Title: Spatio-Temporal Finite Mixture Model using 'TMB'

Version: 0.1.0

Description: Fits a spatio-temporal finite mixture model using 'TMB'. Covariate, spatial and temporal random effects can be incorporated into the gating formula using multinomial logistic regression, the expert formula using a generalized linear mixed model framework, or both.

License: GPL-3

URL: https://github.com/Andrea-Havron/clustTMB, https://andrea-havron.github.io/clustTMB/

BugReports: https://github.com/Andrea-Havron/clustTMB/issues

Depends: R (≥ 4.0.0)

Imports: cluster, clustMixType, fmesher, lme4, Matrix, mclust, methods, reformulas, MoEClust, sf, stats, TMB (≥ 1.9.0)

Suggests: bookdown, covr, cowplot, dplyr, FMsmsnReg, GGally, ggplot2, ggspatial, giscoR, inlabru, kableExtra, knitr, magrittr, MixSim, mvnfast, mvtnorm, palmerpenguins, rmarkdown, sdmTMB, sp, spData, splancs, testthat, tidyr, tweedie, wesanderson

LinkingTo: RcppEigen, TMB

VignetteBuilder: knitr

Encoding: UTF-8

NeedsCompilation: yes

RoxygenNote: 7.3.2

SystemRequirements: GNU make

Packaged: 2024年10月09日 22:38:03 UTC; andrea.havron

Author: Andrea M. Havron ORCID iD [aut, cre, cph]

Maintainer: Andrea M. Havron <andrea.havron@noaa.gov>

Repository: CRAN

Date/Publication: 2024年10月14日 11:50:46 UTC

clustTMB(
 response = NULL,
 expertformula = ~1,
 gatingformula = ~1,
 expertdata = NULL,
 gatingdata = NULL,
 family = gaussian(link = "identity"),
 Offset = NULL,
 G = 2,
 rr = list(spatial = NULL, temporal = NULL, random = NULL),
 covariance.structure = NULL,
 Start = list(),
 Map = list(),
 initialization.args = list(control = init.options()),
 spatial.list = list(loc = NULL, mesh = NULL, init.range = list(gating.range = NULL,
 expert.range = NULL)),
 projection.dat = NULL,
 control = run.options()
)

response

A numeric vector, matrix, or data frame of observations. When data are multivariate, rows correspond to observations and columns correspond to the multivariate response.

expertformula

Formula defining expert model. This formula corresponds to the covariates included in the response densities. Defaults to intercept only (~1) when no covariates are used.

gatingformula

Formula defining gating model. This formula corresponds to the covariates included in the mixing proportions (logistic regression). Defaults to intercept only (~1) when no covariates are used. When a random effects term is included in the gating network, this formula will be updated so that the intercept term is removed.

expertdata

Data frame containing expert model covariates.

gatingdata

Data frame containing gating model covariates.

family

Statistical distribution and link function of observations.

Offset

Constant in expertformula only used to offset density expectation.

G

Integer specifying the number of clusters.

rr

List specifying dimension of rank reduction in spatial, temporal, and/or random effects. Dimension must be smaller than the total dimension of the response. Rank reduction is applied only to the expertformula random effects. The rank reduction reduces the dimensionality of a correlated multivariate response to a smaller dimension independent response. When used, the covariance structure of the response is switched to 'Diagonal.' Defaults to NULL, no rank reduction. If rank reduction is used in conjunction with a random effect, that random effect must also be specified in the expert formula. Currently, rank reduction on temporal random effects is disabled.

covariance.structure

A character string specifying the covariance structure of the response using mclust naming scheme. See description of modelNames under ?Mclust for details.

Start

Set initial values for random effects parameters (fixed and random terms)

Map

Vector indicating parameter maps, see ?TMB::MakeADFun() for details. Defaults in clustTMB control this map argument and user input is limited

initialization.args

A list consisting of initialization settings used to generate initial values. control Calls init.options() to generate settings for initial values. Arguments of init.options() can be specified by the user.

1. init.method - Single character string indicating initial clustering method. Methods include: hc, quantile, random, mclust, kmeans, mixed, user. Defaults to 'hc'. In the case where data are univariate and there are no covariates in the gating/expert formula, this defaults to 'quantile'

2. hc.options - Named list of two character strings specifying hc modelName and hcUse when init.method = 'hc'. The default modelName is 'VVV' and the default use is 'SVD' unless gating/expert covariates specified, in which case default in VARS. See ?mclust::mclust.options for complete list of options.

3. mix.method - String stating initialization method for mixed-type data (init.method = 'mixed'). Current default when Tweedie family specified. Options include: Gower kmeans (default), Gower hclust, and kproto.

4. user - Numeric or character vector defining user specified initial classification. init.method must be set to 'user' when using this option.

spatial.list

List of data objects needed when fitting a spatial GMRF model

projection.dat

Spatial Points class of projection coordinates or Spatial Points Dataframe containing projection coordinates and projection covariates

control

List controlling whether models are run and whether standard errors are calculated.

data("faithful")
m1 <- clustTMB(response = faithful, covariance.structure = "VVV")
plot(faithful$eruptions, faithful$waiting, pch = 16, col = m1$report$classification + 1)

## S3 method for class 'clustTMB'
coef(object, complete = FALSE, ...)

object

The fitted clustTMB model

complete

Currently ignored

...

Currently ignored

## S3 method for class 'clustTMB'
extractAIC(fit, scale, k = 2, ...)

fit

The fitted clustTMB model

scale

The scale, currently ignored

k

Penalization parameter, defaults to 2

...

Currently ignored

fixStruct.names()

fixStruct.names()

init.options(
 init.method = "hc",
 hc.options = list(modelName = "VVV", use = "SVD"),
 exp.init = list(mahala = TRUE),
 mix.method = "Gower kmeans",
 user.class = integer()
)

init.method

Name of method used to set initial values. If init.method = 'user', must define 'user.class' with a classification vector.

hc.options

Model names and use when init.method is 'hc' following conventions of mclust::mclust.options()

exp.init

Turn on mahala initialization when expert network

mix.method

Initialization methods when data are mixed. Default method when data are Tweedie distributed.

user.class

Vector of classification vector set by user and required when init.method = 'user'

init.options()
init.options(init.method = "hc")
init.options(init.method = "mixed")
init.options(init.method = "user", user.class = c(1, 1, 2, 1, 3, 3, 1, 2))

## S3 method for class 'clustTMB'
logLik(object, ...)

object

The fitted clustTMB model

...

Currently ignored

lognormal(link = "identity")

link

link function association with family

fam <- lognormal()
fam$family
fam$link

mkInitClass(n.g, n.i, n.j, control, y)

n.g

Number of clusters

n.i

Number of observations

n.j

Number of columns

control

Classification settings from init.options()

y

Observations

data("faithful")
mkInitClass(2, nrow(faithful), ncol(faithful), init.options(), faithful)

parm.lookup()

parm.lookup()

## S3 method for class 'clustTMB'
print(x, ...)

x

The fitted clustTMB model

...

Not used

run.options(check.input = NULL, run.model = NULL, do.sdreport = NULL)

check.input

TRUE: Return initial values before running TMB

run.model

FALSE: Return TMB object before optimizing model

do.sdreport

TRUE: Run delta method to obtain standard errors

run.options()

setup.projDat(mesh, projection.dat, expert.formula, gating.formula)

mesh

spatial constrained Delaunay triangulation derived from the fmesher R package

projection.dat

Spatial Points class of projection coordinates or Spatial Points Dataframe containing projection coordinates and projection covariates

expert.formula

Formula defining expert model. This formula corresponds to the covariates included in the response densities. Defaults to intercept only (~1) when no covariates are used.

gating.formula

Formula defining gating model. This formula corresponds to the covariates included in the mixing proportions (logistic regression). Defaults to intercept only (~1) when no covariates are used. When a random effects term is included in the gating network, this formula will be updated so that the intercept term is removed.

setup.spatialDat(n.i, spatial.list, projection.dat)

n.i

number of observations

spatial.list

list of spatial locations and mesh

projection.dat

Points class of projection coordinates or Spatial Points Dataframe containing projection coordinates and projection covariates

skewness(x)

x

numeric vector of values for which skewness is calculated

skewness(rgamma(100, 1, 1))

spdeStruct(mesh)

mesh

mesh object generated from fmesher::fm_rcdt_2d() or fmesher::fm_mesh_2d()

splitForm(
 formula,
 defaultTerm = "norm",
 allowFixedOnly = TRUE,
 allowNoSpecials = TRUE,
 debug = FALSE
)

formula

a formula containing special random effect terms

defaultTerm

default type for non-special RE terms

allowFixedOnly

(logical) are formulas with no RE terms OK?

allowNoSpecials

(logical) are formulas with only standard RE terms OK?

debug

(logical) debug?

splitForm(~x+y) ## no specials or RE
splitForm(~x+y+(f|g)) ## no specials
splitForm(~x+y+diag(f|g)) ## one special
splitForm(~x+y+(diag(f|g))) ## 'hidden' special
splitForm(~x+y+(f|g)+cs(1|g)) ## combination
splitForm(~x+y+(1|f/g)) ## 'slash'; term
splitForm(~x+y+(1|f/g/h)) ## 'slash'; term
splitForm(~x+y+(1|(f/g)/h)) ## 'slash'; term
splitForm(~x+y+(f|g)+cs(1|g)+cs(a|b,stuff)) ## complex special
splitForm(~(((x+y)))) ## lots of parentheses
splitForm(~1+rr(f|g,n=2))

## S3 method for class 'clustTMB'
summary(
 object,
 select = c("all", "fixed", "random", "report"),
 p.value = FALSE,
 ...
)

object

The fitted clustTMB model

select

Parameter classes to select. Can be any subset of "fixed" (\hat{\theta}), "random" (\hat{u}) or "report" (\phi(\hat{u},\hat{\theta)}) using notation as TMB::sdreport() .

p.value

Add column with approximate p-values

...

Currently ignored

tweedie(link = "log")

link

link function association with family

fam <- tweedie()
fam$family
fam$link