Statistical Modeling Task

A Statistical Modeling Task is a model-based learning task where the predictor function is a probability function (typically from a statistical model family).

• AKA: Probabilistic Data Analysis, Probabilistic Model Training.
• Context:
  • It can be solved by a Statistical Modeling System with a statistical modeling capability (that applies a statistical modeling algorithm).
  • It can range from being a Parametric Statistical Modeling Task to being a Non-Parametric Statistical Modeling Task.
  • It can range from being a Manual Statistical Modeling Task to being an Automated Statistical Modeling Task.
  • It can range from being an Exploratory Statistical Modeling Task to being a Confirmatory Statistical Modeling Task.
• Example(s):
  • Bayesian Modeling.
  • ...
• Counter-Example(s):
  • an Instance-based Learning Task.
  • a Machine Learning Task.
• See: Probabilistic Analysis, Data Mining, Mathematical Modeling, Probabilistic Language Modeling.

References

2003

• (Davison, 2003) ⇒ Anthony C. Davison. (2003). "Statistical Models." Cambridge University Press. ISBN:0521773393
  • QUOTE: The key idea in statistical modelling is to treat the data as the outcome of a random experiment.

    The fundamental idea of statistical modelling is to treat data as the observed values of random variables.

1999

• (Hoeting et al., 1999) ⇒ Jennifer A. Hoeting, David Madigan, Adrian E. Raftery, and Chris T. Volinsky. (1999). "Bayesian Model Averaging: A Tutorial." In: Statistical science.
  • QUOTE: Standard statistical practice ignores model uncertainty. Data analysts typically select a model from some class of models and then proceed as if the selected model had generated the data.

• Concept