Subject: Re: two questions are broken From: Brian Junker Date: Fri, 01 Apr 2011 09:52:19 -0400 To: Dave Eckhardt CC: groupg.303@gmail.com, Dong Seob Kim , Hye Jung Cho , Erica Choi , Aiena Garg , John Shoup > two questions are broken > > ********************************************************************** > 19. Do you think... > > 20. Do you think... > ********************************************************************** thanks for the feedback! Team G, please fix! > Meanwhile, I am kind of curious as to what level of actual anonymity > exists in the face of this pair of questions: > > 1. What is your Job title (assistant professor, head of department, > teaching professor, professor, etc)? > > 2. Department you are associated with? (Statistics, English, Chemistry, > etc) > > Was the sample drawn so that {Associate Teaching Professor, Computer > Science} appears multiple times? Is that still anonymous after the > "number of years at CMU" variable is considered? > > Dave Eckhardt These are excellent questions (of course), very much related to the discussion of the Netflix and AOL database releases that we discussed in class: even if respondents' specific names, emails, etc. are not kept, matching with other data (e.g. department faculty lists) can de-anonymize respondents if fine-enough grained data on other attributes (rank, # of years at CMU, dept, etc.) are released. Team G: Please email Dr. Eckhardt with a carefully thought-out email, letting him know: (a) at what level you will summarize data in your final report so that someone who reads the report cannot identify individual faculty in the way Dr. Eckhardt is worried about; and (b) how you will keep the raw data confidential during the survey project and how you plan to dispose of it after the project so that no one can come along later and use your raw data to identify faculty who took your survey, in this way. You may wish to keep this email for future use, since I expect other faculty may have similar questions. cc me of course. best, -BJ -- Brian Junker (412) 268 - 2718 Department of Statistics brian@stat.cmu.edu 232 Baker Hall FAX: (412) CMU-STAT Carnegie Mellon University or (412) 268-7828 Pittsburgh PA 15213 USA WWW: http://www.stat.cmu.edu/~brian/