Generally a nice job on the 2nd midterm!

An overall summary of the grades on the 2nd midterm follows:

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   39.0    85.0    90.0    85.9    93.0   100.0 

The stem and leaf diagram looks like this:

  The decimal point is 1 digit(s) to the right of the |

   3 | 9
   4 | 
   5 | 
   6 | 4
   7 | 3
   8 | 035578
   9 | 00001133589
  10 | 0

Approximate letter grades can follow the usual 90/80/70 
prescription (90 and above, A; 80 and above, B; etc.).

Daniel (grader) reports that the most common problems on the
exam were related to the calculation of variances:

(1) For a proportion, the population variance is p(1-p),
and the sample variance is p-hat*(1 - p-hat), so you don't 
have to bother with the sum of the squared differences 
from the mean.

(2) The variance of an estimator (like p-hat or y-bar) is 
the population or sample variance divided by n.  

The same ideas apply in survey statistics with two additional 
notes:

(a) you have to remember to mulitply by the fpc

(b) in some cases you calculate the variance of the 
    estimator directly (like with the Taylor Series
    method for weighted means); in those cases you
    do not have to divide by n, because you are 
    already working with the variance of the estimator
    rather than the variance of the population or 
    sample.

-BJ