Section 9.14 Key Functions & Commands
The following functions and commands are introduced or reinforced in this chapter to support logistic regression modeling, classification, and model evaluation.
-
glm()(stats)-
Fits generalized linear models, including logistic regression when using the binomial family.
-
-
summary()(base R)-
Summarizes logistic regression output, including coefficients, standard errors, and p-values.
-
-
exp()(base R)-
Converts log-odds coefficients into odds ratios for interpretation.
-
-
predict()(stats)-
Generates predicted probabilities or classifications from a fitted logistic regression model.
-
-
sample.split()(caTools)-
Splits data into training and testing sets for model validation.
-
-
confusionMatrix()(caret)-
Evaluates classification performance using accuracy, sensitivity, specificity, and related metrics.
-
-
pR2()(pscl)-
Computes pseudo R² measures (e.g., McFadden’s R²) for logistic regression models.
-
-
varImp()(caret)-
Assesses the relative importance of predictors in a classification model.
-
-
vif()(car)-
Detects multicollinearity among predictors using variance inflation factors.
-
-
roc()(pROC)-
Constructs a Receiver Operating Characteristic (ROC) curve to evaluate classification performance.
-
-
auc()(pROC)-
Calculates the Area Under the ROC Curve (AUC) as a summary measure of model discrimination.
-
