Markov Analysis of an Alternative to Pure Random Assignment
Author(s)Bier, Vicki M.
There are many public policy settings in which random assignment of clients to experimental and control groups is not feasible. I will discuss one such case, and the alternative method of assignment which was actually used. The vulnerability of this method to intentional selection bias will be explored using Markov methods of analysis.
Massachusetts Institute of Technology, Operations Research Center
Operations Research Center Working Paper;OR 090-79