A grading distribution can be described by a mean value and a standard deviation. A histogram counts the number of observed values in a given "bin" range and contains no spaces between frequency bars
Study the data dictionary and the data sheets to conceptualize what the data set contains
Use VLOOKUP functions in your spreadsheet of choice to populate the missing fields in the rows for both the mid-term grades and the final grades. Make sure to use the lookup tool instead of hand-classifying the data. Imagine there are millions of rows!
Once you have populated data in the core spreadsheet, copy the values into a new sheet such that
there are no more formulas and just "plain" numbers and letters to work with
Create a pivot table which computes the mean and standard deviation of grade points for each class at the mid-term and the final grade
Create a frequency distribution (a historgram) which graphically shows the distribution of the mid-term and final grades for at least two of the classes (Probably CIT-111, since there are the most students, and perhaps CIT-100 which was offered online)
Compose a set of defensible statements comparing the grade distribution in each course based on the data revealed in the spreadsheet. Are the data skewed in a certain direction? Which course without point-based grading is most similar to the point-based counterpart (the Javascript)? Which is most different?
27-JAN-19: Creation of Version 0.9 of the print-friendly module page for rollout with classes in the Spring of 2019!!