Question: Stat 2118 Homework 8 For this homework use the data set class.xlsx, which is on blackboard. This data set consists of a previous semester's students'

Stat 2118 Homework 8 For this homework use the data set class.xlsx, which is on blackboard. This data set consists of a previous semester's students' scores in STAT 2118. The variables from the data set are the scores in eight homework; two midterms, and the nal. The objective is to study the nal exam score and which variables inuence it. The goal is to t the best multiple regression model to the response (nal exam score). 1. Fit the full model with all ten predictor variables. a) Does there appear to be any multicollinearity? b) Are there any high inuence points (use a threshold of Cook's D greater than 0.5)? If there are any outlier(s), remove the observation(s) for the rest of the exercises. 2. Use the stepwise regression methods (use a = 0.1) to see which model is the best. Repeat using \"best subset\" regression. Do they agree? 3. Come up with one model that you think best describes the data and can be used for future predictions. Show the residual plot for this one. Does the model seem appropriate? 4. Use this model to predict what your nal exam score will be (it is out of 50). Construct a 95% prediction interval for this estimate
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
