Methods for Estimating Subgroup Effects in Cost-Effectiveness Analyses That Use Observational Data

Abstract

Decision makers require cost-effectiveness estimates for patient subgroups. In nonrandomized studies, propensity score (PS) matching and inverse probability of treatment weighting (IPTW) can address overt selection bias, but only if they balance observed covariates between treatment groups. Genetic matching (GM) matches on the PS and individual covariates using an automated search algorithm to directly balance baseline covariates. This article compares these methods for estimating subgroup effects in cost-effectiveness analyses (CEA). The motivating case study is a CEA of a pharmaceutical intervention, drotrecogin alfa (DrotAA), for patient subgroups with severe sepsis (n = 2726). Here, GM reported better covariate balance than PS matching and IPTW. For the subgroup at a high level of baseline risk, the probability that DrotAA was cost-effective ranged from 30% (IPTW) to 90% (PS matching and GM), at a threshold of £20 000 per quality-adjusted life-year. We then compared the methods in a simulation study, in which initially the PS was correctly specified and then misspecified, for example, by ignoring the subgroup-specific treatment assignment. Relative performance was assessed as bias and root mean squared error (RMSE) in the estimated incremental net benefits. When the PS was correctly specified and inverse probability weights were stable, each method performed well; IPTW reported the lowest RMSE. When the subgroup-specific treatment assignment was ignored, PS matching and IPTW reported covariate imbalance and bias; GM reported better balance, less bias, and more precise estimates. We conclude that if the PS is correctly specified and the weights for IPTW are stable, each method can provide unbiased cost-effectiveness estimates. However, unlike IPTW and PS matching, GM is relatively robust to PS misspecification.

Cemented, cementless, and hybrid prostheses for total hip replacement: cost effectiveness analysis

“…GenMatch is a multivariate matching method that aims to make the distribution of baseline characteristics as similar as possible, 26 and it has previously been used in evaluating relative effectiveness and cost effectiveness. [27][28][29] GenMatch selects matched pairs using a generalised Mahalanobis distance metric, which weights each baseline covariate included in the matching. The weights define alternative distance metrics, which differ in the relative importance given to matching each covariate.…”

A framework for conducting economic evaluations alongside natural experiments

“…Regression and matching methods can handle correlated data using a Bayesian framework (Nixon and Thompson (2005); Manca and Austin (2008)), as well as the non-parametric bootstrap (Sekhon and Grieve (2012) (Kreif et al (2012); Kreif et al (2013b)). Furthermore, flexible parametric and semiparametric approaches have been proposed to handle skewed cost distributions (Jones et al, 2015) and outcomes, e.g.…”

A review of the performance of different methods for propensity score matched subgroup analyses and a summary of their application in peer‐reviewed research studies

“…Their results were consistent with the others regarding matching on the subgroup specific PS versus an overall PS, with the former tending to result in less bias. Furthermore, they reported that in their simulations, which included a limited number of scenarios focused on cost effectiveness and binary outcomes, IPTW was more sensitive to PS misspecification, resulting in greater bias and variance than PS matching subgroup analyses.…”