It is well known that the modeling of cost data is often problematic due to the distribution of such data. Commonly observed problems include 1) a strongly right-skewed data distribution and 2) a significant percentage of zero-cost observations. This article demonstrates how a hurdle model can be implemented from a Bayesian perspective by means of Markov Chain Monte Carlo simulation methods using the freely available software WinBUGS. Assessment of model fit is addressed through the implementation of two cross-validation methods. The relative merits of this Bayesian approach compared to the classical equivalent are discussed in detail. To illustrate the methods described, patient-specific nonhealth-care resource-use data from a prospective longitudinal study and the Norfolk Arthritis Register (NOAR) are utilized for 218 individuals with early inflammatory polyarthritis (IP). The NOAR database also includes information on various patient-level covariates.
Get full access to this article
View all access options for this article.
References
1.
1. Hodgson TA. Cost of illness studies—no aid to decision-making—comments on the 2nd opinion by Shiell et-al . Health Policy. 1989;11: 57–60 .
3. Drummond MF. Cost of illness—a major headache . Pharmaco-Economics. 1992;2: 1–4 .
4.
4. Lipscomb J, Ancukiewicz M, Parmigiani G, Hasselblad V, Samsa G, Matchar DB. Predicting the cost of illness: a comparison of alternative models applied to stroke . Med Dec Making. 1998;18: S39–S56 .
5.
5. Gold MR, Siegel JE, Russell LB, Weinstein MC. Cost-Effectiveness in Health and Medicine. New York: Oxford University Press ; 1996.
6.
6. Greene WH. Econometric Analysis: International Edition. Englewood Cliffs, NJ: Prentice Hall ; 1997.
7.
7. Chang B-H, Pocock S. Analyzing data with clumping at zero: An example demonstration . J Clin Epidemiol. 2000;53: 1036–43 .
8.
8. Dudley RA, Harrell FE, Smith LR, et al. Comparison of analytic models for estimating the effect of clinical factors on the cost of coronary artery bypass graft surgery . J Clin Epidemiol. 1993;46: 261–71 .
9.
9. Barber JA, Thompson SG. Analysis and interpretation of cost data in randomised controlled trials: review of published studies . BMJ. 1998;317: 1195–200 .
10.
10. O’Brien B. Statistical analysis of cost-effectiveness data . J Rheumatol. 1999;26: 2078–80 .
11.
11. Thompson SG, Barber JA. How should cost data in pragmatic randomised trials be analysed? BMJ. 2000;320: 1197–200 .
12.
12. Duan N. Smearing estimate: a non-parametric retransformation method . J Am Stat Assoc. 1983;78: 605–10 .
13.
13. Spiegelhalter DJ, Thomas A, Best NG. WinBUGSVersion 1.2 User Manual. Cambridge: MRC Biostatistics Unit ; 1999.
14.
14. Spiegelhalter DJ. Bayesian graphical modelling: a case study in monitoring health outcomes . J R Stat Soc Series C. 1998;47: 115–33 .
15.
15. Carlin BP, Louis TA. Bayes and emipirical Bayes methods for data analysis. London: Chapman & Hall ; 2000.
16.
16. Spiegelhalter DJ, Myles JP, Jones DR, Abrams KR. Methods in health service research: an introduction to Bayesian methods in health technology assessment . BMJ. 1999;319: 508–12 .
17.
17. Gilks WR, Richardson S, Spiegelhalter DJ. Markov Chain Monte Carlo in Practice: Interdisiplinary Statistics. London: Chapman & Hall ; 1996.
18.
18. O’Hagan A, Stevens JW, Montmartin J. Inference for the costeffectiveness acceptability curve and cost-effectiveness ratio . Pharmacoeconomics. 2000;17: 339–49 .
19.
19. O’Hagan A, Stevens JW, Montmartin J. Bayesian cost-effectiveness analysis from clinical trial data . Stat Med. 2001;20: 733–53 .
20.
20. Cowles MK, Carlin BP. Markov Chain Monte Carlo convergence diagnostics: A comparative review . J Am Stat Assoc. 1996;91: 883–904 .
21.
21. Spiegelhalter DJ, Lauritzen SL. Sequential updating of conditional probabilities on directed graphical structures . Networks. 1990;20: 579–605 .
22.
22. Cirincione C, Gurrieri GA. Research methodology: computer-intensive methods in the social sciences . Soc Sci Comp Rev. 1997;15: 83–97 .
23.
23. Mullahy J. Much ado about two: reconsidering retransformation and the two-part model in health econometrics . J Health Econ. 1998;17: 247–81 .
24.
24. Manning WG. The logged dependent variable, heteroscedasticity, and the retransformation problem . J Health Econ. 1998;17: 283–95 .
25.
25. Manning WG, Mullahy J. Estimating log models: to transform or not to transform? J Health Econ. 2001;20: 461–676 .
26.
26. Blough DB, Ramsey SD. Using generalized linear models to assess care costs . Health Serv Outcomes Res Methodol. 2000;1: 185–202 .
27.
27. Efron B, Tibshirani RJ. The Jacknife: An Introduction to the Bootstrap. New York: Chapman & Hall ; 1993. p 141–52.
28.
28. Draper D. Assessment and propagation of model uncertainty . J R Stat Soc Series B. 1995;57: 45–97 .
29.
29. Geisser S. Predictive Inference: An Introduction. New York: Chapman & Hall ; 1993.
30.
30. Symmons DPM, Barrett EM, Bankhead CR, Scott DGI, Silman AJ. The incidence of rheumatoid arthritis in the United Kingdom: Results from the Norfolk arthritis register . BJ Rheumatol. 1994;33: 735–9 .
31.
31. Cooper NJ, Mugford M, Symmons DPM, Barrett EM, Scott DGI. Total costs and predictors of costs in individuals with early inflammatory polyarthritis: a community prospective study . Rheumatol. 2002;41: 767–74 .
32.
32. Netten A, Dennett J, Knight J. Unit Costs of Health and Social Care. 1999. University of Kent, PSSRU.
33.
33. Fries JF, Spitz PW, Young DY. The dimensions of health outcomes: the Health Assessment Questionnaire, Disability and Pain scales . J Rheumatol. 1982;9: 789–93 .
34.
34. Arnett FC, Edworthy SM, Bloch DA, et al. The American Rheumatism Association 1987 revised criteria for the classification of rheumatoid arthritis . Arthritis Rheum. 1987;31: 315–24 .
35.
35. Office of Population Censuses and Surveys. Standard Occupational Classification. Volume 3. Social Classifications and Coding Methodology. London: HMSO ; 1991.
36.
36. Gelman A, Rubin DB. Inference from iterative simulation using multiple sequences . Stat Sci. 1992;7: 457–72 .
37.
37. Natarajan R, Kass RE. Reference Bayesian methods for generalised linear mixed models . J Am Stat Assoc. 2000;95: 227–37 .
38.
38. Altman DG. Practical Statistics for Medical Research. London: Chapman & Hall ; 1991.
39.
39. Gelfand AE, Gilks WR, Richardson S, Spiegelhalter DJ. Markov Model Determination Using Sampling-Based Methods. London: Chapman & Hall ; 1996.
40.
40. Spiegelhalter DJ, Thomas A, Best NG, Gilks WR. BUGS: Bayesian Inference Using Gibbs Sampling Version 0.50. Cambridge: MRC Biostatistics Unit ; 1995.
41.
41. Gelfand AE, Dey DK. Bayesian model choice: asymptotics and exact calculations. J R Stat Soc Series B. 1994;56.
42.
42. Geisser S, Eddy W. A predictive approach to model selection . J Am Stat Assoc. 1979;74: 153–60 .
43.
43. Lin DY. Linear regression analysis of censored medical costs . Biostatistics. 2000;1: 35–47 .
44.
44. Spiegelhalter DJ, Myles JP, Jones DR, Abrams KR. Bayesian methods in health technology assessment: a review. Health Technol Assess. 2000;4.
