logitClassificationTable: Logit Classification Table

In dnepple/tprstats: TSB Statistics Package

Logit Classification Table

Description

Logit Classification Table. p_cutoff may be specified by user. If p_cutoff is unspecified, the p_cutoff is set equal to the mean of the predicted probabilities.

Usage

logitClassificationTable(mylogit, myvar, data, p_cutoff = NULL)

Arguments

mylogit	Logit regression.
myvar	name of the dependent variable. Use quotes.
data	data.
p_cutoff	predicted probabilities greater than the p_cutoff are classified as 1, and 0 otherwise.

Details

The following table displays the results from the command from an example. The default p_cutoff is the mean of the predicted values. The tabulation of results is interpreted as follows: 83 values of myvar were correctly predicted to be 0, 401 values were correctly predicted to be 1, 81 values were incorrectly predicted to be 0, and 43 values were incorrectly predicted to be 1.

p_cutoff is 0.53266667

Summary	Actual	Predicted	Freq
Correct	0	0	83
Incorrect	1	0	81
Incorrect	0	1	43
Correct	1	1	401

dnepple/tprstats documentation built on April 5, 2025, 6:18 a.m.