Three-level data structures arising from repeated measures on individuals who are clustered within larger units are common in clinical …

Multilevel data with three levels of hierarchy resulting from repeated measures data on individuals who are clustered within larger …

The event:The completion seminar is an important milestone of PhD candidature where objectives, methods, findings and significance of …

The Missing Data, Imputation and Analysis (MiDIA) Group meets 4 times a year, to discuss work in progress in the area of missing data …

Diving headfirst into a PhD after a bachelors can be quite a challenge. Transitioning from a naive undergraduate student to a full-time …

Three-level data is common in medical research, as is missing. While multiple imputation (MI) is widely used to handle missing data in such studies, its validity depends on the appropriate tailoring of the imputation model to the substantive analysis. This means all the key features of the substantive analysis such as non-linear relationships, interactions and multilevel features should be appropriately accommodated in the imputation process. This paper evaluates a number of MI approaches that may be used for imputing three-level data when the substantive analysis model contains interactions and non-linear terms using both a simulation and a case study.

While many MI approaches for imputing multilevel data have been developed recently, there is a lack of approaches specifically for three-level data and as a result, insufficient guidance for practitioners in the context of complex three-level data.This study evaluates the performance of available MI approaches for handling three-level incomplete data under a number of different scenarios via simulations and an empirical application based on a case study.

Understanding choice of the statistical test used in testing a particular hypothesis of interest is of utmost importance so that valid statistical conclusions can be made.This study compares the robustness,in terms of type I error rate and power,of the widely used parametric hypothesis tests; pooled t test, unpooled t test, paired t test and one way ANOVA F test with their randomization counterpart using simulations,so as to provide guidance on if and when they should be used.