Question 2. Multiple Linear Regression (Use trainData for t…
Question 2. Multiple Linear Regression (Use trainData for this question) (20 points) PDF ONLY Question 2 ONLY Submit to BOTH Canvas and Gradescope Question 2 Gradescope Submission Link Expire after 10 minutes once opened Upload PDF here in Canvas. Starter templates: . Summer2025_midterm_Question no. 2_R-2.ipynb . Summer2025_midterm_Question no. 2_Python-2.ipynb a) (9 points)(2 points) i) Using trainData, perform a multiple linear regression to predict the sleep_hours using the predicting variables caffeine_intake and evening_habits.Call it model1. Display the summary. (4 points) ii) Interpret the coefficient of evening_habitsReading and caffeine_intake in the contextof the problem. State any assumptions while interpreting the coefficents. Note: Interpret the coefficient irrespective of its statistical significance. (3 points) iii) Suppose you had to build a simpler model with only one evening habit. Which would you choose and why? (Use both coefficient and standard error logic.) (2 points) b) Create a full linear regression model using all the predictors in the dataset “trainData” .Call it model2. Display the summary. (3 points) c) Compare the R-squared and Adjusted R-squared values of the reduced and full models (model1 and model2). What do you observe? Explain the theoretical differences between R-squared and Adjusted R-squared. What does each measure? (6 points) d) Perform all the model diagnostics on model2 (the full model). Explain your findings based on the diagnostic plots.
Read Details