Missing data is an integral part of clinical trials and its analysis. This study discusses the downsides of having missing values in clinical data, traditional methods used to resolve this issue and some techniques which can be implemented to remedy the same.
The data used for the study is simulated from Theophylline data from Pinheiro and Bates (1995). The simulated data measures the Theophylline drug concentration in the body of 10 Subjects over 24 hours. There are three cases considered with increasing number of randomly created missing values for the Concentration variable. Subsets are created to fit linear and quadratic linear subject and population models. The fitted models are compared using Sums of Squares of Imputation and Imputed R2. These comparative techniques indicate that replacing the missing values in clinical data with appropriate estimates, while maintaining the authenticity of the data, is feasible.
Library of Congress Subject Headings
Clinical trials--Statistical methods; Clinical trials--Data processing; Missing observations (Statistics); Mathematical statistics; Linear models (Statistics); Population--Mathematical models
Applied Statistics (MS)
Department, Program, or Center
School of Mathematical Sciences (COS)
Purandare, Vaishnavi, "Comparison of Statistical Models for Imputation of Missing Data in Clinical Trials" (2020). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus