Skip to main content\(\require{cancel}
\newcommand{\lt}{<}
\newcommand{\gt}{>}
\newcommand{\amp}{&}
\definecolor{fillinmathshade}{gray}{0.9}
\newcommand{\fillinmath}[1]{\mathchoice{\colorbox{fillinmathshade}{$\displaystyle \phantom{\,#1\,}$}}{\colorbox{fillinmathshade}{$\textstyle \phantom{\,#1\,}$}}{\colorbox{fillinmathshade}{$\scriptstyle \phantom{\,#1\,}$}}{\colorbox{fillinmathshade}{$\scriptscriptstyle\phantom{\,#1\,}$}}}
\)
Section 9.12 Key Takeaways
-
Logistic Regression predicts the
probability of a categorical (binary) outcome.
-
Instead of fitting a straight line, it models the
log-odds of the outcome.
-
Coefficients tell us how each variable changes the
log-odds of the event.
-
Positive coefficients increase the odds; negative ones decrease them.
-
We exponentiate coefficients (exp()) to interpret them as
odds ratios.
-
Example: An odds ratio of 1.50 means 50% higher odds of the outcome.
-
AUC (Area Under the Curve) tells how well the model separates the two groups:
-
0.5 = no skill, 0.7–0.8 = good, 0.8–0.9 = great, >0.9 = excellent.
-
Accuracy can be misleading when classes are imbalanced — check sensitivity and specificity instead.
-
ROC curves and confusion matrices help visualize model performance.
-
Logistic regression is a gateway to machine learning — it’s the foundation for classification models in predictive analytics.
