Latest SYE 6414 Final Exam 2026 | Correct A+ Answers

SYE 6414 Final Exam 2025, ISYE 6414 Final Exam Real Exam Questions and Correct Verified Answers (Revised Exam) A New Updated Version Latest 2025 | Already Graded A+ (Actual Exam) 1. We should always use mean squared error to determine the best value of lambda in lassoregression. a. True b. False Sol: False. The criterion used is a choice we make. 2. Standard linear regression is an example of a generalized linear model where the response isnormally distributed and the link is the identity function. a. True b. False Sol: True. See Unit 4.4.1. 3. Goodness-of-fit assessment for logistic regression involves checking for the independence,constant variance, and normality of the deviance residuals. a. True b. False Sol: False. We don’t have constant variance in binomial regression. 4. You are interested in understanding the relationship between stress level and exercise, with stress as the response. In your model, the number of hours a person spends exercising per weekwould be considered an explanatory variable while the person’s age would be a controlling variable. a. True b. False Sol: True. Time spent exercising is part of the relationship you are trying to understand while agecould act as a confounding variable that you need to control. 5. The hypothesis test for goodness-of-fit using Pearson residuals and the test using devianceresiduals will always reach the same conclusion. a. True b. False Sol: False. One test may conclude plausibly good fit while the other rejects it. 6. A logistic regression model with high goodness of fit can have low predictive power. a. True b. False Sol: True. See Unit 4.2.3. 7. If we apply a Poisson regression model using a small sample size, the estimators of the regression coefficient may not follow an approximate Normal distribution, affecting thereliability of the statistical inference on the coefficients. a. True b. False Sol: True. See Unit 4.2.1. 8. You fit a regression model using three predictors. You notice the estimated coefficient for predictor X1 is an order of magnitude larger than the estimated coefficient for predictor X2. It iscorrect to conclude that X1 has a greater effect on the response than X2. a. True b. False Sol: False. We do not know that the variables are on the same scale in order to directly compare them. We can only conclude that a 1-unit change in X1 is associated with a greater change in the response than a 1-unit change in X2 holding other variables constant. 9. Regularized regression with a lambda value equal to 0 is equivalent to regression modelestimation without penalization. a. True b. False Sol: True. See Unit 5.2.2. 10. In a Poisson regression model, the difference between the null deviance and residual deviancefollows a normal distribution. a. True b. False Sol: False. It follows a Chi-square distribution (this is used to check the overall regressionsignificance). 11. You want to examine the relationship between study time and score on exams. You create five exams and recruit 50 participants. For each participant in your study, you record their time studying for and grade on each of those five exams. If you were to use all the data you recorded to build a simple linear regression model, you would violate the independence assumption. a. True b. False Sol: True. Because you are collecting 5 observations from each person, the observations comingfrom the same person would be correlated. Similarly, all observations from the same test may be correlated. 12. Maximum likelihood estimation produces unbiased coefficient estimates for logistic and Poissonregression. a. True b. False Sol: True. Coefficient estimators follow an approximate normal distribution with the truecoefficient as the mean. 13. If considering only BIC for the model selection criterion, a model with lower BIC is preferred overa model with higher BIC. a. True b. False Sol: True. A lower BIC corresponds to a lower penalized prediction risk, and the statementspecified that is the only thing we are considering. 14. If we do not penalize the training risk, our variable selection method would always prefer morecomplex models. a. True b. False Sol: True. See Unit 5.1.3. 15. One goal of variable selection is to balance the bias-variance tradeoff when making predictions. a. True b. False Sol: True. See Unit 5.1.4. 16. Forward stepwise selection is computationally more expensive than backward stepwiseselection because it takes more iterations to terminate. a. True b. False Sol: False. Backwards is more expensive because it fits larger models. 17. When testing for the significance of a subset of predictors, the null hypothesis is that all coefficients for variables in that subset are 0 and the alternative is that all those coefficients arenot 0. a. True b. False Sol: False. The alternative is that at least one variable is significantly nonzero. 18. Classification error estimated from leave-one-out cross validation tends to have higher bias butlower variability than classification error estimated from 2-fold cross validation