D Question 19 On large data sets, BIC generally penalizes complexity more than AIC and Mallow's Cp. True False D Question 20 1.5 pts The logit link is the only link function that yields s-shaped curves used to model binary response data. O True FalseD Question 21 2 pts Mary has a dataset with height (in inches), weight (in Ibs), and math_score (final exam score out of 100) of 300 students in an undergraduate math course. She creates another field called BMI (Body Mass Index) calculated as BMI-703"(weight/height?). She wants to examine if math_score is related to height, weight and BMI. She plans to use a linear regression model math_score - height +weight+BMI to study this relationship. Leonard hears about Mary's plan and tells Mary that BMI should not be used in her experiment because it is created from the height and weight variables which are already included in the model. He says this leads to an issue called multicollinearity in linear regression. Which of the below options is TRUE? Leonard is right; retaining height, weight, BMI in the model will certainly lead to multicollinearity. Leonard is wrong because BMI is not a linear combination of weight and height. Leonard is wrong: it is impossible to say whether multicollinearity is a problem in a proposed model without first fitting the model. Leonard is right, but the correct name for this issue is homoscedasticity.D Question 22 High VIF (> 10) value for predictors in linear regression suggests Homoscedasticity Multicolinearity. " Autocorrelation. non-Linear relation between dependent and independent variables. D Question 23 2 pts Which of the following is not correct? Lasso regression uses the L1 norm. Ridge regression uses the L2 norm. O Ridge regression does not perform variable selection. Elastic net does not perform variable selection.D Question 24 2 pts Which of the following is correct? A chi-squared iest is used to test the overall regression of a logistic regression model. At-test is used to test the statistical significance of predictors in a logistic regression model. A 2-test is used to test the statistical significance of predictors in a standard linear regression model. An F-test test is used to test the overall regression of a Poisson regression model. Question 25 2 pts The regression gim(Y-X, family=poisson) was fitted to count data, resulting in the estimate of Bo to be 20 and the estimate of B, to be 0.8. For a one unit increase in X, the rate increases by 0.8 units. O the log rate increases by 0.8 units. the log rate increases by exp(0.8) units. the rate increases by exp(0.8) percent.D Question 26 2 pts Which of the following is correct? Overdispersion is a concern for standard linear regression. O For both logistic and Poisson regression, the variance of the response equals the expectation of the response given the predicting variables. With overdispersion, the observed variance is larger than the variance implied by our model. With overdispersion, the observed variance is smaller than the variance implied by our model. ' D Question 27 2 pts Simpson's Paradox occurs when: O a coefficient of a predictor is not significant in a marginal model, and also not significant in a multivariate model the p-value of an estimate is significant at an alpha level of 0.05 but not at an alpha level of 0.01 the coefficient of a predictor reverses sign when considered under a marginal model versus a conditional model O Homer Simpson buys a dozen doughnuts and O remain when he arrives home.D Question 28 2 pts Which of the following is true regarding logistic regression? Logistic regression can also be replaced by standard linear regression if there are repetitions. O Logistic regression can only be used with continuous predicting variables. Logistic regression can only be used when the response variable is binary. Logistic regression requires replications for residual analysisD Question 29 2 pts Which of the following is TRUE about adjusted R-squared? The adjusted R2 can be used to compare models, and its value will always be less than or equal to that of R2. The adjusted R2 cannot be used to compare models, and its value will always be less than or equal to that of R2. The adjusted R2 can be used to compare models, and its value will always be greater than or equal to that of R2 The adjusted R2 cannot be used to compare models, and its value will always be greater than or equal to that of R2D Question 30 2 pts In simple linear regression, what is the relation between R-squared and the correlation coefficient p? O R-squared = p R-squared = p^2 O R-squared + Adjusted R-squared = p There is no relation between the two