Multiple Imputation of Missing Data in Cross-Cultural Samples

Abstract

Listwise deletion of cases with missing data prior to statistical analysis, the approach overwhelmingly used by cross-cultural survey researchers, requires the assumption that the missing data are missing completely at random. This assumption is not often likely to hold for cross-cultural sample data, and when it fails statistical analysis based only on complete-case subsamples introduces the possibility of biased estimates and standard errors. Over the past 20 or so years statisticians have made major advances in specifying the conditions under which missing data can be ignored when making inferences based on incomplete data. We review these conditions since they have a direct bearing on when the usual approaches to dealing with missing cross-cultural survey data are invalid.

Parental Nurturance in the Standard Cross-Cultural Sample

“…In many cases, there is only a brief comment on a particular person’s acts toward a child. The amount of missing data (Dow, 2009) reported in Rohner and Rohner may be because of the fact that the ambitious coding system does not fit the text in many ethnographies. A simple solution is to return to the approach used by Rohner (1975) and develop a coding system that can amalgamate multiple types of information into a meaningful overall score for a common underlying variable.…”

Dismissed with Prejudice: Gender Inequality in the Utah Legal Market

“…The analysis of a statistical model is then performed on each data set, and the analyses are aggregated to yield a set of results (Royston 2004). By accounting for the error of variance in the imputed values, multiple imputation provides reliable estimates for missing observations (Dow and Eff 2009).…”

How to Deal with Missing Data and Galton’s Problem in Cross-Cultural Survey Research: A Primer for R

“…Estimates based on such subsamples are valid only if certain assumptions are made about the mechanism(s) by which the data become missing. These assumptions are reviewed by Dow and Eff (2009b) who conclude that they will seldom hold for cross-cultural data sets.…”

“…A few recent cross-cultural papers point out the advantages of multiple imputation. Dow and Eff (2009b) provide a review of the issues and literature. The methods have also been used in two recent empirical studies (Dow and Eff 2009a;Eff and Dow 2009).…”