DImodelsVis (version 1.0.4)

model_selection_data: Prepare data for visualising model selection

Description

The data preparation function for visualising model selection. The output of this function can be passed to the model_selection_plot function for showing a visual comparison between the information criteria for different models. It is also possible to visualise a breakup of the information criteria into deviance (goodness-of-fit) and penalty terms for each model.

Usage

model_selection_data(
  models,
  metric = c("AIC", "BIC", "AICc", "BICc", "deviance"),
  sort = FALSE,
  breakup = FALSE,
  model_names = names(models)
)

Value

A data-frame with multiple columns containing values of several information criteria for each model specified in `models`.

model_name

An identifier name for each model object to be shown on X-axis.

deviance

The deviance values for each model object.

logLik

The -2*Log-Likelihood values for each model object.

AIC

The Akaike information criteria (AIC) values for each model object.

BIC

The Bayesian information criteria (BIC) values for each model object.

AICc

The corrected AIC (AICc) values for each model object.

BICc

The corrected BIC (BICc) values for each model object.

Component

The names of the components to be shown in the plot.

Value

The values for the components to be shown in the plot.

Arguments

models

List of statistical regression model objects.

metric

Metric used for comparisons between models. Takes values from c("AIC", "BIC", "AICc", "BICc", "logLik"). Can choose a single or multiple metrics for comparing the different models.

sort

A boolean value indicating whether to sort the model from highest to lowest value of chosen metric.

breakup

A boolean value indicating whether to breakup the metric value into deviance (defined as -2*loglikelihood) and penalty components. Will work only if a single metric out of "AIC", "AICc", "BIC", or "BICc" is chosen to plot.

model_names

A character string describing the names to display on X-axis for each model in order they appear in the models parameter.

Examples

## Fit different candidate models
mod1 <- lm(mpg ~ disp, data = mtcars)
mod2 <- lm(mpg ~ disp + hp, data = mtcars)
mod3 <- lm(mpg ~ disp + hp + wt, data = mtcars)
mod4 <- lm(mpg ~ disp + hp + wt + carb, data = mtcars)

## Group models into list
models_list <- list("Model 1" = mod1, "Model 2" = mod2,
                    "Model 3" = mod3, "Model 4" = mod4)

## Prepare data for visualisation
## Specific metric
model_selection_data(models = models_list,
                     metric = c("AIC"))

## Multiple metrics can be plotted together as well
model_selection_data(models = models_list,
                     metric = c("AIC", "BIC"))

## If single metric is specified then breakup of metric
## between goodness of fit and penalty can also be visualised
model_selection_data(models = models_list,
                     metric = c("AICc"),
                     breakup = TRUE)

## Sort models
model_selection_data(models = models_list,
                     metric = c("AICc"),
                     breakup = TRUE, sort = TRUE)

## If multiple metrics are specified then sorting
## will be done on first metric specified in list (AIC in this case)
model_selection_data(models = models_list,
                     metric = c("AIC", "BIC", "AICc", "BICc"), sort = TRUE)