robertthiesmeier/cqi_missing_data

Multiple imputation for systematically missing effect modifiers in individual participant data meta-analysis

Multiple imputation for systematically missing effect modifiers in individual participant data meta-analysis

Thiesmeier R, Scott SM, Orsini N

Department of Global Public Health, Karolinska Institutet, Stockholm, Sweden

This repository includes the Stata code to illustrate the use of conditional quantile imputation as described in the manuscript: "Multiple imputation for systematically missing effect modifiers in individual participant data meta-analysis" by Thiesmeier R, Hofer SM, Orsini N (2024). The Stata code uses the publicly available individual participant data set, describing the effect of postoperative radiotherapy on survival at different stages of the disease. The CQI package described and used in the manuscript is available for Stata 18. A log log-file of the example demonstrating the use of CQI is available here. In addition, the Data Generating Mechanism, as described in detail in the manuscript can be found in the dgm.do file.