Project 24
Project description

In this project, use the model that you set up in Project 8, which you used again in Project 16 and Project 18. Perform the standard regression diagnostics on this model to assess its suitability and the correctness of your hypothesis tests and/or confidence intervals. For any of the regression assumptions that do not hold, comment on what changes this should direct you to in your analysis.

Background on the data set

In Chuck Hommel's Introduction to Applied Statistics course at the University of Puget Sound, he gives periodic homework quizzes. These are given on Mondays, take about ten minutes, and cover the homework that students have had a chance both to try and to ask about in class. The quizzes include a selection of two or three homework problems taken directly from the text. Students can copy their homework onto the quiz paper. In theory, if the student has done the homework, the quiz should be easy. Over a semester, there will be four or five quizzes.

At the end of the semester, all students take a comprehensive final examination. This exam is taken during a two-hour period and contains original questions the students have not previously seen.

Homework quiz scores are between 0 and 5 points. For each student, the mean quiz score is calculated and a percent correct is calculated by dividing the mean by 5 and multiplying by 100. This results in an overall homework quiz score in the range 0 to 100. The final exam is scored on a scale of 0 to 100. A five-point extra credit question means the highest possible final exam score is 105.

Data was collected from four sections of Introduction to Applied Statistics taught during the Fall semester of 2006 and the Spring and Fall semesters of 2007. A total of 97 students were enrolled.

Homework quiz averages and final exam scores were collected for all 97 students who completed Chuck Hommel's Introduction to Applied Statistics classes at the University of Puget Sound for the Fall 2006, Spring 2007, and Fall 2007 semesters.

Variables in the data set
The variables in the data set are as follows:
termF06 = Fall 2006 semester, S07 = Spring 2007 semester, F07 = Fall 2007 semestercourse semester
quizAvgpercent (0-100)average of homework quiz scores
finalExampoints (0-105)score on final exam
Link to the data set
The full data set in csv format is at: