The presence of outliers and influential cases can dramatically change the magnitude of regression coefficients and even the direction of coefficient signs (i.e., from positive to negative or vice versa). When researchers ignore abnormal observations, especially with respect to dependent variables, their empirical results can be misleading. Unfortunately, the fact remains underappreciated in studies of political science. To expound upon the outlier issue, I reexamine an empirical study that reports on two opposing effects of democratic institutions on inflows of foreign direct investment (FDI). In doing so, I illustrate the way influential outliers can drastically affect the substantive results of regression analysis. After properly reanalyzing outlying countries, I conclude that democratic countries attract more FDI than authoritarian countries.
Commentary
Outlier, Measurement, and the Democracy-FDI Controversy , Quarterly Journal of Political Science, Volume 4, Issue 2 10.1561/100.00009028