Open Access<p>Handling Missing Values in Interrupted Time Series Analysis of Longitudinal Individual-Level Data</p>
Author(s) -
Juan Carlos BazoAlvarez,
Tim P. Morris,
Tra My Pham,
James Carpenter,
Irene Petersen
Publication year - 2020
Publication title -
clinical epidemiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.868
H-Index - 58
ISSN - 1179-1349
DOI - 10.2147/clep.s266428
Subject(s) - missing data , imputation (statistics) , statistics , random effects model , covariate , mixed model , multilevel model , econometrics , aggregate data , aggregate (composite) , time point , mathematics , medicine , meta analysis , philosophy , materials science , composite material , aesthetics
In the interrupted time series (ITS) approach, it is common to average the outcome of interest at each time point and then perform a segmented regression (SR) analysis. In this study, we illustrate that such 'aggregate-level' analysis is biased when data are missing at random (MAR) and provide alternative analysis methods.