Logistic regression for binary response variables Space shuttle example • n = 24 space shuttle launches prior to Challenger disaster on January 27, 1986 • Response y is an indicator variable – y = 1 if O-ring failures during launch – y = 0 if no O-ring failures during launch • Predictor x1 is launch temperature, in degrees Fahrenheit Space shuttle example Plot of Failure versus Temperature Failure Yes No 1.0 0.5 0.0 50 60 70 Temperature 80 A model The mean of a binary response If there are 20% smokers and 80% non-smokers, and Yi = 1, if smoker and 0, if non-smoker, then: E Yi (1)(0.20) (0)(0.80) 0.20 P Yi 1 If pi = P (Yi = 1) and 1 – pi = P (Yi = 0), then: E Yi (1)( pi ) (0)(1 pi ) pi P Yi 1 A linear regression model for a binary response If the simple linear regression model is: Yi 0 1 xi i for Yi = 0, 1 Then, the mean response … E Yi P Yi 1 0 1 xi … is the probability that Yi = 1 when the level of the predictor variable is xi. Space shuttle example Regression Plot failure = 2.43729 - 0.0306883 temp S = 0.414476 R-Sq = 23.8 % R-Sq(adj) = 20.3 % Probability of Failure 1.0 0.5 0.0 50 60 70 Temperature 80 (Simple) logistic regression function exp x i pi P Yi 1 1 exp x i exp 10 0.1x i pi P Yi 1 1 exp 10 0.1x i E(Y) = p 1.0 0.5 0.0 50 100 X 150 exp 10 0.1x i pi P Yi 1 1 exp 10 0.1x i E(Y) = p 1.0 0.5 0.0 50 100 X 150 Space shuttle example exp 10.8 0.17 x i ˆpi Pˆ Yi 1 1 exp 10.8 0.17 x i Probability of failure 1.0 0.5 0.0 50 60 70 Temperature 80 Alternative formulation of (simple) logistic regression function exp x i pi P Yi 1 1 exp x i (algebra) pi ln 1 pi “logit” xi Space shuttle example pˆ i ln 1 pˆ i 2 10.8 0.17 xi 1 Logit 0 -1 -2 -3 50 60 70 Temperature 80 Interpretation of slope coefficients Odds If there are 20% smokers and 80% non-smokers: 0.80 Odds 4 0.20 and ln Odds ln 4 1.39 “Odds are 4 to 1” … 4 non-smokers to 1 smoker. If pi = P (Yi = 1) and 1 – pi = P (Yi = 0), then: pi Odds 1 pi and pi ln Odds ln 1 pi Odds ratio MALE: 20% smokers and 80% non-smokers: 0.80 OddsM 4 0.20 4 OR 2.67 1.5 FEMALE: 40% smokers and 60% non-smokers: 0.60 OddsF 1.5 0.40 The odds that a male is a nonsmoker is 2.67 times the odds that a female is a nonsmoker. Odds ratio Group 2 Group 1 Odds1 pi|1 1 pi|1 Odds2 pi | 2 1 pi | 2 The odds ratio pi|1 pi | 2 Odds1 OR Odds2 1 pi|1 1 pi|2 Space shuttle example Predicted odds: pˆ i exp 10.8 0.17 x i 1 pˆ i Predicted odds at x1 = 55 degrees: pˆ i|55 exp 10.8 0.1755 4.263 1 pˆ i|55 Predicted odds at x1 = 80 degrees: pˆ i|80 exp 10.8 0.1780 0.06081 1 pˆ i|80 Space shuttle example Predicted odds ratio for x1 = 55 relative to x1 = 80: pˆ i|55 pˆ i|80 exp 10.8 0.1755 4.263 76 1 pˆ i|55 1 pˆ i|80 exp 10.8 0.1780 0.06081 The odds of O-ring failure at 55 degrees Fahrenheit is 76 times the odds of O-ring failure at 80 degrees Fahrenheit! Interpretation of slope coefficients The ratio of the odds at X1 = A relative to the odds at X1 = B (for fixed values of other X’s) is: Odds A exp A1 exp 1 A B OddsB exp B1 Estimation of logistic regression coefficients Maximum likelihood estimation • Choose as estimates of the parameters the values that assign the highest probability to (“maximize likelihood of”) the observed outcome. exp 10 0.15 x i Suppose pi P Yi 1 1 exp 10 0.15 x i For first observation, Y1 = 1 and x1 = 53: exp 10 0.15(53) P Y1 1 0.886 1 exp 10 0.15(53) … for second observation, Y2 = 1 and x2 = 56: exp 10 0.15(56) P Y2 1 0.832 1 exp 10 0.15(56) … and for 24th observation, Y24 = 0 and x24 = 81: P Y24 0 1 exp 10 0.15(81) 0.896 1 exp 10 0.15(81) If α = 10 and β = -0.15, what is the probability of observed outcome? The likelihood of the observed outcome is: P Y1 1, Y2 1,..., Y24 0 P Y1 1 P Y2 1 ... P Y24 0 0.886 0.832 ... 0.896 4.82 10 6 The log likelihood of the observed outcome is: ln P Y1 1, Y2 1,..., Y24 0 ln P Y1 1 P Y2 1 ... P Y24 0 ln 0.886 ln 0.832 ... ln 0.896 12.24 Maximum likelihood estimation • Choose as estimates of the parameters the values that assign the highest probability to (“maximize likelihood of”) the observed outcome. exp 10.8 0.17 x i Suppose pi P Yi 1 1 exp 10.8 0.17 x i For first observation, Y1 = 1 and x1 = 53: exp 10.8 0.17(53) P Y1 1 0.857 1 exp 10.8 0.17(53) … for second observation, Y2 = 1 and x2 = 56: exp 10.8 0.17(56) P Y2 1 0.782 1 exp 10.8 0.17(56) … and for 24th observation, Y24 = 0 and x24 = 81: P Y24 0 1 exp 10.8 0.17(81) 0.951 1 exp 10.8 0.17(81) If α = 10.8 and β = -0.17, what is the probability of observed outcome? The likelihood of the observed outcome is: P Y1 1, Y2 1,..., Y24 0 P Y1 1 P Y2 1 ... P Y24 0 0.857 0.782 ... 0.951 9.97 10 6 The log likelihood of the observed outcome is: ln P Y1 1, Y2 1,..., Y24 0 ln P Y1 1 P Y2 1 ... P Y24 0 ln 0.857 ln 0.782 ... ln 0.951 11.52 Space shuttle example Link Function: Logit Response Information Variable failure Value 1 0 Total Count 7 17 24 (Event) Logistic Regression Table Predictor Coef SE Coef Z P Constant 10.875 5.703 1.91 0.057 temp -0.17132 0.08344 -2.05 0.040 Odds Ratio 0.84 95% CI Lower Upper 0.72 0.99 Properties of MLEs • If a model is correct and the sample size is large enough: – MLEs are essentially unbiased. – Formulas exist for estimating the standard errors of the estimators. – The estimators are about as precise as any nearly unbiased estimators. – MLEs are approximately normally distributed. Test and confidence intervals for single coefficients Inference for βj Test statistic: Z Confidence interval: ˆ j j se ˆ j follows approximate standard normal distribution. ˆ j z / 2 se ˆ j Space shuttle example Link Function: Logit Response Information Variable failure Value 1 0 Total Count 7 17 24 (Event) Logistic Regression Table Predictor Coef SE Coef Z P Constant 10.875 5.703 1.91 0.057 temp -0.17132 0.08344 -2.05 0.040 Odds Ratio 0.84 95% CI Lower Upper 0.72 0.99 Space shuttle example • There is sufficient evidence, at the α = 0.05 level, to conclude that temperature is related to the probability of O-ring failure. • For every 1-degree increase in temperature, the odds ratio of O-ring failure to O-ring non-failure is estimated to be 0.84 (95% CI is 0.72 to 0.99). Survival in the Donner Party • In 1846, Donner and Reed families traveled from Illinois to California by covered wagon. • Group became stranded in eastern Sierra Nevada mountains when hit by heavy snow. • 40 of 87 members died from famine and exposure. • Are females better able to withstand harsh conditions than are males? Survival in the Donner Party Probability of survival 0.9 0.8 0.7 Female 0.6 0.5 0.4 0.3 Male 0.2 0.1 0.0 15 25 35 45 Age 55 65 Survival in the Donner Party Link Function: Logit Response Information Variable STATUS Value SURVIVED DIED Total Count 20 25 45 (Event) Logistic Regression Table Predictor Coef SE Coef Z P Constant 1.633 1.110 1.47 0.141 AGE -0.07820 0.03729 -2.10 0.036 Gender 1.5973 0.7555 2.11 0.034 Odds Ratio 0.92 4.94 95% CI Lower Upper 0.86 1.12 0.99 21.72