Skip to main content

Advertisement

SpringerLink
Log in

Modeling right-censored medical cost data in regression and the effects of covariates

  • Original Paper
  • Published:
Statistical Methods & Applications Aims and scope Submit manuscript

Abstract

This paper focuses on the problem of modeling medical costs with covariates when the cost data are subject to right-censoring. The prevailing methods are divided into three categories, (a) the inverse probability weighted (IPW) regressions; (b) the generalized survival-adjusted estimators; and (c) the joint-modeling methods. Comparisons are made both in and between categories to demonstrate their different mechanisms to handle the informative censoring, to take into account the covariates and the way they interpret the covariates effects. Based on the above discussion, we believe that the linear or generalized linear regressions using the IPW scheme are very popular due to its convenience to fit and interpret, which could be a good choice in practice with additional conditional means to address the role of survival to some extent. The recently proposed generalized survival-adjusted estimator is very intuitive as the derivative of the estimation function naturally decomposes the effects of covariates into the intensity part and the survival part, therefore especially useful when the covariates have substantial effect on survival. The joint-modelling methods have the advantage in providing the access to the correlation between medical cost and survival, although they suffer from theoretical and computational complexity. The effect of covariates on cost through survival in this kind of joint-modelling methods could be a desirable topic for further research.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Notes

  1. More discussion about marked point process, please refer to Zhao and Tsiatis (1997), Tsiatis (2000) or to Strawderman (2000).

References

  • Bang H (2005) Medical cost analysis: application to colorectal cancer data from the SEER Medicare database. Contemp Clin Trial 26(5):586–597

    Article  Google Scholar 

  • Bang H, Tsiatis AA (2000) Estimating medical costs with censored data. Biometrika 87(2):329–343

    Article  MathSciNet  MATH  Google Scholar 

  • Bang H, Tsiatis AA (2002) Median regression with censored cost data. Biometrics 58(3):643–649

    Article  MathSciNet  MATH  Google Scholar 

  • Başer O, Gardiner JC, Bradley CJ et al (2004) Estimation from censored medical cost data. Biom J 46(3):351–363

    Article  MathSciNet  Google Scholar 

  • Başer O, Gardiner JC, Bradley CJ et al (2006) Longitudinal analysis of censored medical cost data. Health Econ 15(5):513–525

    Article  Google Scholar 

  • Basu A, Manning WG (2010) Estimating lifetime or episode-of-illness costs under censoring. Health Econ 19(1):1010–1028

    Article  Google Scholar 

  • Carides GW (1998) Estimation of mean treatment cost in the presence of right-censoring. Ph.D. Thesis, Temple University, Philadelphia

  • Carides GW, Heyse JF, Iglewicz B (2000) A regression-based method for estimating mean treatment cost in the presence of right-censoring. Biostatistics 1(3):299–313

    Article  MATH  Google Scholar 

  • Deng D (2016) Estimating the cumulative mean function for history process with time-dependent covariates and censoring mechanism. Stat Med 35(25):4624–4636

    Article  MathSciNet  Google Scholar 

  • Etzioni RD, Feuer EJ, Sullivan SD et al (1999) On the use of survival analysis techniques to estimate medical care costs. J Health Econ 18(3):365–80

    Article  Google Scholar 

  • Fenn P, McGuire A, Phillips V, Backhouse M, Jones D (1995) The analysis of censored treatment cost data in economic evaluation. Med Care 33(8):851–863

    Article  Google Scholar 

  • Hagan O, Stevens JW (2004) On estimators of medical costs with censored data. J Health Econ 23(3):615–625

    Article  Google Scholar 

  • Heitjan DF, Kim CY, Li H (2004) Bayesian estimation of cost-effectiveness from censored data. Stat Med 23(8):1297–1309

    Article  Google Scholar 

  • Hiatt RA, Quesenberry CP, Selby JV, Fireman BH, Knight A (1990) The cost of acquired immunodeficiency syndrome in Northern California: the experience of a large prepaid health plan. Arch Internal Med 150(4):833–838

    Article  Google Scholar 

  • Horvitz DG, Thompson DJ (1952) A generalization of sampling without replacement from a finite universe. J Am Stat Assoc 47(260):663–685

    Article  MathSciNet  MATH  Google Scholar 

  • Huang Y (2002) Calibration regression of censored lifetime medical cost. J Am Statist Assoc 97(457):318–327 Correction, 97:661

    Article  MathSciNet  MATH  Google Scholar 

  • Lin DY (2000) Linear regression analysis of censored medical costs. Biostatistics 1(1):35–47

    Article  MATH  Google Scholar 

  • Lin DY (2003) Regression analysis of incomplete medical cost data. Stat Med 22(7):1181–1200

    Article  Google Scholar 

  • Lin DY, Feuer EJ, Etzioni R et al (1997) Estimating medical costs from incomplete follow-up data. Biometrics 53(2):113–128

    Article  MATH  Google Scholar 

  • Liu L (2009) Joint modeling longitudinal semi-continuous data and survival, with application to longitudinal medical cost data. Stat Med 28(6):972–986

    Article  MathSciNet  Google Scholar 

  • Liu L, Wolfe RA, Kalbfleisch JD (2007) A shared random effects model for censored medical costs and mortality. Stat Med 26(1):139–155

    Article  MathSciNet  Google Scholar 

  • Liu L, Conaway MR, Knaus WA et al (2008) A random effects four-part model, with application to correlated medical costs. Comput Stat Data Anal 52(9):4458–4473

    Article  MathSciNet  MATH  Google Scholar 

  • Locatelli I, Marazzi A (2013) Robust parametric indirect estimates of the expected cost of a hospital stay with covariates and censored data. Stat Med 32(14):2457–2466

    Article  MathSciNet  Google Scholar 

  • Pullenayegum EM, Willan AR (2007) Semi-parametric regression models for cost-effectiveness analysis: improving the efficiency of estimation from censored data. Stat Med 26(17):3274–3299

    Article  MathSciNet  Google Scholar 

  • Quesenberry CP, Fireman B, Hiatt RA, Selby JV (1989) A survival analysis of hospitalization among patients with acquired immunodeficiency syndrome. Am J Public Health 79(12):1643–1647

    Article  Google Scholar 

  • Raikou M, McGuire A (2004) Estimating medical care costs under conditions of censoring. J Health Econ 23(3):443–470

    Article  Google Scholar 

  • Robins JM, Rotnitzky A, Zhao LP (1994) Estimation of regression coefficients when some regressors are not always observed. J Am Stat Assoc 89:846–66

    Article  MathSciNet  MATH  Google Scholar 

  • Strawderman RL (2000) Estimating the mean of an increasing stochastic process at a censored stopping time. J Am Statist Assoc 95(452):1192–1208

    Article  MathSciNet  MATH  Google Scholar 

  • Wang H, Zhao H (2007) Regression analysis of mean quality-adjusted lifetime with censored data. Biostatistics 8(2):368–382

    Article  MATH  Google Scholar 

  • Zhao H, Tian L (2001) On estimating medical cost and incremental cost-effectiveness ratios with censored data. Biometrics 57(4):1002–1008

    Article  MathSciNet  MATH  Google Scholar 

  • Zhao H, Tsiatis AA (1997) A consistent estimator for the distribution of quality-adjusted survival time. Biometrika 84(2):339–348

    Article  MathSciNet  MATH  Google Scholar 

  • Zhao H, Tsiatis AA (2000) Estimating mean quality adjusted lifetime with censored data. Sankhya. Spec Issue Biostat Ser B 62:175–188

    MATH  Google Scholar 

  • Zhao H, Bang H, Wang H et al (2007) On the equivalence of some medical cost estimators with censored data. Stat Med 26(24):4520–4530

    Article  MathSciNet  Google Scholar 

  • Zhao H, Zuo C, Chen S et al (2012) Nonparametric inference for median costs with censored data. Biometrics 68(3):717–725

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Statistics and Mathematics, Central University of Finance and Economics, Beijing, 10081, China

    Lu Deng

  2. Division of Biostatistics, Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada

    Wendy Lou

  3. Biostatistics Research Unit, University Health Network, Toronto, ON, Canada

    Nicholas Mitsakakis

  4. Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, ON, Canada

    Nicholas Mitsakakis

Authors
  1. Lu Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wendy Lou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nicholas Mitsakakis
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nicholas Mitsakakis.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Deng, L., Lou, W. & Mitsakakis, N. Modeling right-censored medical cost data in regression and the effects of covariates. Stat Methods Appl 28, 143–155 (2019). https://doi.org/10.1007/s10260-018-0428-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10260-018-0428-0

Keywords

Search

Navigation