Division of General Internal Medicine

Department Home >

  • Base >
  • You are here
Division of General Internal Medicine

Economic Evaluation in Clinical Trials

Chapter 5, Multivariable Analysis of Cost
  • This chapter provides an example of a multivariable analysis of cost and QALYs by use of generalized linear models (multivcostanalysis.eeinct.pdf). In addition to providing a dataset (rchapter5.dta) that includes cost, QALYs, and six explanatory variables (a treatment indicator, a disease severity measure, baseline cost and QALYs, gender, and race), we provide one more general program (glmdiagnostic.do), a bootstrap program that is written specifically for this dataset (bsmultiv.do), and a bootstrapped dataset that was generated by the bootstrap program (bsmvpred.dta). Multivcostanalysis.eeinct.pdf walks you through a basic multvariable analysis of the data, using programs that are basic parts of STATA as well as the more specialized programs that we provide.

  • multivcostanalysis.eeinct.pdf: Tutorial that walks you through an example of multivariable analysis of cost and QALYs
  • Programs
    • glmdiagnostic.do: Contains the program glmdiag. "Doing" glmdiagnostic does not run any diagnostics. Instead, it loads glmdiag so that it can be called by STATA. glmdiag performs the modified Park test (for the GLM family) and the Pearson correlation test, the Pregibon link test, and the modified Hosmer and Lemeshow test (for the GLM link)
    • bsmultiv.do: Custom bootstrap program written specifically for the analysis of the rchapter5.dta dataset. You can edit this program so that it can be used with other datasets
  • Datasets
    • rchapter5.dta: Cost (and effect) dataset illustrated in chapter 5, including explanatory variables
    • bsmvpred.dta: Bootstrapped results derive by use of bsmultiv.do

Updated 4/25/08