plot.modelSampler: Graphical analysis of modelSampler

In tanujitdey/modelSampler: A unique tool for variable selection and model exploration in linear regression model

Description

Graphical analysis of the object created by modelSampler.

Usage

    plot.modelSampler(x,...)

Arguments

x	An object of class modelSampler, created by the function modelSampler. See below.
...	Further arguments passed to or from other methods.

Details

Five plots are produced. Going from top to bottom, left to right:

(1) modelSampler estimates a complexity parameter. A Complexity Plot indicating the range of estimated complexity parameters, thus allowing the user to interpret the dimensionality of model space. A higher complexity value characterizes a larger model.

(2) A Penalization Plot depicting FPE values as a function of dimension.

(3) A Dimensionality Plot depicting model size visited by modelSampler.

(4) An Image Plot for visualization of models sampled as a function of the number of Monte Carlo iterations. The importance of a variable can be indirectly assessed by this plot.

(5) A Coverage Plot depicting the probability of visiting a new model at each iteration.

Author(s)

Tanujit Dey [e-mail]

References

Dey, T. (2013). modelSampler: An R Tool for Variable Selection and Model Exploration in Linear Regression. Journal of Data Science, 11(2), 371-387.

See Also

boot.modelSampler, modelSampler, print.modelSampler, print.boot.modelSampler, plot.icicle, plot.FPE, plot.var.stability, plot.ooberror.

Examples

  data(Pollute, package = "modelSampler") 
  ms.out <- modelSampler(MortRate~., Pollute, n.iter1=2500, 
  n.iter2=2500, verbose=TRUE)
  plot.modelSampler(ms.out)

tanujitdey/modelSampler documentation built on May 5, 2019, 11:01 p.m.