Functional form and risk adjustment of hospital costs: Bayesian analysis of a Box-Cox random coefficients model

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


While risk-adjusted outcomes are often used to compare the performance of hospitals and physicians, the most appropriate functional form for the risk adjustment process is not always obvious for continuous outcomes such as costs. Semi-log models are used most often to correct skewness in cost data, but there has been limited research to determine whether the log transformation is sufficient or whether another transformation is more appropriate. This study explores the most appropriate functional form for risk-adjusting the cost of coronary artery bypass graft (CABG) surgery. Data included patients undergoing CABG surgery at four hospitals in the midwest and were fit to a Box-Cox model with random coefficients (BCRC) using Markov chain Monte Carlo methods. Marginal likelihoods and Bayes factors were computed to perform model comparison of alternative model specifications. Rankings of hospital performance were created from the simulation output and the rankings produced by Bayesian estimates were compared to rankings produced by standard models fit using classical methods. Results suggest that, for these data, the most appropriate functional form is not logarithmic, but corresponds to a Box-Cox transformation of -1. Furthermore, Bayes factors overwhelmingly rejected the natural log transformation. However, the hospital ranking induced by the BCRC model was not different from the ranking produced by maximum likelihood estimates of either the linear or semi-log model.

Original languageEnglish (US)
Pages (from-to)3005-3018
Number of pages14
JournalStatistics in Medicine
Issue number19
StatePublished - Oct 15 2005

All Science Journal Classification (ASJC) codes

  • Epidemiology
  • Statistics and Probability


Dive into the research topics of 'Functional form and risk adjustment of hospital costs: Bayesian analysis of a Box-Cox random coefficients model'. Together they form a unique fingerprint.

Cite this