AEA 2015 Presentation Friday, November 13 There is a controversy surrounding propensity scores (Pearl, 2009, p 350). The controversy involves the assumption of strongly ignorable treatment assignment (Rosenbaum and Rubin, 1983). In practice it can be difficult to determine whether or not treatment assignment is strongly ignorable. During this session we will learn more about what it means for treatment assignment to be strongly ignorable. We will investigate what happens when propensity score matching is carried out when treatment assignment is not strongly ignorable. We will learn how to use statistical simulation to assess the sensitivity of results to departures from the assumption of strongly ignorable treatment assignment. Analysis will be carried out on data from the TAACCCT grant. TAACCCT grants provide community colleges and other eligible institutions of higher education with funds to expand and improve their ability to deliver education and career training programs that can be completed in two years or less.#2015Conference