Let us talk about faculty evaluation.
My colleagues and good friends taught STAT 200 in 1684 at UNC. Both had ten students in their respective classes, sections 6980 and 6981. Below please find their evaluation by their students on their overall satisfaction with the class. The students ranked their level of satisfaction from 1 to 5, 1 being the lowest, and 5 the highest.
|
6980
|
1
|
4
|
3
|
4
|
5
|
5
|
4
|
3
|
4
|
5
|
|
6981
|
3
|
4
|
5
|
5
|
3
|
4
|
4
|
4
|
3
|
3
|
Now, let's see if we can summarize the student evaluation results the old fashion way, please provide answers for the following:
1. Let us go after the "usual suspects" for each class:
- Mean (μ):
- Median:
- Mode:
- Lowest value:
- Highest value:
- Range:
- Variance (σ2):
- Standard deviation (σ):
2. Can we tell from these numbers which instructor was more popular with the students? And why do or don't you think so?
3. How about the standard deviation? Do you think we can make some more intelligent statements about the two instructors when we have the standard deviations?
4. Now, put together a boxplot and compare the boxplots for the two classes. What kind of stories can we tell from this comparison?
5. Does the boxplot help to better explain the differences between the two evaluation results that the "usual suspects" could not? And why do or don't you think so?