Speaker: Paul Imbriano
Longitudinal or panel surveys are effective tools for measuring individual level changes in the outcome variables and their correlates. One drawback of these studies is dropout or non-response, potentially leading to biased results. One potential reason for dropout is the burden placed on subjects for repeatedly responding to long questionnaires. Advancements in survey administration methodology and multiple imputation software make it possible for planned missing data designs to be implemented for improving the data quality through a reduction in survey length. Many papers have discussed implementing a planned missing data study using a split questionnaire design in the cross-sectional setting, but development of these designs in a longitudinal study has been fairly limited. We propose several methods for implementing split questionnaire designs in the longitudinal setting. Using both simulations and data from a longitudinal study, we compare the performance of these methods. The results suggest that the optimal design depends on both the data structure and estimate of interest. These factors should be taken into account when designing a longitudinal study with planned missing data.