Methods for handling missing data in the behavioral neurosciences: Don't throw the baby rat out with the bath water

Missing data are a major problem in the behavioral neurosciences, particularly when data collection is costly. Often researchers exclude cases with missing data, which can result in biased estimates and reduced power. Trying to avoid the deletion of a case because of a missing data point can be conducted, but implementing a naïve missing data method can result in distorted estimates and incorrect conclusions. New approaches for handling missing data have been developed but these techniques are not typically included in undergraduate research methods texts. The topic of missing data techniques would be useful for teaching research methods and for helping students with their research projects. This paper aimed to illustrate that estimating missing data is often more efficacious than complete case analysis, otherwise known as listwise deletion. Longitudinal data was obtained from an experiment examining the effects of an anorectic drug on food consumption in a small sample (n=17) of rats. The complete dataset was degraded by removing a percentage of datapoints (1-5%, 10%). Four missing data techniques: listwise deletion, mean substitution, regression, and expectation-maximization (EM) were applied to all six datasets to ensure that each approach was applied to the same missing data points. P-values, effect sizes, and Bayes factors were computed. Results demonstrated listwise deletion was the least effective method. EM and regression imputation were the preferred methods when more than 5% of the data were missing. Based on these findings it is recommended that researchers avoid using listwise deletion and consider alternative missing data techniques.