Limits...
The use of bootstrapping when using propensity-score matching without replacement: a simulation study.

Austin PC, Small DS - Stat Med (2014)

Bottom Line: An important issue when using propensity-score matching is how to estimate the standard error of the estimated treatment effect.The second method involved drawing bootstrap samples from the original sample and estimating the propensity score separately in each bootstrap sample and creating a matched sample within each of these bootstrap samples.The former approach was found to result in estimates of the standard error that were closer to the empirical standard deviation of the sampling distribution of estimated effects.

View Article: PubMed Central - PubMed

Affiliation: Institute for Clinical Evaluative Sciences, Toronto, Canada; Institute of Health Management, Policy and Evaluation, University of Toronto, Toronto, Canada; Schulich Heart Research Program, Sunnybrook Research Institute, Toronto, Canada.

Show MeSH

Related in: MedlinePlus

Empirical coverage rates of 95% confidence intervals (estimated propensity score).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4260115&req=5

fig02: Empirical coverage rates of 95% confidence intervals (estimated propensity score).

Mentions: The empirical coverage rates of estimated 95% confidence intervals obtained using the seven different methods (naïve parametric estimate, matched parametric estimate, simple bootstrap (normal-theory method), simple bootstrap (percentile method), simple bootstrap (BCa), complex bootstrap (normal-theory method), and complex bootstrap (percentile method)) are reported in Figure 2. As above, there is a separate panel for each of the three different types of outcome (continuous, binary, and survival). Because of our use of 1000 simulated datasets for each scenario, an empirical coverage rate less than 0.9365 or greater than 0.9635 is statistically significantly different than the advertised rate of 0.95, based on a standard normal-theory test. On each panel, we have superimposed vertical lines denoting empirical coverage rates of 0.9365, 0.95, and 0.9635.


The use of bootstrapping when using propensity-score matching without replacement: a simulation study.

Austin PC, Small DS - Stat Med (2014)

Empirical coverage rates of 95% confidence intervals (estimated propensity score).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4260115&req=5

fig02: Empirical coverage rates of 95% confidence intervals (estimated propensity score).
Mentions: The empirical coverage rates of estimated 95% confidence intervals obtained using the seven different methods (naïve parametric estimate, matched parametric estimate, simple bootstrap (normal-theory method), simple bootstrap (percentile method), simple bootstrap (BCa), complex bootstrap (normal-theory method), and complex bootstrap (percentile method)) are reported in Figure 2. As above, there is a separate panel for each of the three different types of outcome (continuous, binary, and survival). Because of our use of 1000 simulated datasets for each scenario, an empirical coverage rate less than 0.9365 or greater than 0.9635 is statistically significantly different than the advertised rate of 0.95, based on a standard normal-theory test. On each panel, we have superimposed vertical lines denoting empirical coverage rates of 0.9365, 0.95, and 0.9635.

Bottom Line: An important issue when using propensity-score matching is how to estimate the standard error of the estimated treatment effect.The second method involved drawing bootstrap samples from the original sample and estimating the propensity score separately in each bootstrap sample and creating a matched sample within each of these bootstrap samples.The former approach was found to result in estimates of the standard error that were closer to the empirical standard deviation of the sampling distribution of estimated effects.

View Article: PubMed Central - PubMed

Affiliation: Institute for Clinical Evaluative Sciences, Toronto, Canada; Institute of Health Management, Policy and Evaluation, University of Toronto, Toronto, Canada; Schulich Heart Research Program, Sunnybrook Research Institute, Toronto, Canada.

Show MeSH
Related in: MedlinePlus