Logistic regression model

Practicing Statistics Interview Questions in R

Zuzanna Chmielewska

Actuary

Logistic regression's application

spam

financial fraud

binary data points

$$f(x) = \frac{1}{1+e^{-x}} $$

$$f(x) = \frac{1}{1+e^{-x}} \in (0,1)$$

Probability prediction: $$ p_i = P(y_i=1) = \frac{1}{1+e^{-(\beta_0+\beta_1 \cdot x_{i1}+...+\beta_p \cdot x_{ip})}} $$

Logit prediction: $$ l_i = ln(\frac{p_i}{1-p_i}) = \beta_0+\beta_1 \cdot x_{i1}+...+\beta_p \cdot x_{ip}$$

a prediction of binary data points

model <- glm(y ~ x, data = df, family = "binomial")

model <- glm(y ~ x, data = df, family = "binomial")
predict(model, newdata = new_df, type = "response")

Practicing Statistics Interview Questions in R