| |
CSCI A113
|
Start by downloading the data from the midterm exam. Then review chapter 3 in your textbook (thin green book) and especially section 3.5 (pp. 40-47).
The aim of this data analysis is to assess student learning on the midterm examination. The data analysis sequence should begin by developing a graphical presentation of the results and then by computing certain statistical measures, as detailed below. Data for this example comes from our midterm examination 10 days ago. There were 28 questions with each question counting a certain number of points. The total number of points was 77. There was one student that obtained a perfect score (line 49 in the spreadsheet) so you can use that line for the max number of points per question on the exam.
Scores include partial credit for each question. Do the following:
The next set of procedures is aimed at extracting information of student performance relative to individual questions.
This percentage will give you a measure of difficulty (between 0 and 1) for each item. The higher the value the easier the item: a value of 1 means everybody got maximum number of points on the problem (so the problem was tremendously easy). A value of 0 means nobody solved any part of that problem (which means the problem was extremely hard). This value is also equal to "the percentage of students who got the question right".
A113