EVALUATING COSTS WITH UNMEASURED CONFOUNDING: A SENSITIVITY ANALYSIS FOR THE TREATMENT EFFECT

Overview

Journal Ann Appl Stat

Date 2014 Mar 4

PMID 24587844

Citations 6

Authors

Elizabeth A Handorf

Justin E Bekelman

Daniel F Heitjan

Nandita Mitra

Affiliations

Soon will be listed here.

Abstract

Estimates of the effects of treatment on cost from observational studies are subject to bias if there are unmeasured confounders. It is therefore advisable in practice to assess the potential magnitude of such biases. We derive a general adjustment formula for loglinear models of mean cost and explore special cases under plausible assumptions about the distribution of the unmeasured confounder. We assess the performance of the adjustment by simulation, in particular, examining robustness to a key assumption of conditional independence between the unmeasured and measured covariates given the treatment indicator. We apply our method to SEER-Medicare cost data for a stage II/III muscle-invasive bladder cancer cohort. We evaluate the costs for radical cystectomy combined radiation/chemotherapy, and find that the significance of the treatment effect is sensitive to plausible unmeasured Bernoulli, Poisson and Gamma confounders.

Citing Articles

Nested g-computation: A causal approach to analysis of censored medical costs in the presence of time-varying treatment.

Spieker A, Ko E, Roy J, Mitra N J R Stat Soc Ser C Appl Stat. 2021; 69(5):1189-1208.

PMID: 34108743 PMC: 8186489. DOI: 10.1111/rssc.12441.

Net benefit separation and the determination curve: A probabilistic framework for cost-effectiveness estimation.

Spieker A, Illenberger N, Roy J, Mitra N Stat Methods Med Res. 2021; 30(5):1306-1319.

PMID: 33826460 PMC: 8211369. DOI: 10.1177/0962280221995972.

Illustration of the Impact of Unmeasured Confounding Within an Economic Evaluation Based on Nonrandomized Data.

Guertin J, Bowen J, De Rose G, OReilly D, Tarride J MDM Policy Pract. 2018; 2(1):2381468317697711.

PMID: 30288418 PMC: 6124939. DOI: 10.1177/2381468317697711.

Estimating cost-effectiveness from claims and registry data with measured and unmeasured confounders.

Handorf E, Heitjan D, Bekelman J, Mitra N Stat Methods Med Res. 2018; 28(7):2227-2242.

PMID: 29468944 PMC: 7673459. DOI: 10.1177/0962280218759137.

Propensity score and doubly robust methods for estimating the effect of treatment on censored cost.

Li J, Handorf E, Bekelman J, Mitra N Stat Med. 2015; 35(12):1985-99.

PMID: 26678242 PMC: 4848146. DOI: 10.1002/sim.6842.

References

Liu L . Joint modeling longitudinal semi-continuous data and survival, with application to longitudinal medical cost data. Stat Med. 2008; 28(6):972-86. DOI: 10.1002/sim.3497. View

Lin D . Regression analysis of incomplete medical cost data. Stat Med. 2003; 22(7):1181-200. DOI: 10.1002/sim.1377. View

Lin D, Psaty B, Kronmal R . Assessing the sensitivity of regression results to unmeasured confounders in observational studies. Biometrics. 1998; 54(3):948-63. View

Willan A, Lin D, Cook R, Chen E . Using inverse-weighting in cost-effectiveness analysis with censored data. Stat Methods Med Res. 2003; 11(6):539-51. DOI: 10.1191/0962280202sm308ra. View

Bang H, Tsiatis A . Median regression with censored cost data. Biometrics. 2002; 58(3):643-9. DOI: 10.1111/j.0006-341x.2002.00643.x. View

Lin D, Feuer E, Etzioni R, Wax Y . Estimating medical costs from incomplete follow-up data. Biometrics. 1997; 53(2):419-34. View

Arah O, Chiba Y, Greenland S . Bias formulas for external adjustment and sensitivity analysis of unmeasured confounders. Ann Epidemiol. 2008; 18(8):637-46. DOI: 10.1016/j.annepidem.2008.04.003. View

Liu L, Huang X, OQuigley J . Analysis of longitudinal data in the presence of informative observational times and a dependent terminal event, with application to medical cost data. Biometrics. 2007; 64(3):950-958. DOI: 10.1111/j.1541-0420.2007.00954.x. View

Wang H, Heitjan D . Modeling heaping in self-reported cigarette counts. Stat Med. 2008; 27(19):3789-804. PMC: 2684113. DOI: 10.1002/sim.3281. View

10.

Baris D, Karagas M, Verrill C, Johnson A, Andrew A, Marsit C . A case-control study of smoking and bladder cancer risk: emergent patterns over time. J Natl Cancer Inst. 2009; 101(22):1553-61. PMC: 2778671. DOI: 10.1093/jnci/djp361. View

11.

Lin D . Linear regression analysis of censored medical costs. Biostatistics. 2003; 1(1):35-47. DOI: 10.1093/biostatistics/1.1.35. View

12.

Schrag D, Mitra N, Xu F, Rabbani F, Bach P, Herr H . Cystectomy for muscle-invasive bladder cancer: patterns and outcomes of care in the Medicare population. Urology. 2005; 65(6):1118-25. DOI: 10.1016/j.urology.2004.12.029. View

13.

Hernan M, Robins J . Method for conducting sensitivity analysis. Biometrics. 2001; 55(4):1316-7. View

14.

Dodd S, Bassi A, Bodger K, Williamson P . A comparison of multivariable regression models to analyse cost data. J Eval Clin Pract. 2006; 12(1):76-86. DOI: 10.1111/j.1365-2753.2006.00610.x. View

15.

Basu A, Manning W . Estimating lifetime or episode-of-illness costs under censoring. Health Econ. 2010; 19(9):1010-28. DOI: 10.1002/hec.1640. View

16.

Etzioni R, Feuer E, Sullivan S, Lin D, Hu C, Ramsey S . On the use of survival analysis techniques to estimate medical care costs. J Health Econ. 1999; 18(3):365-80. DOI: 10.1016/s0167-6296(98)00056-3. View

17.

Black N . Why we need observational studies to evaluate the effectiveness of health care. BMJ. 1996; 312(7040):1215-8. PMC: 2350940. DOI: 10.1136/bmj.312.7040.1215. View

18.

McCandless L, Gustafson P, Levy A . Bayesian sensitivity analysis for unmeasured confounding in observational studies. Stat Med. 2006; 26(11):2331-47. DOI: 10.1002/sim.2711. View

19.

Yabroff K, Lamont E, Mariotto A, Warren J, Topor M, Meekins A . Cost of care for elderly cancer patients in the United States. J Natl Cancer Inst. 2008; 100(9):630-41. DOI: 10.1093/jnci/djn103. View

20.

Mitra N, Heitjan D . Sensitivity of the hazard ratio to nonignorable treatment assignment in an observational study. Stat Med. 2006; 26(6):1398-414. DOI: 10.1002/sim.2606. View