~ A + B + A:B + (1|R)).

In mixed_model_slopes and mixed_anova_slopes, the following kind of formula is used: Y ~ A*B + (S|R) (which is equivalent to Y ~ A + B + A:B + (S|R)). In this experimental implementation, random slopes and intercepts are fitted ((Slopes_Factor|Random_Factor)). Only one term each is allowed for Slopes_Factor and Random_Factor.

Value

ANOVA table of class "anova" and "data.frame".

Examples

#Usage with one fixed (Student) and random factor (Experiment)
mixed_anova(data = data_doubling_time, 
Y_value = "Doubling_time", 
Fixed_Factor = "Student", 
Random_Factor = "Experiment")
#with formula
mixed_anova(data = data_doubling_time, 
Formula = "Doubling_time ~ Student +(1|Experiment)")

ANOVA table from linear mixed effects analysis.

Description

One of four related functions for mixed effects analyses (based on lmer and as_lmerModLmerTest ) to get a linear model for downstream steps, or an ANOVA table.

1. mixed_model

2. mixed_anova

3. mixed_model_slopes

4. mixed_anova_slopes.

Usage

mixed_anova_slopes(
 data,
 Y_value,
 Fixed_Factor,
 Slopes_Factor,
 Random_Factor,
 Df_method = "Kenward-Roger",
 SS_method = "II",
 AvgRF = TRUE,
 ...
)

Arguments

Details

These functions require a data table, one dependent variable (Y_value), one or more independent variables (Fixed_Factor), and at least one random factor (Random_Factor). These should match names of variables in the long-format data table exactly. Since v5.0.0, if AvgRF = TRUE, the response variable is averaged over levels of the fixed and random factors (to collapse replicate observations) and reduce the number of denominator degrees of freedom. If you do not want to do this, set AvgRF = FALSE. If you do not want to do this, set AvgRF = FALSE.

For more advanced models with slopes and intercept, use mixed_model or mixed_anova using the Formula argument.

Outputs of mixed_model and mixed_model_slopes can be used for post-hoc comparisons with posthoc_Pairwise , posthoc_Levelwise , posthoc_vsRef , posthoc_Trends_Pairwise , posthoc_Trends_Levelwise and posthoc_Trends_vsRef or with emmeans .

More than one fixed factors can be provided as a vector (e.g. c("A", "B")). A full model with interaction term is fitted. This means when Y_value = Y, Fixed_factor = c("A", "B"), Random_factor = "R" are entered as arguments, these are passed on as Y ~ A*B + (1|R) (which is equivalent to Y ~ A + B + A:B + (1|R)).

In mixed_model_slopes and mixed_anova_slopes, the following kind of formula is used: Y ~ A*B + (S|R) (which is equivalent to Y ~ A + B + A:B + (S|R)). In this experimental implementation, random slopes and intercepts are fitted ((Slopes_Factor|Random_Factor)). Only one term each is allowed for Slopes_Factor and Random_Factor.

Value

ANOVA table of class "anova" and "data.frame".

Examples

mixed_anova_slopes(data = data_2w_Tdeath,
Y_value = "PI",
Fixed_Factor = c("Genotype", "Time"),
Slopes_Factor = "Time",
Random_Factor = "Experiment")

Model from a linear mixed effects model

Description

One of four related functions for mixed effects analyses (based on lmer and as_lmerModLmerTest ) to get a linear model for downstream steps, or an ANOVA table.

1. mixed_model

2. mixed_anova

3. mixed_model_slopes

4. mixed_anova_slopes.

Usage

mixed_model(
 data,
 Y_value,
 Fixed_Factor,
 Random_Factor,
 AvgRF = TRUE,
 Formula = NULL,
 ...
)

Arguments

Details

These functions require a data table, one dependent variable (Y_value), one or more independent variables (Fixed_Factor), and at least one random factor (Random_Factor). These should match names of variables in the long-format data table exactly. Since v5.0.0, if AvgRF = TRUE, the response variable is averaged over levels of the fixed and random factors (to collapse replicate observations) and reduce the number of denominator degrees of freedom. If you do not want to do this, set AvgRF = FALSE.

Outputs of mixed_model and mixed_model_slopes can be used for post-hoc comparisons with posthoc_Pairwise , posthoc_Levelwise , posthoc_vsRef , posthoc_Trends_Pairwise , posthoc_Trends_Levelwise and posthoc_Trends_vsRef or with emmeans .

More than one fixed factors can be provided as a vector (e.g. c("A", "B")). A full model with interaction term is fitted. This means when Y_value = Y, Fixed_factor = c("A", "B"), Random_factor = "R" are entered as arguments, these are passed on as Y ~ A*B + (1|R) (which is equivalent to Y ~ A + B + A:B + (1|R)).

In mixed_model_slopes and mixed_anova_slopes, the following kind of formula is used: Y ~ A*B + (S|R) (which is equivalent to Y ~ A + B + A:B + (S|R)). In this experimental implementation, random slopes and intercepts are fitted ((Slopes_Factor|Random_Factor)). Only one term each is allowed for Slopes_Factor and Random_Factor.

Value

This function returns an S4 object of class "lmerModLmerTest".

Examples

#one fixed factor and random factor
mixed_model(data = data_doubling_time, 
Y_value = "Doubling_time", 
Fixed_Factor = "Student", 
Random_Factor = "Experiment")
#with formula
mixed_anova(data = data_doubling_time, 
Formula = "Doubling_time ~ Student +(1|Experiment)")
#' #save model
model <- mixed_model(data = data_doubling_time, 
Y_value = "Doubling_time", 
Fixed_Factor = "Student", 
Random_Factor = "Experiment")
#get model summary
summary(model)

Model from a linear mixed effects model with varying slopes

Description

One of four related functions for mixed effects analyses (based on lmer and as_lmerModLmerTest ) to get a linear model for downstream steps, or an ANOVA table.

1. mixed_model

2. mixed_anova

3. mixed_model_slopes

4. mixed_anova_slopes.

Usage

mixed_model_slopes(
 data,
 Y_value,
 Fixed_Factor,
 Slopes_Factor,
 Random_Factor,
 AvgRF = TRUE,
 ...
)

Arguments

Details

These functions require a data table, one dependent variable (Y_value), one or more independent variables (Fixed_Factor), and at least one random factor (Random_Factor). These should match names of variables in the long-format data table exactly. Since v5.0.0, if AvgRF = TRUE, the response variable is averaged over levels of the fixed and random factors (to collapse replicate observations) and reduce the number of denominator degrees of freedom. If you do not want to do this, set AvgRF = FALSE.

For more advanced models with slopes and intercept, use mixed_model or mixed_anova using the Formula argument.

Outputs of mixed_model and mixed_model_slopes can be used for post-hoc comparisons with posthoc_Pairwise , posthoc_Levelwise , posthoc_vsRef , posthoc_Trends_Pairwise , posthoc_Trends_Levelwise and posthoc_Trends_vsRef or with emmeans .

More than one fixed factors can be provided as a vector (e.g. c("A", "B")). A full model with interaction term is fitted. This means when Y_value = Y, Fixed_factor = c("A", "B"), Random_factor = "R" are entered as arguments, these are passed on as Y ~ A*B + (1|R) (which is equivalent to Y ~ A + B + A:B + (1|R)).

In mixed_model_slopes and mixed_anova_slopes, the following kind of formula is used: Y ~ A*B + (S|R) (which is equivalent to Y ~ A + B + A:B + (S|R)). In this experimental implementation, random slopes and intercepts are fitted ((Slopes_Factor|Random_Factor)). Only one term each is allowed for Slopes_Factor and Random_Factor.

Value

This function returns an S4 object of class "lmerModLmerTest".

Examples

#two fixed factors as a vector, 
#exactly one slope factor and random factor
mod <- mixed_model_slopes(data = data_2w_Tdeath,
Y_value = "PI",
Fixed_Factor = c("Genotype", "Time"),
Slopes_Factor = "Time",
Random_Factor = "Experiment")
#get summary
summary(mod)

Plot of mean & error bars for 1-way ANOVAs with matched shapes mapped to blocking factor.

Description

One of 4 related functions for plotting 1-way ANOVA designs with a blocking factor.

1. plot_3d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_3d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_3d_scatterbox (box & whiskers)

4. plot_3d_scatterviolin (box & whiskers, violin)

Usage

plot_3d_point_sd(
 data,
 xcol,
 ycol,
 shapes,
 facet,
 ErrorType = "SD",
 symsize = 3.5,
 s_alpha = 1,
 symshape = 22,
 all_alpha = 0.3,
 all_size = 2.5,
 all_shape = 0,
 all_jitter = 0,
 ewid = 0.2,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 ethick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

The blocking factor (or any other categorical variable) can be mapped to the shapes argument (up to 25 levels allowed). Variables passed to xcol and shapes are internally converted to factors even if they are numeric or other type of variables.

In plot_3d_point_sd and plot_3d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_3d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#3d version for 1-way data with blocking
#use plot_point_sd when no a blocking factor is not used
plot_3d_point_sd(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
shapes = Experiment)

Plot a bar graph for 1-way ANOVAs with matched shapes mapped to blocking factor.

Description

One of 4 related functions for plotting 1-way ANOVA designs with a blocking factor.

1. plot_3d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_3d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_3d_scatterbox (box & whiskers)

4. plot_3d_scatterviolin (box & whiskers, violin)

Usage

plot_3d_scatterbar(
 data,
 xcol,
 ycol,
 shapes,
 facet,
 ErrorType = "SD",
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 1,
 jitter = 0.1,
 ewid = 0.2,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

The blocking factor (or any other categorical variable) can be mapped to the shapes argument (up to 25 levels allowed). Variables passed to xcol and shapes are internally converted to factors even if they are numeric or other type of variables.

In plot_3d_point_sd and plot_3d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_3d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#3d version for 1-way data with blocking
#use plot_scatterbar_sd without blocking factor
plot_3d_scatterbar(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
shapes = Experiment)

Plot a scatter and box plot for 1-way ANOVAs with matched shapes mapped to blocking factor.

Description

One of 4 related functions for plotting 1-way ANOVA designs with a blocking factor.

1. plot_3d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_3d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_3d_scatterbox (box & whiskers)

4. plot_3d_scatterviolin (box & whiskers, violin)

Usage

plot_3d_scatterbox(
 data,
 xcol,
 ycol,
 shapes,
 facet,
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.5,
 jitter = 0.1,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

The blocking factor (or any other categorical variable) can be mapped to the shapes argument (up to 25 levels allowed). Variables passed to xcol and shapes are internally converted to factors even if they are numeric or other type of variables.

In plot_3d_point_sd and plot_3d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_3d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#3d version for 1-way data with blocking
plot_3d_scatterbox(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
shapes = Experiment)
#use plot_scatterbox without a blocking factor

Plot a scatter with violin & box plot for 1-way ANOVAs with matched shapes mapped to blocking factor.

Description

One of 4 related functions for plotting 1-way ANOVA designs with a blocking factor.

1. plot_3d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_3d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_3d_scatterbox (box & whiskers)

4. plot_3d_scatterviolin (box & whiskers, violin)

Usage

plot_3d_scatterviolin(
 data,
 xcol,
 ycol,
 shapes,
 facet,
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 0,
 v_alpha = 1,
 bwid = 0.3,
 vadjust = 1,
 jitter = 0.1,
 TextXAngle = 0,
 scale = "width",
 trim = TRUE,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 vthick,
 bvthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

The blocking factor (or any other categorical variable) can be mapped to the shapes argument (up to 25 levels allowed). Variables passed to xcol and shapes are internally converted to factors even if they are numeric or other type of variables.

In plot_3d_point_sd and plot_3d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_3d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#3d version for 1-way data with blocking
plot_3d_scatterviolin(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
shapes = Experiment)
#use plot_scatterviolin without a blocking factor

Plot mean & error bars for 2-way ANOVAs with or without a blocking factor.

Description

There are 4 related functions for 2-way ANOVA type plots. In addition to a categorical variable along the X-axis, a grouping factor is passed to either points, bars or boxes argument in these functions. A blocking factor (or any other categorical variable) can be optionally passed to the shapes argument.

1. plot_4d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_4d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_4d_scatterbox (box & whiskers)

4. plot_4d_scatterviolin (box & whiskers, violin)

Usage

plot_4d_point_sd(
 data,
 xcol,
 ycol,
 points,
 shapes,
 facet,
 ErrorType = "SD",
 symsize = 3.5,
 s_alpha = 1,
 symshape = 22,
 all_alpha = 0.3,
 all_size = 2.5,
 all_shape = 0,
 all_jitter = 0,
 ewid = 0.2,
 group_wid = 0.8,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 ethick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 ...
)

Arguments

Details

These can be especially useful when the fourth variable shapes is a random factor or blocking factor (up to 25 levels are allowed; there will be an error with more levels). The shapes argument can be left blank to plot ordinary 2-way ANOVAs without blocking.

In plot_4d_point_sd and plot_4d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_4d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#4d version for 2-way data with blocking
plot_4d_point_sd(data = data_2w_Tdeath, 
xcol = Genotype, 
ycol = PI, 
points = Time, 
shapes = Experiment)
#4d version without blocking factor
#`shapes` can be left blank
plot_4d_point_sd(data = data_2w_Festing, 
xcol = Strain, 
ycol = GST, 
points = Treatment)

Plot scatter plot with bar & error bars for 2-way ANOVAs with or without a blocking factor.

Description

There are 4 related functions for 2-way ANOVA type plots. In addition to a categorical variable along the X-axis, a grouping factor is passed to either points, bars or boxes argument in these functions. A blocking factor (or any other categorical variable) can be optionally passed to the shapes argument.

1. plot_4d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_4d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_4d_scatterbox (box & whiskers)

4. plot_4d_scatterviolin (box & whiskers, violin)

Usage

plot_4d_scatterbar(
 data,
 xcol,
 ycol,
 bars,
 shapes,
 facet,
 ErrorType = "SD",
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.7,
 jitter = 0.1,
 ewid = 0.2,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 group_wid = 0.8,
 symthick,
 bthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColRev = FALSE,
 ColSeq = TRUE,
 ...
)

Arguments

Details

These can be especially useful when the fourth variable shapes is a random factor or blocking factor (up to 25 levels are allowed; there will be an error with more levels). The shapes argument can be left blank to plot ordinary 2-way ANOVAs without blocking.

In plot_4d_point_sd and plot_4d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_4d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#4d version for 2-way data with blocking
plot_4d_scatterbar(data = data_2w_Tdeath, 
xcol = Genotype, 
ycol = PI, 
bars = Time, 
shapes = Experiment)
#4d version without blocking factor
#`shapes` can be left blank
plot_4d_scatterbar(data = data_2w_Tdeath, 
xcol = Genotype, 
ycol = PI, 
bars = Time)

Plot scatter, box & whiskers for 2-way ANOVAs with or without a blocking factor.

Description

There are 4 related functions for 2-way ANOVA type plots. In addition to a categorical variable along the X-axis, a grouping factor is passed to either points, bars or boxes argument in these functions. A blocking factor (or any other categorical variable) can be optionally passed to the shapes argument.

1. plot_4d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_4d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_4d_scatterbox (box & whiskers)

4. plot_4d_scatterviolin (box & whiskers, violin)

Usage

plot_4d_scatterbox(
 data,
 xcol,
 ycol,
 boxes,
 shapes,
 facet,
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.7,
 jitter = 0.1,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 group_wid = 0.8,
 symthick,
 bthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 ...
)

Arguments

Details

These can be especially useful when the fourth variable shapes is a random factor or blocking factor (up to 25 levels are allowed; there will be an error with more levels). The shapes argument can be left blank to plot ordinary 2-way ANOVAs without blocking.

In plot_4d_point_sd and plot_4d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_4d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#4d version for 2-way data with blocking
plot_4d_scatterbox(data = data_2w_Tdeath, 
xcol = Genotype, 
ycol = PI, 
boxes = Time, 
shapes = Experiment)
#4d version without blocking factor
#`shapes` can be left blank
plot_4d_scatterbox(data = data_2w_Tdeath, 
xcol = Genotype, 
ycol = PI, 
boxes = Time)

Plot scatter, box & violin for 2-way ANOVAs with or without a blocking factor.

Description

There are 4 related functions for 2-way ANOVA type plots. In addition to a categorical variable along the X-axis, a grouping factor is passed to either points, bars or boxes argument in these functions. A blocking factor (or any other categorical variable) can be optionally passed to the shapes argument.

1. plot_4d_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_4d_scatterbar (bar & SD, SEM or CI95 error bars)

3. plot_4d_scatterbox (box & whiskers)

4. plot_4d_scatterviolin (box & whiskers, violin)

Usage

plot_4d_scatterviolin(
 data,
 xcol,
 ycol,
 boxes,
 shapes,
 facet,
 symsize = 3,
 s_alpha = 0.8,
 v_alpha = 1,
 b_alpha = 0,
 bwid = 0.3,
 vadjust = 1,
 jitter = 0.1,
 TextXAngle = 0,
 scale = "width",
 trim = TRUE,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 group_wid = 0.8,
 symthick,
 bthick,
 vthick,
 bvthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 ...
)

Arguments

Details

These can be especially useful when the fourth variable shapes is a random factor or blocking factor (up to 25 levels are allowed; there will be an error with more levels). The shapes argument can be left blank to plot ordinary 2-way ANOVAs without blocking.

In plot_4d_point_sd and plot_4d_scatterbar, the default error bar is SD (can be changed to SEM or CI95). In plot_4d_point_sd, a large coloured symbol is plotted at the mean, all other data are shown as smaller symbols. Boxplot uses geom_boxplot to depict median (thicker line), box (interquartile range (IQR)) and the whiskers (1.5*IQR).

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#4d version for 2-way data with blocking
plot_4d_scatterviolin(data = data_2w_Tdeath, 
xcol = Genotype, 
ycol = PI, 
boxes = Time, 
shapes = Experiment)
#4d version without blocking factor
#`shapes` can be left blank
plot_4d_scatterviolin(data = data_2w_Tdeath, 
xcol = Genotype, 
ycol = PI, 
boxes = Time)

Before-after style graph with a boxplot

Description

One of 3 related functions to plot matching data joined by lines. The variable containing information for matching (e.g. matched subjects or experiments etc.) is passed to the match argument.

1. plot_befafter_colours or plot_befafter_colors ,

2. plot_befafter_shapes

3. plot_befafter_box

Usage

plot_befafter_box(
 data,
 xcol,
 ycol,
 match,
 facet,
 PlotShapes = FALSE,
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.4,
 jitter = 0.1,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 lthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

In plot_befafter_colours/plot_befafter_colors and plot_befafter_shapes setting Boxplot = TRUE will also plot a box and whiskers plot.

Note that only 25 shapes are available, and there will be errors with plot_befafter_shapes when there are fewer than 25 matched observations; instead use plot_befafter_colours instead.

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

To plot a graph with a single colour along the X axis variable, use the SingleColour argument.

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

plot_befafter_box(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
match = Subject)
#with PlotShapes = TRUE
plot_befafter_box(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
match = Subject, PlotShapes = TRUE)

Plot a before-after plot with lines joining colour-matched symbols.

Description

One of 3 related functions to plot matching data joined by lines. The variable containing information for matching (e.g. matched subjects or experiments etc.) is passed to the match argument.

1. plot_befafter_colours or plot_befafter_colors ,

2. plot_befafter_shapes

3. plot_befafter_box

Usage

plot_befafter_colours(
 data,
 xcol,
 ycol,
 match,
 facet,
 Boxplot = FALSE,
 symsize = 3,
 s_alpha = 1,
 jitter = 0.1,
 bwid = 0.4,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 lthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)
plot_befafter_colors(
 data,
 xcol,
 ycol,
 match,
 facet,
 Boxplot = FALSE,
 symsize = 3,
 s_alpha = 1,
 jitter = 0.1,
 bwid = 0.4,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 lthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

In plot_befafter_colours/plot_befafter_colors and plot_befafter_shapes setting Boxplot = TRUE will also plot a box and whiskers plot.

Note that only 25 shapes are available, and there will be errors with plot_befafter_shapes when there are fewer than 25 matched observations; instead use plot_befafter_colours instead.

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

To plot a graph with a single colour along the X axis variable, use the SingleColour argument.

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#plot without legends if necessary
plot_befafter_colours(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
match = Subject, s_alpha = .9, ColSeq = FALSE)+
guides(fill = "none", 
colour = "none") #remove guides
#plot with boxplot
plot_befafter_colours(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
match = Subject, s_alpha = .9, ColSeq = FALSE,
Boxplot = TRUE)+
guides(fill = "none", 
colour = "none") #remove guides

Plot a before-after plot with lines joining shape-matched symbols.

Description

One of 3 related functions to plot matching data joined by lines. The variable containing information for matching (e.g. matched subjects or experiments etc.) is passed to the match argument.

1. plot_befafter_colours or plot_befafter_colors ,

2. plot_befafter_shapes

3. plot_befafter_box

Usage

plot_befafter_shapes(
 data,
 xcol,
 ycol,
 match,
 facet,
 Boxplot = FALSE,
 symsize = 3,
 s_alpha = 1,
 bwid = 0.4,
 jitter = 0.1,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 lthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

In plot_befafter_colours/plot_befafter_colors and plot_befafter_shapes setting Boxplot = TRUE will also plot a box and whiskers plot.

Note that only 25 shapes are available, and there will be errors with plot_befafter_shapes when there are fewer than 25 matched observations; instead use plot_befafter_colours instead.

Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

To plot a graph with a single colour along the X axis variable, use the SingleColour argument.

The resulting ggplot2 graph can take additional geometries or other layers.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#plot without legends if necessary
plot_befafter_colors(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
match = Subject, s_alpha = .9, ColSeq = FALSE)+
guides(fill = "none", 
colour = "none") #remove guides
#plot with boxplot
plot_befafter_colors(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
match = Subject, s_alpha = .9, ColSeq = FALSE,
Boxplot = TRUE)+
guides(fill = "none", 
colour = "none") #remove guides

Plot density distribution of data.

Description

This function takes a data table, ycol of quantitative variable and a categorical grouping variable (group), if available, and plots a density graph using geom_density ). Alternatives are plot_histogram , or plot_qqline .

Usage

plot_density(
 data,
 ycol,
 group,
 facet,
 PlotType = c("Density", "Counts", "Normalised counts"),
 c_alpha = 0.2,
 TextXAngle = 0,
 facet_scales = "fixed",
 fontsize = 20,
 linethick,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = NULL,
 ...
)

Arguments

Details

Note that the function requires the quantitative Y variable first, and groups them based on an X variable. The group variable is mapped to the fill and colour aesthetics in geom_density . Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

plot_density(data = data_t_pratio, 
ycol = log(Cytokine), group = Genotype)
#with faceting
plot_density(data = data_cholesterol, 
ycol = Cholesterol, group = Treatment, 
facet = Treatment, fontsize = 12)
#Counts
plot_density(data = data_cholesterol, 
ycol = Cholesterol, group = Treatment,
PlotType = "Counts", 
facet = Treatment, fontsize = 12)

Plot a dotplot on a bar graph with SD error bars with two variables.

Description

There are three types of plot_dot_ functions that plot data as "dots" using the geom_dotplot geometry. They all take a data table, a categorical X variable and a numeric Y variable.

1. plot_dotbar_sd (bar & SD, SEM or CI95 error bars)

2. plot_dotbox (box & whiskers)

3. plot_dotviolin (box & whiskers, violin)

Usage

plot_dotbar_sd(
 data,
 xcol,
 ycol,
 facet,
 ErrorType = "SD",
 dotsize = 1.5,
 d_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.5,
 ewid = 0.2,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 dotthick,
 bthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

Related plot_scatter_ variants show data symbols using the geom_point geometry. These are plot_scatterbar_sd (or SEM or CI95 error bars), plot_scatterbox and plot_scatterviolin. Over plotting in plot_scatter variants can be reduced with the jitter argument.

The X variable is mapped to the fill aesthetic of dots, symbols, bars, boxes and violins.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

If you prefer a single colour for the graph, use the SingleColour argument.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

plot_dotbar_sd(data = data_cholesterol, 
xcol = Treatment,
ycol = Cholesterol)
plot_dotbar_sd(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
ColPal = "pale", ColSeq = FALSE, ColRev = TRUE)
#single colour along X
plot_dotbar_sd(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
SingleColour = "light_orange")

Plot a dotplot on a boxplot with two variables.

Description

There are three types of plot_dot_ functions that plot data as "dots" using the geom_dotplot geometry. They all take a data table, a categorical X variable and a numeric Y variable.

1. plot_dotbar_sd (bar & SD, SEM or CI95 error bars)

2. plot_dotbox (box & whiskers)

3. plot_dotviolin (box & whiskers, violin)

Usage

plot_dotbox(
 data,
 xcol,
 ycol,
 facet,
 dotsize = 1.5,
 d_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.5,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 dotthick,
 bthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

Related plot_scatter_ variants show data symbols using the geom_point geometry. These are plot_scatterbar_sd (or SEM or CI95 error bars), plot_scatterbox and plot_scatterviolin. Over plotting in plot_scatter variants can be reduced with the jitter argument.

The X variable is mapped to the fill aesthetic of dots, symbols, bars, boxes and violins.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

If you prefer a single colour for the graph, use the SingleColour argument.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

plot_dotbox(data = data_1w_death, 
xcol = Genotype, ycol = Death)
plot_dotbox(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
ColPal = "vibrant", b_alpha = 0.5)
plot_dotbox(data = data_1w_death, 
xcol = Genotype, ycol = Death, 
SingleColour = "safe_bluegreen", b_alpha = 0.5) 

Plot a dotplot on a violin plot with two variables.

Description

There are three types of plot_dot_ functions that plot data as "dots" using the geom_dotplot geometry. They all take a data table, a categorical X variable and a numeric Y variable.

1. plot_dotbar_sd (bar & SD, SEM or CI95 error bars)

2. plot_dotbox (box & whiskers)

3. plot_dotviolin (box & whiskers, violin)

Usage

plot_dotviolin(
 data,
 xcol,
 ycol,
 facet,
 dotsize = 1.5,
 d_alpha = 0.8,
 b_alpha = 0,
 v_alpha = 1,
 bwid = 0.3,
 vadjust = 1,
 trim = TRUE,
 scale = "width",
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 dotthick,
 bthick,
 vthick,
 bvthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

Related plot_scatter_ variants show data symbols using the geom_point geometry. These are plot_scatterbar_sd (or SEM or CI95 error bars), plot_scatterbox and plot_scatterviolin. Over plotting in plot_scatter variants can be reduced with the jitter argument.

The X variable is mapped to the fill aesthetic of dots, symbols, bars, boxes and violins.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

If you prefer a single colour for the graph, use the SingleColour argument.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#plot with trim = FALSE
plot_dotviolin(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
dotsize = 2, trim = FALSE)
plot_dotviolin(data = data_t_pdiff, 
xcol = Condition, ycol = Mass,
trim = FALSE, b_alpha = 0.5, 
ColPal = "pale", ColSeq = FALSE)
#single colour along X
plot_dotviolin(data = data_t_pdiff, 
xcol = Condition, ycol = Mass,
trim = FALSE, b_alpha = 0.5, 
SingleColour = "pale_cyan")

Plot prediction of gam model

Description

Plot prediction of gam model

Usage

plot_gam_predict(
 Model,
 xcol,
 ycol,
 ByFactor,
 symsize = 1,
 s_alpha = 0.1,
 smooth_alpha = 0.7,
 linethick,
 fontsize = 20,
 ...
)

Arguments

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#fit zooplankton data
z1 <- ga_model(data = data_zooplankton,
Y_value = "log(density_adj)",
Fixed_Factor = "taxon",
Smooth_Factor = "day")
#plot fitted data
plot_gam_predict(Model = z1,
xcol = day, 
ycol = `log(density_adj)`,
ByFactor = taxon)

See grafify colour palettes

Description

This simple function allows quick visualisation of colours in grafify palettes and their hex codes. It uses plot_scatterbar_sd and some arguments are similar and can be adjusted.

Usage

plot_grafify_palette(
 palette = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant", "OrBl_div", "PrGn_div",
 "blue_conti", "grey_conti", "yellow_conti"),
 fontsize = 14,
 ...
)

Arguments

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

plot_grafify_palette("pale")
plot_grafify_palette("contrast")

Plot data distribution as histograms.

Description

This function takes a data table, a quantitative variable (ycol) and a grouping variable (group), if available, and plots a histogram graph using geom_histogram ). Alternatives are plot_density , or plot_qqline .

Usage

plot_histogram(
 data,
 ycol,
 group,
 facet,
 PlotType = c("Counts", "Normalised counts"),
 BinSize = 30,
 c_alpha = 0.8,
 TextXAngle = 0,
 facet_scales = "fixed",
 fontsize = 20,
 linethick,
 alpha,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = NULL,
 ...
)

Arguments

Details

Note that the function requires the quantitative Y variable first, and groups them based on a categorical variable passed on via the group argument. The grouping variable is mapped to the fill aesthetics in geom_histogram .

ColPal & ColRev options are applied to both fill and colour scales. Colours available can be seen quickly with plot_grafify_palette . Colours can be changed using ColPal, ColRev or ColSeq arguments. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#Basic usage
plot_histogram(data = data_t_pratio, 
ycol = Cytokine, group = Genotype, 
BinSize = 10)
#with log transformation
plot_histogram(data = data_t_pratio, 
ycol = log(Cytokine), group = Genotype, 
BinSize = 10)
#Normalised counts
plot_histogram(data = data_t_pratio, 
ycol = log(Cytokine), group = Genotype, 
PlotType = "Normalised counts", 
BinSize = 10)

Plot data and predictions from linear model

Description

This function takes a linear model, and up to three variables and plots observe data (circles) and model predictions (squares). If the X-variable is categorical, a box and whiskers plot is overlaid. A variable (ByFactor) can be used for faceting.

Usage

plot_lm_predict(
 Model,
 xcol,
 ycol,
 ByFactor,
 obs_size = 2,
 obs_alpha = 0.3,
 pred_size = 2,
 pred_alpha = 0.8,
 linethick,
 base_size = 15,
 ...
)

Arguments

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#fit a model
deathm1 <- mixed_model(data_2w_Tdeath, 
"PI", c("Genotype", "Time"), 
"Experiment")
#plot model
plot_lm_predict(deathm1,
Genotype, PI, Time)
#fit zooplankton data
z1 <- ga_model(data = data_zooplankton,
Y_value = "log(density_adj)",
Fixed_Factor = "taxon",
Smooth_Factor = "day")
#plot fitted data
plot_lm_predict(Model = z1,
xcol = day, 
ycol = `log(density_adj)`,
ByFactor = taxon)

Add log transformations to graphs

Description

This function allows "log10" or "log2" transformation of X or Y axes. With "log10" transformation, log10 ticks are also added on the outside.

Usage

plot_logscale(
 Plot,
 LogYTrans = "log10",
 LogXTrans,
 LogYBreaks = waiver(),
 LogXBreaks = waiver(),
 LogYLimits = NULL,
 LogXLimits = NULL,
 LogYLabels = waiver(),
 LogXLabels = waiver(),
 fontsize = 22,
 ...
)

Arguments

Details

Arguments allow for axes limits, breaks and labels to passed on.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#save a ggplot object
P <- ggplot(data_t_pratio, 
aes(Genotype,Cytokine))+
geom_jitter(shape = 21, 
size = 5, width = .2, 
aes(fill = Genotype), 
alpha = .7)
#transform Y axis
plot_logscale(Plot = P)
#or in one go 
plot_logscale(ggplot(data_t_pratio, 
aes(Genotype,Cytokine))+
geom_jitter(shape = 21, 
size = 5, width = .2, 
aes(fill = Genotype), 
alpha = .7))

Plot a point as mean with SD error bars using two variables.

Description

There are 4 related functions that use geom_point to plot a categorical variable along the X axis.

1. plot_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_scatterbar_sd (bar & SD, SEM or CI95 error bars)

3. plot_scatterbox (box & whiskers)

4. plot_scatterviolin (box & whiskers, violin)

Usage

plot_point_sd(
 data,
 xcol,
 ycol,
 facet,
 ErrorType = "SD",
 symsize = 3.5,
 s_alpha = 1,
 symshape = 22,
 all_alpha = 0.3,
 all_size = 2.5,
 all_shape = 1,
 all_jitter = 0,
 ewid = 0.2,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 ethick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

These functions take a data table, categorical X and numeric Y variables, and plot various geometries. The X variable is mapped to the fill aesthetic of symbols.

In plot_point_sd and plot_scatterbar_sd, default error bars are SD, which can be changed to SEM or CI95.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

If there are many groups along the X axis and you prefer a single colour for the graph,use the SingleColour argument.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#Basic usage
plot_point_sd(data = data_doubling_time, 
xcol = Student, ycol = Doubling_time)

Plot model diagnostics for generalised additive models

Description

This is a clone of the appraise function in the gratia package (rewritten to avoid depending on gratia package for these plots). This function will plot 4 diagnostic plots when given a generalised additive model fitted with ga_model or mgcv. It creates graphs that use grafify colours and theme_grafify().

Usage

plot_qq_gam(
 Model,
 symsize = 2,
 s_colour = "#E69F00",
 s_alpha = 0.6,
 line_col = "black",
 base_size = 12,
 linethick,
 n_bins = c("sturges", "scott", "fd")
)

Arguments

Value

This function returns an object of classes "ggplot" and "gg".

This function returns a ggplot2 object of class "gg" and "ggplot".

Plot quantile-quantile (QQ) graphs from data.

Description

This function takes a data table, a quantitative variable (ycol), and a categorical grouping variable (group), if available, and plots a QQ graph using stat_qq and stat_qq_line . Alternatives are plot_histogram , or plot_qqline .

Usage

plot_qqline(
 data,
 ycol,
 group,
 facet,
 symsize = 3,
 s_alpha = 0.8,
 TextXAngle = 0,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 linethick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 ...
)

Arguments

Details

Note that the function requires the quantitative Y variable first, and a grouping variable as group if required. The graph plots sample quantiles on Y axis & theoretical quantiles on X axis. The X variable is mapped to the fill aesthetic instat_qq and colour aesthetic for the stat_qq_line .

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . When only one level is present within group, symbols will receive "ok_orange" colour. ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

plot_qqline(data = data_cholesterol, 
ycol = Cholesterol, group = Treatment)

Plot quantile-quantile (QQ) graphs from residuals of linear models.

Description

This function takes a linear model (simple or mixed effects) and plots a QQ graph after running rstudent from rstudent to generate a table of Studentised model residuals on an ordinary (simple_model ), mixed model (mixed_model or mixed_model_slopes . The graph plots studentised residuals from the model (sample) on Y axis & Theoretical quantiles on X axis.

Usage

plot_qqmodel(
 Model,
 symsize = 3,
 s_alpha = 0.8,
 fontsize = 20,
 symthick,
 linethick,
 SingleColour = "#E69F00"
)

Arguments

Details

For generalised additive models fit with mgcv, scaled Pearson residuals are plotted.

The function uses geom_qq and geom_qq_line geometries. Symbols receive "ok_orange" colour by default.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#Basic usage
m1 <- simple_model(data = data_2w_Festing, 
Y_value = "GST", 
Fixed_Factor = c("Treatment", "Strain"))
plot_qqmodel(m1)

Plot scatter dots on a bar graph with SD error bars with two variables.

Description

There are 4 related functions that use geom_point to plot a categorical variable along the X axis.

1. plot_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_scatterbar_sd (bar & SD, SEM or CI95 error bars)

3. plot_scatterbox (box & whiskers)

4. plot_scatterviolin (box & whiskers, violin)

Usage

plot_scatterbar_sd(
 data,
 xcol,
 ycol,
 facet,
 ErrorType = "SD",
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.5,
 ewid = 0.3,
 jitter = 0.1,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

These functions take a data table, categorical X and numeric Y variables, and plot various geometries. The X variable is mapped to the fill aesthetic of symbols.

In plot_point_sd and plot_scatterbar_sd, default error bars are SD, which can be changed to SEM or CI95.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

If you prefer a single colour for the graph, use the SingleColour argument.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#with jitter
plot_scatterbar_sd(data = data_cholesterol, 
xcol = Treatment, ycol = Cholesterol)
plot_scatterbar_sd(data = data_doubling_time, 
xcol = Student, ycol = Doubling_time,
SingleColour = "ok_grey")

Plot a scatter plot on a boxplot with two variables.

Description

There are 4 related functions that use geom_point to plot a categorical variable along the X axis.

1. plot_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_scatterbar_sd (bar & SD, SEM or CI95 error bars)

3. plot_scatterbox (box & whiskers)

4. plot_scatterviolin (box & whiskers, violin)

Usage

plot_scatterbox(
 data,
 xcol,
 ycol,
 facet,
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 1,
 bwid = 0.5,
 jitter = 0.1,
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 Ylabels = waiver(),
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

These functions take a data table, categorical X and numeric Y variables, and plot various geometries. The X variable is mapped to the fill aesthetic of symbols.

In plot_point_sd and plot_scatterbar_sd, default error bars are SD, which can be changed to SEM or CI95.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

If you prefer a single colour for the graph, use the SingleColour argument.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

plot_scatterbox(data = data_cholesterol, 
xcol = Treatment, ycol = Cholesterol)
plot_scatterbox(data = data_doubling_time, 
xcol = Student, ycol = Doubling_time,
SingleColour = "ok_grey")

Plot a scatter plot on a violin plot with two variables.

Description

There are 4 related functions that use geom_point to plot a categorical variable along the X axis.

1. plot_point_sd (mean & SD, SEM or CI95 error bars)

2. plot_scatterbar_sd (bar & SD, SEM or CI95 error bars)

3. plot_scatterbox (box & whiskers)

4. plot_scatterviolin (box & whiskers, violin)

Usage

plot_scatterviolin(
 data,
 xcol,
 ycol,
 facet,
 symsize = 3,
 s_alpha = 0.8,
 b_alpha = 0,
 v_alpha = 1,
 bwid = 0.3,
 vadjust = 1,
 jitter = 0.1,
 trim = TRUE,
 scale = "width",
 TextXAngle = 0,
 LogYTrans,
 LogYBreaks = waiver(),
 LogYLabels = waiver(),
 LogYLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 symthick,
 bthick,
 vthick,
 bvthick,
 Ylabels = waiver(),
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 SingleColour = "NULL",
 ...
)

Arguments

Details

These functions take a data table, categorical X and numeric Y variables, and plot various geometries. The X variable is mapped to the fill aesthetic of symbols.

In plot_point_sd and plot_scatterbar_sd, default error bars are SD, which can be changed to SEM or CI95.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

If you prefer a single colour for the graph, use the SingleColour argument.

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#plot without jitter
plot_scatterviolin(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
symsize = 2, trim = FALSE)
#no symbols
plot_scatterviolin(data = data_t_pdiff, 
xcol = Condition, ycol = Mass, 
s_alpha = 0,
symsize = 2, trim = FALSE)

Plot points on a quantitative X - Y plot & a categorical grouping variable.

Description

This function takes a data table, quantitative X and Y variables along with a categorical grouping variable, and a and plots a graph with using geom_point . The categorical CatGroup variable is mapped to the fill aesthetic of symbols.

Usage

plot_xy_CatGroup(
 data,
 xcol,
 ycol,
 CatGroup,
 facet,
 Boxplot = FALSE,
 Mean = FALSE,
 ErrorType = "SD",
 symsize = 3,
 s_alpha = 0.8,
 TextXAngle = 0,
 LogYTrans,
 LogXTrans,
 LogYBreaks = waiver(),
 LogXBreaks = waiver(),
 LogYLabels = waiver(),
 LogXLabels = waiver(),
 LogYLimits = NULL,
 LogXLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 bwid = 0.3,
 b_alpha = 0.3,
 l_alpha = 0.8,
 e_alpha = 0.8,
 all_size = 2,
 all_alpha = 0.5,
 symthick,
 bthick,
 ethick,
 ewid = 0.2,
 ColPal = c("okabe_ito", "all_grafify", "bright", "contrast", "dark", "fishy", "kelly",
 "light", "muted", "pale", "r4", "safe", "vibrant"),
 ColSeq = TRUE,
 ColRev = FALSE,
 ...
)

Arguments

Details

A box and whisker plot with lines joining the medians can be plotted with Boxplot = TRUE. If only box plot is needed without the line, set the opacity of the line to 0 (i.e., l_alpha = 0).

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

This plot is related to plot_xy_NumGroup which requires a numeric grouping factor. When summary statistics (mean/median) are required, use plot_3d_scatterbar , plot_3d_scatterbox or plot_4d_scatterbox .

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#The grouping factor cyl is automatically converted to categorical variable
plot_xy_CatGroup(data = mtcars,
xcol = mpg, ycol = disp, CatGroup = cyl, 
ColPal = "vibrant", ColSeq = FALSE)
#with boxplot
plot_xy_CatGroup(data = mpg, 
xcol = cyl, ycol = cty, 
CatGroup = fl, Boxplot = TRUE)
#add another variable
#with boxplot
plot_xy_CatGroup(data = mpg, 
xcol = cyl, ycol = cty, 
CatGroup = fl, facet = drv,
Boxplot = TRUE)

Plot points on a quantitative X - Y plot & a grouping variable.

Description

This function takes a data table, quantitative X and Y variables along with a grouping variable that is either categorical or numeric. The colour of data symbols is mapped to the grouping variable. This function is related to plot_xy_CatGroup and plot_xy_NumGroup , and could eventually replace them in future updates.

Central value and scatter can be shown by choosing the ErrorType argument. Mean and error bars (SD, SEM or CI95) or box and whisker plot options are available.

Usage

plot_xy_Group(
 data,
 xcol,
 ycol,
 Group,
 facet,
 ErrorType = c("none", "SD", "SEM", "CI95", "Boxplot"),
 SmoothType = c("none", "Loess", "Linear"),
 symsize = 3,
 s_alpha,
 TextXAngle = 0,
 mean_size,
 m_alpha = 1,
 LogYTrans,
 LogXTrans,
 LogYBreaks = waiver(),
 LogXBreaks = waiver(),
 LogYLabels = waiver(),
 LogXLabels = waiver(),
 LogYLimits = NULL,
 LogXLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 bwid = 0.3,
 b_alpha = 0.3,
 l_alpha = 0.8,
 sm_alpha = 0.3,
 symthick,
 bthick,
 ewid = 0.1,
 e_alpha = 1,
 ColPal = NULL,
 ColSeq = TRUE,
 ColRev = FALSE,
 ...
)

Arguments

Details

When ErrorType is set to a value other than none, a line joining the central value (mean or median, respectively) will also appear (set l_alpha = 0 if this is not desired). Other options for ErrorType are: SD, SEM, CI95, Boxplot.

When SD/SEM/CI95 are chosen, the mean value will appear as a larger square symbol. Its opacity and size can be adjusted with m_alpha and mean_size, respectively.

The smooth fitted line type can be shown with the SmoothType argument, which can take the following options: none, Linear or Loess. Latter two options are fitted using stat_smooth with lm or loess options, respectively.

Colours can be changed using ColPal, ColRev or ColSeq arguments. Colours available can be seen quickly with plot_grafify_palette . ColPal can be one of the following: "okabe_ito", "dark", "light", "bright", "pale", "vibrant, "muted" or "contrast". ColRev (logical TRUE/FALSE) decides whether colours are chosen from first-to-last or last-to-first from within the chosen palette. ColSeq (logical TRUE/FALSE) decides whether colours are picked by respecting the order in the palette or the most distant ones using colorRampPalette .

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#The grouping factor cyl is automatically converted to categorical variable
plot_xy_Group(data = mpg,
xcol = cyl, ycol = cty, Group = drv,
ErrorType = "SD")
#with a Linear smooth line
plot_xy_Group(data = mpg,
xcol = cyl, ycol = cty, Group = drv,
ErrorType = "SD", SmoothType = "Linear")
 

Plot points on a quantitative X - Y plot & a numeric grouping variable.

Description

This function takes a data table, quantitative X and Y variables, and a numeric grouping variable, and a and plots a graph with using geom_point . The numerical NumGroup variable is mapped to the fill aesthetic of symbols, which receives the scale_fill_grafify default quantitative palette (blue_conti). Alternatives are yellow_conti, grey_conti, OrBl_div and PrGn_div. Colour order can be reversed with ColRev = TRUE (default is FALSE).

Usage

plot_xy_NumGroup(
 data,
 xcol,
 ycol,
 NumGroup,
 facet,
 Boxplot = FALSE,
 symsize = 3,
 s_alpha = 0.8,
 TextXAngle = 0,
 LogYTrans,
 LogXTrans,
 LogYBreaks = waiver(),
 LogXBreaks = waiver(),
 LogYLabels = waiver(),
 LogXLabels = waiver(),
 LogYLimits = NULL,
 LogXLimits = NULL,
 facet_scales = "fixed",
 fontsize = 20,
 bwid = 0.3,
 b_alpha = 0.3,
 l_alpha = 0.8,
 symthick,
 bthick,
 ColPal = c("blue_conti", "yellow_conti", "grey_conti", "PrGn_div", "OrBl_div"),
 ColRev = FALSE,
 ...
)

Arguments

Details

This plot is related to plot_xy_CatGroup which requires a categorical grouping factor. When summary statistics (mean/median) are required, use plot_3d_scatterbar , plot_3d_scatterbox or plot_4d_scatterbox .

Value

This function returns a ggplot2 object of class "gg" and "ggplot".

Examples

#The grouping factor gear is numeric 
plot_xy_NumGroup(data = mtcars,
xcol = mpg, ycol = disp, NumGroup = cyl,
s_alpha = 0.8)
#change colour palette
plot_xy_NumGroup(data = mtcars,
xcol = mpg, ycol = disp, NumGroup = cyl,
s_alpha = 0.8, 
ColPal = "grey_conti")

Level-wise post-hoc comparisons from a linear or linear mixed effects model.

Description

This function is a wrapper based on emmeans , and needs a ordinary linear model produced by simple_model or a mixed effects model produced by mixed_model or mixed_model_slopes (or generated directly with lm, lme4 or lmerTest calls). It also needs to know the fixed factor(s), which should match those in the model and data table.

Usage

posthoc_Levelwise(Model, Fixed_Factor, P_Adj = "fdr", Factor, ...)

Arguments

Details

The function will generate level-wise comparisons (as described in Comparisons and contrasts in emmeans), i.e. comparison between of every level of one factor separately at each level of the other factor. By default, P values are corrected by the FDR method (which can be changed). If the model was fit by transforming the quantitative response variable using "log", "logit", "sqrt" etc., results will still be on the original scale, i.e. type = "response" is the default; data will be back-transformed (check results to confirm this), and for log or logit see Transformations and link functions in emmeans, ratios will be compared. The first part of the emmeans results has the estimated marginal means, SE and CI ($emmeans), which are generated from the fitted model, and not the original data table. The second part has the results of the comparisons ($contrasts).

Value

returns an "emm_list" object containing contrasts and emmeans through emmeans .

Examples

#make a linear model first
CholMod <- mixed_model(data = data_cholesterol, 
Y_value = "Cholesterol", 
Fixed_Factor = c("Hospital", "Treatment"),
Random_Factor = "Subject") 
#note Fixed_Factor needs a vector or variable in quotes
#to get comparisons between different hospitals separately for each level of Treatment
posthoc_Levelwise(Model = CholMod, 
Fixed_Factor = c("Hospital", "Treatment"))
#get comparisons between treatments separately at each hospital
posthoc_Levelwise(Model = CholMod, 
Fixed_Factor = c("Treatment", "Hospital"))

Pairwise post-hoc comparisons from a linear or linear mixed effects model.

Description

This function is a wrapper based on emmeans , and needs a ordinary linear model produced by simple_model or a mixed effects model produced by mixed_model or mixed_model_slopes (or generated directly with lm, lme4 or lmerTest calls). It also needs to know the fixed factor(s), which should match those in the model and data table.

Usage

posthoc_Pairwise(Model, Fixed_Factor, P_Adj = "fdr", Factor, ...)

Arguments

Details

The function will generate pairwise comparisons of every level of every factor (as described in Comparisons and contrasts in emmeans). Too many comparisons will be generated and only use this when necessary. By default, P values are corrected by the FDR method (which can be changed). If the model was fit by transforming the quantitative response variable using "log", "logit", "sqrt" etc., results will still be on the original scale, i.e. type = "response" is the default; data will be back-transformed (check results to confirm this), and for log or logit see Transformations and link functions in emmeans, ratios will be compared. The first part of the emmeans results has the estimated marginal means, SE and CI ($emmeans), which are generated from the fitted model, and not the original data table. The second part has the results of the comparisons ($contrasts).

Value

returns an "emm_list" object containing contrasts and emmeans through emmeans .

Examples

#make linear models first
DoublMod <- simple_model(data = data_doubling_time, 
Y_value = "Doubling_time", Fixed_Factor = "Student") 
#mixed model
CholMod <- mixed_model(data = data_cholesterol, 
Y_value = "Cholesterol",
Fixed_Factor = c("Hospital", "Treatment"), 
Random_Factor = "Subject") 
posthoc_Pairwise(Model = DoublMod, 
Fixed_Factor = "Student")
#basic use with two Fixed_Factor provided as a vector
posthoc_Pairwise(Model = CholMod, 
Fixed_Factor = c("Treatment", "Hospital"))
#same call with "tukey" adjustment
posthoc_Pairwise(Model = CholMod, 
Fixed_Factor = c("Treatment", "Hospital"), 
P_adj = "tukey")

Use emtrends to get level-wise comparison of slopes from a linear model.

Description

This function is a wrapper based on emmeans , and needs a ordinary linear model produced by simple_model or a mixed effects model produced by mixed_model or mixed_model_slopes (or generated directly with lm, lme4 or lmerTest calls). At least one of the factors should be a numeric covariate whose slopes you wish to find. It also needs to know the fixed factor(s), which should match those in the model and data table.

Usage

posthoc_Trends_Levelwise(
 Model,
 Fixed_Factor,
 Trend_Factor,
 P_Adj = "sidak",
 ...
)

Arguments

Details

Checkout the Interactions with covariates section in the emmeans vignette for more details. One of the independent variables should be a quantitative (e.g. time points) variable whose slope (trend) you want to find at levels of the other factor.

Value

returns an "emm_list" object containing slopes and their contrasts calculated through emtrends .

Examples

#create an lm model 
#Time2 is numeric (time points)
m1 <- simple_model(data = data_2w_Tdeath, 
Y_value = "PI", Fixed_Factor = c("Genotype", "Time2"))
posthoc_Trends_Levelwise(Model = m1, 
Fixed_Factor = "Genotype", 
Trend_Factor = "Time2")

Use emtrends to get pairwise comparison of slopes from a linear model.

Description

This function is a wrapper based on emmeans , and needs a ordinary linear model produced by simple_model or a mixed effects model produced by mixed_model or mixed_model_slopes (or generated directly with lm, lme4 or lmerTest calls). At least one of the factors should be a numeric covariate whose slopes you wish to find. It also needs to know the fixed factor(s), which should match those in the model and data table.

Usage

posthoc_Trends_Pairwise(
 Model,
 Fixed_Factor,
 Trend_Factor,
 P_Adj = "sidak",
 ...
)

Arguments

Details

Checkout the Interactions with covariates section in the emmeans vignette for more details. One of the independent variables should be a quantitative (e.g. time points) variable whose slope (trend) you want to find at levels of the other factor.

Value

returns an "emm_list" object containing slopes and their contrasts calculated through emtrends .

Examples

#create an lm model 
#Time2 is numeric (time points)
m1 <- simple_model(data = data_2w_Tdeath, 
Y_value = "PI", Fixed_Factor = c("Genotype", "Time2"))
posthoc_Trends_Pairwise(Model = m1, 
Fixed_Factor = "Genotype", 
Trend_Factor = "Time2")

Use emtrends to get level-wise comparison of slopes from a linear model.

Description

This function is a wrapper based on emmeans , and needs a ordinary linear model produced by simple_model or a mixed effects model produced by mixed_model or mixed_model_slopes (or generated directly with lm, lme4 or lmerTest calls). At least one of the factors should be a numeric covariate whose slopes you wish to find. It also needs to know the fixed factor(s), which should match those in the model and data table.

Usage

posthoc_Trends_vsRef(
 Model,
 Fixed_Factor,
 Trend_Factor,
 Ref_Level = 1,
 P_Adj = "sidak",
 ...
)

Arguments

Details

Checkout the Interactions with covariates section in the emmeans vignette for more details. One of the independent variables should be a quantitative (e.g. time points) variable whose slope (trend) you want to find at levels of the other factor.

Value

returns an "emm_list" object containing slopes and their contrasts calculated through emtrends .

Examples

#create an lm model 
#Time2 is numeric (time points)
m1 <- simple_model(data = data_2w_Tdeath, 
Y_value = "PI", Fixed_Factor = c("Genotype", "Time2"))
posthoc_Trends_vsRef(Model = m1, 
Fixed_Factor = "Genotype", 
Trend_Factor = "Time2", 
Ref_Level = 2)

Post-hoc comparisons to a control or reference group.

Description

This function is a wrapper based on emmeans , and needs a ordinary linear model produced by simple_model or a mixed effects model produced by mixed_model or mixed_model_slopes (or generated directly with lm, lme4 or lmerTest calls). It also needs to know the fixed factor(s), which should match those in the model and data table.

Usage

posthoc_vsRef(Model, Fixed_Factor, Ref_Level = 1, P_Adj = "fdr", Factor, ...)

Arguments

Details

The function will generate treatment vs control type of comparisons (as described in Comparisons and contrasts in emmeans), i.e. comparison of each level of a factor to a reference level, which is set by default to the first level in the factor (Ref_Level = 1). By default, P values are corrected by the FDR method (which can be changed). If the model was fit by transforming the quantitative response variable using "log", "logit", "sqrt" etc., results will still be on the original scale, i.e. type = "response" is the default; data will be back-transformed (check results to confirm this), and for log or logit see Transformations and link functions in emmeans, ratios will be compared. The first part of the emmeans results has the estimated marginal means, SE and CI ($emmeans), which are generated from the fitted model, and not the original data table. The second part has the results of the comparisons ($contrasts).

Value

returns an "emm_list" object containing contrasts and emmeans through emmeans .

Examples

#make linear models first
DoublMod <- simple_model(data = data_doubling_time,
Y_value = "Doubling_time", 
Fixed_Factor = "Student") 
CholMod <- mixed_model(data = data_cholesterol, 
Y_value = "Cholesterol", 
Fixed_Factor = c("Hospital", "Treatment"),
Random_Factor = "Subject") 
#to compare all students with student #9
posthoc_vsRef(Model = DoublMod, 
Fixed_Factor = "Student", Ref_Level = 9)
#for comparison between hospital_a to every other hospital, separately at levels of Treatment
posthoc_vsRef(Model = CholMod, 
Fixed_Factor = c("Hospital", "Treatment"), Ref_Level = 1)

scale_colour_ and scale_fill_ functions

Description

These let you apply grafify discrete or continuous palettes as fill or colour aesthetics to any ggplot2 (scale_color_ spelling is also accepted).

Usage

scale_colour_grafify(
 palette = "okabe_ito",
 ColSeq = TRUE,
 reverse = FALSE,
 discrete = TRUE,
 ...
)
scale_color_grafify(
 palette = "okabe_ito",
 ColSeq = TRUE,
 reverse = FALSE,
 discrete = TRUE,
 ...
)

Arguments

Details

The default is palette = "okabe_ito". The discrete argument is not used at present. The following discrete and quantitative palettes can be used.

Categorical/discreet palettes:

• okabe_ito (default)

• bright

• contrast

• dark

• kelly

• light

• muted

• pale

• r4

• safe

• vibrant

By default, sequential colours from above palettes will be chosen. To choose the most distant colours set ColSeq = TRUE.

Sequential quantitative palettes:

• grey_conti

• blue_conti

• yellow_conti

Divergent quantitative palettes:

• OrBl_div

• PrGn_div

Value

ggplot scale_fill function for discrete colours.

Examples

#add a grafify fill scheme to ggplot
ggplot(emmeans::neuralgia, aes(x = Treatment, 
 y = Duration))+
 geom_boxplot(aes(fill = Treatment), 
 alpha = .6)+
 geom_point(aes(colour = Treatment,
 shape = Treatment), 
 size = 3)+
 scale_fill_grafify(palette = "bright")+
 scale_colour_grafify(palette = "bright")+
 facet_wrap("Sex")+
 theme_classic()
#distant colours `ColSeq = FALSE` 
ggplot(emmeans::neuralgia, aes(x = Treatment, 
 y = Duration))+
 geom_boxplot(aes(fill = Treatment), 
 alpha = .6)+
 geom_point(aes(colour = Treatment,
 shape = Treatment), 
 size = 3)+
 scale_fill_grafify(palette = "bright",
 ColSeq = FALSE)+
 scale_colour_grafify(palette = "bright",
 ColSeq = FALSE)+
 facet_wrap("Sex")+
 theme_classic()
#quantitative colour scheme
ggplot(mtcars, aes(x = disp,
 y = mpg))+
 geom_point(aes(colour = cyl), 
 size = 3)+
 scale_colour_grafify(palette = "blue_conti")

scale_colour_ and scale_fill_ functions

Description

These let you apply grafify discrete or continuous palettes as fill or colour aesthetics to any ggplot2 (scale_color_ spelling is also accepted).

Usage

scale_fill_grafify(
 palette = "okabe_ito",
 ColSeq = TRUE,
 reverse = FALSE,
 discrete = TRUE,
 ...
)

Arguments

Details

The default is palette = "okabe_ito". The discrete argument is not used at present. The following discrete and quantitative palettes can be used.

Categorical/discreet palettes:

• okabe_ito (default)

• bright

• contrast

• dark

• kelly

• light

• muted

• pale

• r4

• safe

• vibrant

By default, sequential colours from above palettes will be chosen. To choose the most distant colours set ColSeq = TRUE.

Sequential quantitative palettes:

• grey_conti

• blue_conti

• yellow_conti

Divergent quantitative palettes:

• OrBl_div

• PrGn_div

Value

ggplot scale_fill function for discrete colours.

Examples

#add a grafify fill scheme to ggplot
ggplot(emmeans::neuralgia, aes(x = Treatment, 
 y = Duration))+
 geom_boxplot(aes(fill = Treatment), 
 alpha = .6)+
 geom_point(aes(colour = Treatment,
 shape = Treatment), 
 size = 3)+
 scale_fill_grafify(palette = "bright")+
 scale_colour_grafify(palette = "bright")+
 facet_wrap("Sex")+
 theme_classic()
#distant colours `ColSeq = FALSE` 
ggplot(emmeans::neuralgia, aes(x = Treatment, 
 y = Duration))+
 geom_boxplot(aes(fill = Treatment), 
 alpha = .6)+
 geom_point(aes(colour = Treatment,
 shape = Treatment), 
 size = 3)+
 scale_fill_grafify(palette = "bright",
 ColSeq = FALSE)+
 scale_colour_grafify(palette = "bright",
 ColSeq = FALSE)+
 facet_wrap("Sex")+
 theme_classic()
#quantitative colour schemes
ggplot(mtcars, aes(x = disp,
 y = mpg))+
 geom_point(aes(colour = cyl), 
 size = 3)+
 scale_colour_grafify(palette = "blue_conti")

ANOVA table from a linear model fit to data.

Description

One of two functions for simple ANOVA tables and linear models without random effects, which use lm to fit a linear models.

1. link{simple_anova}

2. link{simple_model}

Usage

simple_anova(data, Y_value, Fixed_Factor, ...)

Arguments

Details

Update in v0.2.1: This function uses lm to fit a linear model to data, passes it on to Anova , and outputs the ANOVA table with type II sum of squares with F statistics and P values. (Previous versions produced type I sum of squares using anova call.)

It requires a data table, one quantitative dependent variable and one or more independent variables. If your experiment design has random factors, use the related function mixed_anova .

This function is related to link{simple_model}.

Value

ANOVA table of class "anova" and "data.frame".

Examples

#Basic usage 
simple_anova(data = data_doubling_time, 
Y_value = "Doubling_time", 
Fixed_Factor = "Student")

Model from a linear model fit to data.

Description

One of two functions for simple ANOVA tables and linear models without random effects, which use lm to fit a linear models.

1. link{simple_anova}

2. link{simple_model}

Usage

simple_model(data, Y_value, Fixed_Factor, ...)

Arguments

Details

Update in v0.2.1: This function uses lm to fit a linear model to data, passes it on to Anova , and outputs the ANOVA table with type II sum of squares with F statistics and P values.

(Previous versions produced type I sum of squares using anova call.) It requires a data table, one quantitative dependent variable and one or more independent variables.

The model output can be used to extract coefficients and other information, including post-hoc comparisons. If your experiment design has random factors, use the related function mixed_model .

This function is related to link{simple_anova}. Output of this function can be used with posthoc_Pairwise , posthoc_Levelwise and posthoc_vsRef , or with emmeans .

Value

This function returns an object of class "lm".

Examples

#fixed factors provided as a vector
Doubmodel <- simple_model(data = data_doubling_time,
Y_value = "Doubling_time", 
Fixed_Factor = "Student")
#get summary
summary(Doubmodel)

Get numeric summary grouped by factors

Description

This is a wrapper around aggregate function in base R to obtain mean, median, standard deviation and count for quantitative variable(s) grouped by one or more factors. More than one column containing of quantitative variables can be passed on, and summaries for each is provided with column names with a ..

Usage

table_summary(data, Ycol, ByGroup)

Arguments

Value

this function takes in a data.frame or tibble and returns a data.frame or tibble.

Examples

table_summary(Ycol = "cty",
ByGroup = c("fl", "drv"),
data = mpg)

Reordering groups along X-axis

Description

This simple function takes in a data table and reorders groups (categorical variables or factors) to be plotted along the X-axis in a user-defined order.

Usage

table_x_reorder(data, xcol, OrderX, ...)

Arguments

Details

It uses two base R functions: as.factor to first force the user-selected column into a factor, and factor that reorders levels based on a user-provided vector.

Value

This function returns a data frame with a selected column converted into factor with reordered levels.

Examples

#reorder levels within Genotype
new_data <- table_x_reorder(data_t_pratio, 
xcol = "Genotype", 
OrderX = c("KO", "WT"))
#compare 
plot_scatterbox(data_t_pratio, 
Genotype, 
Cytokine)
#with
plot_scatterbox(new_data, 
Genotype, 
Cytokine)
#also works within the plot call
plot_scatterbox(data = table_x_reorder(data_t_pratio, 
xcol = "Genotype", 
OrderX = c("KO", "WT")), 
xcol = Genotype, 
ycol = Cytokine)

A modified theme_classic() for grafify-like graphs.

Description

This is a slightly modified theme_classic with two key differences: no border & background for facet panel labels, and font size of text on axes is the same as that of the axes titles (prior to v3.2.0, this was 0.85 times the base font size). The size of text legend title is also same as base font.

Usage

theme_grafify(
 base_size = 20,
 base_family = "",
 base_line_size = base_size/22,
 base_rect_size = base_size/22,
 TextXAngle = 0,
 vjust = 0,
 hjust = 0,
 ...
)

Arguments

Details

Since v3.2.0, theme_grafify produces transparent backgrounds.

Value

this returns an output with class "theme" and "gg".

Examples

ggplot(mpg, aes(drv, cty, colour = fl))+
geom_jitter(width = 0.2, 
size = 3, alpha = .7)+
theme_grafify()