One-to-many propensity score matching in cohort studies

Division of Pharmacoepidemiology and Pharmacoeconomics
Pharmacoepidemiology and Drug Safety (Impact Factor: 3.17). 05/2012; 21 Suppl 2:69-80. DOI: 10.1002/pds.3263
Source: PubMed

ABSTRACT Among the large number of cohort studies that employ propensity score matching, most match patients 1:1. Increasing the matching ratio is thought to improve precision but may come with a trade-off with respect to bias.
To evaluate several methods of propensity score matching in cohort studies through simulation and empirical analyses.
We simulated cohorts of 20,000 patients with exposure prevalence of 10%-50%. We simulated five dichotomous and five continuous confounders. We estimated propensity scores and matched using digit-based greedy ("greedy"), pairwise nearest neighbor within a caliper ("nearest neighbor"), and a nearest neighbor approach that sought to balance the scores of the comparison patient above and below that of the treated patient ("balanced nearest neighbor"). We matched at both fixed and variable matching ratios and also evaluated sequential and parallel schemes for the order of formation of 1:n match groups. We then applied this same approach to two cohorts of patients drawn from administrative claims data.
Increasing the match ratio beyond 1:1 generally resulted in somewhat higher bias. It also resulted in lower variance with variable ratio matching but higher variance with fixed. The parallel approach generally resulted in higher mean squared error but lower bias than the sequential approach. Variable ratio, parallel, balanced nearest neighbor matching generally yielded the lowest bias and mean squared error.
1:n matching can be used to increase precision in cohort studies. We recommend a variable ratio, parallel, balanced 1:n, nearest neighbor approach that increases precision over 1:1 matching at a small cost in bias.

  • Source
    Pharmacoepidemiology and Drug Safety 05/2012; 21 Suppl 2:1-5. DOI:10.1002/pds.3270 · 3.17 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Under Medicare Part D, patient characteristics influence plan choice, which in turn influences Part D coverage gap entry. We compared predefined propensity score (PS) and high-dimensional propensity score (hdPS) approaches to address such "confounding by health system use" in assessing whether coverage gap entry is associated with cardiovascular events or death. We followed 243,079 Medicare patients aged 65+ years with linked prescription, medical, and plan-specific data in 2005-2007. Patients reached the coverage gap and were followed until an event or year's end. Exposed patients were responsible for drug costs in the gap; unexposed patients (patients with non-Part D drug insurance and Part D patients receiving a low-income subsidy) received financial assistance. Exposed patients were 1:1 PS-matched or hdPS-matched to unexposed patients. The PS model included 52 predefined covariates; the hdPS model added 400 empirically identified covariates. Hazard ratios for death and any of five cardiovascular outcomes were compared. In sensitivity analyses, we explored residual confounding using only low-income subsidy patients in the unexposed group. In unadjusted analyses, exposed patients had no greater hazard of death (HR = 1.00; 95%CI, 0.84-1.20) or other outcomes. PS-matched (HR = 1.29; 0.99-1.66) and hdPS-matched (HR = 1.11; 0.86-1.42) analyses showed elevated but non-significant hazards of death. In sensitivity analyses, the PS analysis showed a protective effect (HR = 0.78; 0.61-0.98), whereas the hdPS analysis (HR = 1.06; 0.82-1.37) confirmed the main hdPS findings. Although the PS-matched analysis suggested elevated but non-significant hazards of death among patients with no financial assistance during the gap, the hdPS analysis produced lower estimates that were stable across sensitivity analyses.
    Pharmacoepidemiology and Drug Safety 05/2012; 21 Suppl 2:90-8. DOI:10.1002/pds.3250 · 3.17 Impact Factor
  • American Journal of Kidney Diseases 09/2012; 61(1). DOI:10.1053/j.ajkd.2012.08.030 · 5.76 Impact Factor
Show more