Wednesday, November 6, 2013

Kentucky Association of Institutional Research (KAIR) Presentations

I'll be giving the following two talks at KAIR this year.
  
A Guide to Quasi-Experimental Designs

Quasi-experimental designs including propensity score methods, instrumental variables, regression discontinuity, and difference-in-difference estimators offer an inferentially rigorous alternative for program evaluation. In this guide, I begin with an introduction to the potential outcomes framework for rigorously characterizing selection bias and follow with discussions of quasi-experimental methods that may be useful to practitioners involved in program evaluation.

Paper: http://works.bepress.com/matt_bogard/24/
Slides: http://works.bepress.com/matt_bogard/27/

A Data Driven Analytic Strategy for Increasing Yield and Retention

As many Universities face the constraints of declining enrollment demographics, pressure from state governments for increased student success, as well as declining revenues, the costs of utilizing anecdotal evidence and intuition based on ‘gut’ feelings to make time and resource allocation decisions become significant. This presentation describes several data mining algorithms that could be used to develop a model to score university students based on their probability of enrollment and retention early in the enrollment funnel so that staff and administrators can work to recruit students that not only have an average or better chance of enrolling but also succeeding once they enroll. The use of SAS® Enterprise Miner and SAS® EBI server are discussed as an example of a business intelligence platform that can be used for implementing the models and delivering flexible web based reports to end users.

Paper: http://works.bepress.com/matt_bogard/26/
Slides:http://works.bepress.com/matt_bogard/28/




5 comments:

  1. This comment has been removed by the author.

    ReplyDelete
  2. Quick question after reading your paper - which was great!. Is the data in the DID regression the same units (e.g. firms) in year 1 and year 2 (i.e panel data) or independent random samples each time?

    ReplyDelete
  3. I used data from another lecture/presentation. It may be after the break (I work for a university) before I can get back into the office to verify.

    ReplyDelete
    Replies
    1. OK, I was asking generically for the technique.

      Brian

      Delete
    2. I think I understand your question now, and after a week back in the office I'm getting things caught up. DD methods can be thought of as a special case or type of fixed effects or panel estimator. See also: http://econometricsense.blogspot.com/2011/01/mixed-fixed-and-random-effects-models.html and http://econometricsense.blogspot.com/2012/12/difference-in-difference-estimators.html I am hoping at some point to update with some posts with some actual data and code for estimation either in SAS or R.

      Delete