Propensity score based methods for estimating the treatment effects based on observational studies.

Abdia, Younathan

doi:10.18297/etd/2504

Cited by 2 publications

(3 citation statements)

References 5 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our early investigation, we ensembled GPS estimation models by using rank aggregation and bootstrap methods. 30 However, the ensembled GPS method did not generate much improved ATE estimates. The enDR developed in this article coupled with the optimal GPS method (ie, Opt MinMax ) provided much improved estimates for ATEs.…”

Section: Discussionmentioning

confidence: 94%

See 1 more Smart Citation

Estimation of average treatment effects among multiple treatment groups by using an ensemble approach

Yan

Abdia

Datta

et al. 2019

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

In observational studies, generalized propensity score (GPS)–based statistical methods, such as inverse probability weighting (IPW) and doubly robust (DR) method, have been proposed to estimate the average treatment effect (ATE) among multiple treatment groups. In this article, we investigate the GPS‐based statistical methods to estimate treatment effects from two aspects. The first aspect of our investigation is to obtain an optimal GPS estimation method among four competing GPS estimation methods by using a rank aggregation approach. We further examine whether the optimal GPS‐based IPW and DR methods would improve the performance for estimating ATE. It is well known that the DR method is consistent if either the GPS or the outcome models are correctly specified. The second aspect of our investigation is to examine whether the DR method could be improved if we ensemble outcome models. To that end, bootstrap method and rank aggregation method are used to obtain the ensemble optimal outcome model from several competing outcome models, and the resulting outcome model is incorporated into the DR method, resulting in an ensemble DR (enDR) method. Extensive simulation results indicate that the enDR method provides the best performance in estimating the ATE regardless of the method used for estimating GPS. We illustrate our methods using the MarketScan healthcare insurance claims database to examine the treatment effects among three different bones and substitutes used for spinal fusion surgeries. We draw conclusions based on the estimates from the enDR method coupled with the optimal GPS estimation method.

show abstract

Section: Discussionmentioning

confidence: 94%

“…However, the random forest has the worst covariate balance (see Figures and S3), resulting in highly biased estimators for ATEs. In our early investigation, we ensembled GPS estimation models by using rank aggregation and bootstrap methods . However, the ensembled GPS method did not generate much improved ATE estimates.…”

Section: Discussionmentioning

confidence: 99%

Estimation of average treatment effects among multiple treatment groups by using an ensemble approach

Yan

Abdia

Datta

et al. 2019

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the case study based on the MarketScan dataset, the random forest has a slightly larger correct classification rate (0.479) than the multinomial logistic regression model In our early investigation, we ensembled GPS estimation models by using rank aggregation and bootstrap methods (Abdia, 2016). However, the ensembled GPS method did not generate much improved ATE estimates.…”

Section: Discussionmentioning

confidence: 92%

Statistical methods for estimating and testing treatment effect for multiple treatment groups in observational studies.

Yan¹

View full text Add to dashboard Cite

Propensity score based methods for estimating the treatment effects based on observational studies.

Cited by 2 publications

References 5 publications

Estimation of average treatment effects among multiple treatment groups by using an ensemble approach

Estimation of average treatment effects among multiple treatment groups by using an ensemble approach

Statistical methods for estimating and testing treatment effect for multiple treatment groups in observational studies.

Contact Info

Product

Resources

About