Team D

100/100 for I3.  0/100 for I4 until you turn it in.

Ellie Gurary, Bruce Jackson, Maggie Soderholm, Chrissy Swierkocki, Jen
Sung

General Comments:
----------------

Your project seems OK. 

However I did not receive an I4 assignment from you.  Please turn it
in (as an email attachment) so I can give you credit for it!

Specific Comments [based on I3]:
-------------------------------

* The 5 references are probably OK, but they are not formatted in a
  way that makes sense for the "list of references" at the end of a
  paper.  Please reformat them (they need to be included in the final
  paper).


* Your sampling plan appears to be to sample classrooms as "clusters"
  and then sample everyone within each classroom.  

  (a) you will find the list of classes at 

      	  https://enr-apps.as.cmu.edu/open/SOC/web/images/documents.htm

      useful as a frame.  you can do an SRS w/o replacement directly
      from this (be careful to exclude anything that is not an
      undergraduate class).

  (b) You will need to work out a way to get instructor's permission
      to survey the classes in your sample.  I have no idea what the
      response rate (% of instructors who agree) will be.  I suppose
      that if the instructor agrees, most students in the class will
      agree also.  (note that each student needs to agree to an
      informed consent statement)

      If you can't find anything to help you make a guess about
      response rate, you might try to oversample for a response rate
      of about 40% (i.e. oversample about 1/0.4 = 2.5 times as many as
      you think you need from sample size calculations).  Then if you
      notice that the response rate seems to be different from 40%
      once the survey gets underway, adjust the over-sample
      appropriately.

      You will have to guess how many classes to sample.  You should
      do a generous sample size calculation for individual student
      responses, and then convert that to a sample size for classes
      using an estimate of the average class size at CMU.  You may
      need to expand or reduce your sample size for classes if you
      happen to get mostly small or mostly large classes.

* Your draft IRB application is looking good.  you will want to revise
  the details as you develop your questionnaire, solidify the sample
  design, etc.

* good points about confidentiality at the end of I3.