plot_bf is used for plotting values of approximate Bayes factors for models on the nested path created by DMR, stepDMR or DMR4glm algorithm with respect to the best model selected by the procedure. Bayes factors are approximated using values of BIC calculated by the function.
stepDMR
(Package: DMR) :
Stepwise Delete or Merge Regressors
Stepwise DMR is a backward model selection procedure which simultaneously deletes continuous variables and merges levels of factors. It is a stepwise version of DMR, where in every step the values of squared t-statistics are recalculated. The final model is selected by minimization of generalized information criterion in the nested family of models.
● Data Source:
CranContrib
● Keywords: model selection
● Alias: stepDMR
●
0 images
roc is used for calculating measures of performance such as sensitivity and specificity when the true and predicted models can be described using linear hypotheses.
DMR4glm
(Package: DMR) :
Delete or Merge Regressors for Generalized Linear Models
DMR4glm is a backward model selection procedure which simultaneously deletes continuous variables and merges levels of factors. It is a generalization of DMR onto generalized linear models, where instead of squared t-statistics, squared Wald statistics are used. The final model is selected by minimization of generalized information criterion in the nested family of models.
● Data Source:
CranContrib
● Keywords: model selection
● Alias: DMR4glm
●
0 images
DMR is a stepwise backward model selection procedure which simultaneously deletes continuous variables and merges levels of factors. It is based on ranking linear hypotheses with squared t-statistics, using hierarchical clustering for each categorical variable. The final model is selected by minimization of generalized information criterion in the nested family of models.
● Data Source:
CranContrib
● Keywords: model selection
● Alias: DMR
●
0 images
A backward selection procedure called delete or merge regressors (DMR) combines deleting continuous variables with merging levels of factors. The method assumes greedy search among linear models with set of constraints of two types: either a parameter for a continuous variable is set to zero or parameters corresponding to two levels of a factor are compared. DMR is a stepwise regression procedure, where in each step a new constraint is added according to ranking of the hypotheses based on squared t-statistics. As a result a nested family of linear models is obtained and the final decision is made according to minimization of the generalized information criterion (GIC, default BIC). The main function of the package is DMR, which is based on hierarchical clustering. Moreover, other functions for extensions of DMR method are given, such as stepDMR which is based on recalculation of t-statistics in each step and function DMR4glm for generalized linear models.