Abstract
Generalized additive models for location, scale, and shape (GAMLSS) are a class of semi-parametric models with potential applicability to health care cost data. We compared the bias, accuracy, and coverage of GAMLSS estimators with two distributions [gamma and generalized inverse gaussian (GIG)] using a log link to the generalized linear model (GLM) with log link and gamma family and the log-transformed OLS. The evaluation using simulated gamma data showed that the GAMLSS and GLM gamma model had similar bias, accuracy, and coverage and outperformed the GAMLSS GIG. When applied to simulated GIG data, the GLM gamma was similar or improved in bias, accuracy, and coverage compared to the GAMLSS GIG and gamma; furthermore, the GAMLSS estimators produced wildly inaccurate or overly-precise results in certain circumstances. Applying all models to empirical data on health care costs after a fall-related injury, all estimators produced similar coefficient estimates, but GAMLSS estimators produced spuriously smaller standard errors. Although no single alternative was best for all simulations, the GLM gamma was the most consistent, so we recommend against using GAMLSS estimators using GIG or gamma to test for differences in mean health care costs. Since GAMLSS offers many other flexible distributions, future work should evaluate whether GAMLSS is useful when predicting health care costs.
Similar content being viewed by others
References
Basu, A., Arondekar, B.V., Rathouz, P.J.: Scale of interest versus scale of estimation: comparing alternative estimators for the incremental costs of a comorbidity. Health Econ. 15(10), 1091–1107 (2006)
Basu, A.: Extended generalized linear models: simultaneous estimation of flexible link and variance functions. Stata. J. 5(4), 501–516 (2005)
Basu, A., Rathouz, P.J.: Estimating marginal and incremental effects on health outcomes using flexible link and variance function models. Biostatistics 6(1), 93–109 (2005)
Basu, A., Manning, W.G.: Issues for the next generation of health care cost analyses. Med. Care 47(7 Suppl 1), S109–S114 (2009)
Blough, D.K., Madden, C.W., Hornbrook, M.C.: Modeling risk using generalized linear models. J. Health Econ. 18(2), 153–171 (1999)
Bohl, A.A., Fishman, P.A., Ciol, M.A., Williams, B., Logerfo, J., Phelan, E.A.: A longitudinal analysis of total 3-year healthcare costs for older adults who experience a fall requiring medical care. J. Am. Geriatr. Soc. 58(5), 853–860 (2010)
Burton, A., Altman, D.G., Royston, P., Holder, R.L.: The design of simulation studies in medical statistics. Stat. Med. 25(24), 4279–4292 (2006)
Chou, C., Huang, W.: On characterizations of the gamma and generalized inverse gaussian distributions. Stat. Prob. Lett. 69, 381–388 (2004)
Duan, N., Manning, W.G., et al.: A comparison of alternative models for the demand for medical care. J. Busi. Econ. Stat. 1, 115–126 (1983)
Fishman, P.A., Goodman, M.J., Hornbrook, M.C., Meenan, R.T., Bachman, D.J., O’Keeffe Rosetti, M.C.: Risk adjustment using automated ambulatory pharmacy data: the RxRisk model. Med. Care 41(1), 84–99 (2003)
Hill, S.C., Miller, G.E.: Health expenditure estimation and functional form: applications of the generalized gamma and extended estimating equations models. Health Econ. 19(5), 608–627 (2010)
Manning, W.G.: The logged dependent variable, heteroscedasticity, and the retransformation problem. J. Health Econ. 17(3), 283–295 (1998)
Manning, W.G., Basu, A., Mullahy, J.: Generalized modeling approaches to risk adjustment of skewed outcomes data. J. Health Econ. 24(3), 465–488 (2005)
Manning, W.G., Mullahy, J.: Estimating log models: to transform or not to transform. J. Health Econ. 20(4), 461–494 (2001)
Mihaylova, B., Briggs, A., O’Hagan, A., Thompson, S.G.: Review of statistical methods for analyzing healthcare resources and costs. Health Econ. 20(8), 897–916 (2011)
Rigby, R., Stasinopoulos, D.: A flexible regression approach using GAMLSS in R. London Metropolitan University, London (2009)
Roudsari, B.S., Ebel, B.E., Corso, P.S., Molinari, N.A., Koepsell, T.D.: The acute medical care costs of fall-related injuries among the U.S. older adults. Injury 36(11), 1316–1322 (2005)
Stasinopoulos, D., Rigby, R.: Generalized additive models for location scale and shape. J. Stat. Softw. 23(7), 1–46 (2007)
van Buuren, S., Fredriks, M.: Worm plot: a simple diagnostic device for modelling growth reference curves. Stat. Med. 20(8), 1259–1277 (2001)
Acknowledgments
This research was supported by Cooperative Agreement U48-DP-000050 from the Centers for Disease Control and Prevention, Prevention Research Centers Program. The findings and conclusions in this manuscript are those of the authors and do not necessarily represent the official position of the Centers for Disease Control and Prevention nor the Prevention Research Centers Program. A special thanks to Dr. Sara L. Tamers, Ph.D. and Judith Yarrow for their critical edits.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bohl, A.A., Blough, D.K., Fishman, P.A. et al. Are generalized additive models for location, scale, and shape an improvement on existing models for estimating skewed and heteroskedastic cost data?. Health Serv Outcomes Res Method 13, 18–38 (2013). https://doi.org/10.1007/s10742-012-0086-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10742-012-0086-x