Three conditions under which experiments and observational studies produce comparable causal estimates: New findings from within‐study comparisons

This paper analyzes 12 recent within‐study comparisons contrasting causal estimates from a randomized experiment with those from an observational study sharing the same treatment group. The aim is to test whether different causal estimates result when a counterfactual group is formed, either with or without random assignment, and when statistical adjustments for selection are made in the group from which random assignment is absent. We identify three studies comparing experiments and regression‐discontinuity (RD) studies. They produce quite comparable causal estimates at points around the RD cutoff. We identify three other studies where the quasi‐experiment involves careful intact group matching on the pretest. Despite the logical possibility of hidden bias in this instance, all three cases also reproduce their experimental estimates, especially if the match is geographically local. We then identify two studies where the treatment and nonrandomized comparison groups manifestly differ at pretest but where the selection process into treatment is completely or very plausibly known. Here too, experimental results are recreated. Two of the remaining studies result in correspondent experimental and nonexperimental results under some circumstances but not others, while two others produce different experimental and nonexperimental estimates, though in each case the observational study was poorly designed and analyzed. Such evidence is more promising than what was achieved in past within‐study comparisons, most involving job training. Reasons for this difference are discussed. © 2008 by the Association for Public Policy Analysis and Management.     

Mortgaging Security for Economic Gain: U.S. Arms Policy in an Insecure World

Similar to other consumer sectors of the global economy, the transfer of advanced conventional weapons and military technologies has entered the globalization process, a process that has qualitatively and quantitatively altered the composition and structure of U.S. national security policymaking. By injecting the decisionmaking process governing arms transfers into the global market place, U.S. policy makers must now reconcile maintaining economic competitiveness within the global system without jeopardizing U.S. national security interests. By subordinating national security interests to global economic imperatives, U.S. decisionmakers are at risk of mortgaging the political, societal, and security welfare of its citizenry for profit.     

Ethnicity,Islam, and Pakistani Public Opinion toward the Pakistani Taliban

This article argues that an Islamist militant group with a relatively homogenous ethnic make-up is more likely to be supported by those of the same ethnicity even if the group makes no reference to and even downplays the importance of ethnicity. Using survey data from an original survey carried out in Pakistan in 2013, with 7,656 respondents, this hypothesis is tested in a multiple regression analysis of support for the Pakistani Taliban. The results demonstrate that co-ethnicity between the respondent and the Islamist militant group is the most important predictor of support for the militant group.