A blog for CinciDood's (aka Atomic Kid, aka Jack Julian) microeconomics course at IUP. Refresh page to ensure you are reading the most current entries.

Wednesday, October 14, 2009

Test 1 scores and scale

This is not a posting of scores but a posting of the distribution of scores and an approximate grade scale. (Please note: there is NO letter grade recorded for the test, only your raw score which is appropriately weighted is entered into the grade book. Hence, in the future it is NOT appropriate to ever say to me "I got an A on the first test and a B on the second, what do I need to do to get an A in the class." You get points. Points are what matter. The reason I give the scale is for you to know if you are doing "high quality" or "poor quality" work both overall and within a targeted grade range.

First, some descriptive statistics:

Average score is 34.70 (out of 45), or about 77.1%
Median score is 35.25, or about 78%

The mean and median are pretty close together, which they should be. The average is slightly below my target of 80%, but not that bad.

A measure of "dispersion" is the standard deviation. My target is 10%. This test had a standard deviation of 5.44 points or approximately 12.1%. This is a wider than expected dispersion. Another statistic, skewness, is "negative" which suggests that there were a few pretty low scores that made that standard deviation a bit high.

So, there is the approximate grade scale (to be interpreted as relative quality of work). In terms of the raw score,

A: 40 and higher (freq: 20)
B: 34.5 - 39.5 (freq: 34)
C: 29.5 - 34.0 (freq: 26)
D: 24 - 29 (freq: 13)
F: 23 and lower (freq: 3)

(freq is "frequency" which is the number of observations in that range. Note that there are more As and Bs total than Cs, Ds, and Fs.)

Overall, I think it was a good test of reasonable difficulty. Keep up the good work.

0 Comments:

Post a Comment

<< Home