FAST & EASY IMPUTATION OF MISSING SOCIAL SCIENCE DATA

Abstract. Gold-standard approaches to missing data imputation are complicated and computationally expensive. We present a principled solution to this situation, using copula distributions from which missing data may be quickly drawn. We compare this approach to other imputation techniques and show that it performs at least as well as less compu-tationally efficient approaches. Our results demonstrate that most applied researchers can achieve great speed improvements implementing a copula-based imputation approach, while still maintaining the performance of other approaches to multiple imputation. Moreover, this approach can be easily implemented at the point of need in Bayesian analyses. Why do we ignore missing data despite knowing better? When reading and reviewing statistical studies from observational data, we often find that the number of cases used in the analysis does not match up with the actual number of possible observations. For example, even if a particular study covers 50 countries over 20 years, rarely does the actual data analysis include 1000 observations per variable. In fact, scholars are so used to this problem, that few even discuss let alone tackle the root cause: missing data. Missing data is pervasive in political science research and a “feature ” of mos