In a logistic regression predicting whether a customer will churn (1 = churn, 0 = stay), the estimated coefficient for monthly charges (in dollars) is β^=0.03\hat\beta = 0.03β^=0.03. Which statement correctly describes the effect of a \$10 increase in monthly charges on the odds of churning?
The odds of churning increase by 3%.
The odds of churning increase by a factor of e0.3≈1.35e^{0.3} \approx 1.35e0.3≈1.35.
The odds of churning increase by a factor of e0.03≈1.03e^{0.03} \approx 1.03e0.03≈1.03.
The probability of churning increases by 30%.
Unlock full course notes by signing up
Logistic Regression: difficulty 4
Using the fitted model from the figure, ln(p1−p)=−4+0.8x\ln\left(\dfrac{p}{1-p}\right) = -4 + 0.8xln(1−pp)=−4+0.8x, what is the minimum number of study hours xxx (to one decimal place) needed so that the predicted probability of passing is at least 0.95?
Give your answer in hours.
The fitted logistic model ln(p/(1−p))=−4+0.8x\ln(p/(1-p)) = -4 + 0.8xln(p/(1−p))=−4+0.8x produces an S-shaped probability curve. The dashed lines mark the point where the predicted probability equals 0.50, which occurs at x=5x = 5x=5 hours studied.