Latent Class Models Reveal Poor Agreement between Discrete-Choice and Time Tradeoff Preferences

Medical Decision Making - Tập 39 Số 4 - Trang 421-436 - 2019
Eleanor Pullenayegum1,2, A. Simon Pickard3, Feng Xie4,5
1Child Health Evaluative Sciences, Hospital for Sick Children, Toronto, ON, Canada
2Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada
3Department of Pharmacy Systems, Outcomes and Policy, College of Pharmacy, University of Illinois at Chicago, Chicago, IL, USA
4Centre for Health Economics and Policy Analysis, McMaster University, Hamilton, ON, Canada
5Department of Health Research Methods, Evidence, and Impact (formerly Clinical Epidemiology and Biostatistics), McMaster University, Hamilton, ON, Canada

Tóm tắt

Background. In health economics, there has been interest in using discrete-choice experiments (DCEs) to derive preferences for health states in lieu of previously established approaches like time tradeoff (TTO). We examined whether preferences elicited through DCEs are associated and agree with preferences elicited through TTO tasks. Methods. We used data from 1073 respondents to the Canadian EQ-5D-5L valuation study. Multivariate mixed-effects models specified a common likelihood for the TTO and discrete-choice data, with separate but correlated random effects for the TTO and DCE data, for each of the 5 EQ-5D-5L dimensions. Multivariate latent class models allowed separate but associated latent classes for the DCE and TTO data. Results. Correlation between the random effects for the 2 tasks ranged from −0.12 to 0.75, with only pain/discomfort and anxiety/depression having at least a 50% posterior probability of strong (>0.6) correlation. Latent classes for the TTO and DCE data both featured 1 latent class capturing participants attaching large disutilities to pain/discomfort, another capturing participants attaching large disutility to anxiety/depression, and the third class capturing the remainder. Agreement in class membership was poor (κ coefficient: 0.081; 95% credible interval, 0.033–0.13). Fewer respondents expressed strong disutilities for problems with anxiety/depression or pain/discomfort in the TTO than the DCE data (17% v. 55%, respectively). Conclusions. Stated preferences using TTO and DCEs show association across dimensions but poor agreement at the level of individual health states within respondents. Joint models that assume agreement between DCE and TTO have been used to develop national value sets for the EQ-5D-5L. This work indicates that when combining data from both techniques, methods requiring association but not agreement are needed.

Từ khóa


Tài liệu tham khảo

National Institute for Health and Care Excellence, 2013, Guide to the Methods of Technology Appraisal

Pharmaceutical Benefits Advisory Committee, 2013, Guidelines for Preparing Submissions to the Pharmaceutical Benefits Advisory Committee

Canadian Agency for Drugs and Technologies in Health, 2006, Guidelines for Economic Evaluation of Health Technologies

10.1097/01.mlr.0000135827.18610.0d

10.1097/00005650-199607000-00004

10.1016/0168-8510(90)90421-9

10.1016/0167-6296(86)90020-2

10.1002/hec.1069

10.1017/CBO9780511753831

10.1007/978-1-4020-5753-3

10.1002/hec.1697

10.1177/0272989X8400400307

10.1016/0895-4356(92)90099-9

10.1177/0272989X9401400110

10.1016/S0167-6296(96)00509-7

10.1016/j.jclinepi.2008.07.002

10.1097/MLR.0b013e31819432ba

10.1177/0272989X13475718

10.1186/1478-7954-1-12

10.1177/0272989X18778295

Bland JM, 1986, Lancet, 1

McCulloch C, 2002, Generalized, Linear and Mixed Models

Xie F, Health Econ

10.1177/0272989X14559542

10.1093/biomet/61.2.215

10.1097/MLR.0000000000000447

10.1136/bmj.313.7057.569

10.1046/j.1365-2753.2000.00216.x

10.1097/00005650-199711000-00002

10.1177/0272989X0102100102

10.1186/1478-7954-1-11

10.1007/s10198-004-0264-z

10.1097/00005650-200503000-00003

10.1111/j.1524-4733.2008.00349.x

10.1177/1403494809105287

10.1111/j.1524-4733.2009.00596.x

10.1007/s10198-011-0351-x

10.1016/j.jval.2011.04.009

10.1016/j.jval.2011.09.002

Plummer M, Paper presented at: International Workshop on Distributed Statistical Computing

Geweke J., 1992, Bayesian Statistics, 4

10.1287/opre.31.6.1109

10.1214/ss/1177011143

Plummer M, 2006, R News, 6, 7

Proust-Lima C, 2013, Br J Math Stat Psychol, 66

10.1109/TAC.1974.1100705

10.1214/aos/1176344136

R Core Team, 2011, R: A Language and Environment for Statistical Computing

Chambers EA, 1967, Biometrika, 54

10.1198/jcgs.2010.09008

10.18637/jss.v069.c01

10.1177/001316446002000104

Gelman A, 1996, Stat Sinica, 6, 733

Evans JD., 1996, Straightforward Statistics for the Behavioral Sciences

10.1006/jmps.2001.1390

10.2307/1914185

10.1056/NEJM198205273062103

10.1177/0272989X9901900412

10.1016/j.jhealeco.2011.11.004

10.1097/MLR.0000000000000283

Devlin N, 2016, Valuing Health-Related Quality of Life: An EQ-5D-5L Value Set for England

10.1016/j.jval.2016.03.1834

Thông tin
Thông tin xuất bản

Medical Decision Making

Tập 39 Số 4

421-436

Thông tin tác giả