Should a propensity score model be super? The utility of ensemble procedures for causal adjustment

2018 ◽  
Vol 38 (9) ◽  
pp. 1690-1702 ◽  
Author(s):  
Shomoita Alam ◽  
Erica E. M. Moodie ◽  
David A. Stephens
Keyword(s):  
Propensity Score ◽  
Propensity Score Model ◽  
Score Model

scholarly journals Causal Subclassification Tree Algorithm and Robust Causal Effect Estimation via Subclassification

2020 ◽  
Vol 10 (1) ◽  
pp. 40
Author(s):  
Tomoshige Nakamura ◽  
Mihoko Minami
Keyword(s):  
Propensity Score ◽  
Propensity Scores ◽  
Causal Effect ◽  
Model Misspecification ◽  
Robust Estimator ◽  
Propensity Score Model ◽  
Confounding Variables ◽  
Score Model ◽  
Effect Estimation ◽  
Weighting Methods

In observational studies, the existence of confounding variables should be attended to, and propensity score weighting methods are often used to eliminate their e ects. Although many causal estimators have been proposed based on propensity scores, these estimators generally assume that the propensity scores are properly estimated. However, researchers have found that even a slight misspecification of the propensity score model can result in a bias of estimated treatment effects. Model misspecification problems may occur in practice, and hence, using a robust estimator for causal effect is recommended. One such estimator is a subclassification estimator. Wang, Zhang, Richardson, & Zhou (2020) presented the conditions necessary for subclassification estimators to have $\sqrt{N}$-consistency and to be asymptotically well-defined and suggested an idea how to construct subclasses.

A Care Bundle Intervention to Prevent Surgical Site Infections After a Craniotomy

2020 ◽  
Author(s):  
Emilio Jiménez-Martínez ◽  
Guillermo Cuervo ◽  
Jordi Carratalà ◽  
Ana Hornero ◽  
Pilar Ciercoles ◽  
...  
Keyword(s):  
Propensity Score ◽  
Cox Regression ◽  
Surgical Site Infections ◽  
Care Bundle ◽  
Primary Study ◽  
Preventive Strategy ◽  
Propensity Score Model ◽  
Vancomycin Powder ◽  
Score Model ◽  
Control Study

Abstract Background Although surgical site infections after a craniotomy (SSI-CRANs) are a serious problem that involves significant morbidity and costs, information on their prevention is scarce. We aimed to determine whether the implementation of a care bundle was effective in preventing SSI-CRANs. Methods A historical control study was used to evaluate the care bundle, which included a preoperative shower with 4% chlorhexidine soap, appropriate hair removal, adequate preoperative systemic antibiotic prophylaxis, the administration of 1 g of vancomycin powder into the subgaleal space before closing, and a postoperative dressing of the incisional surgical wound with a sterile absorbent cover. Patients were divided into 2 groups: preintervention (January 2013 to December 2015) and intervention (January 2016 to December 2017). The primary study end point was the incidence of SSI-CRANs within 1 year postsurgery. Propensity score matching was performed, and differences between the 2 study periods were assessed using Cox regression models. Results A total of 595 and 422 patients were included in the preintervention and intervention periods, respectively. The incidence of SSI-CRANs was lower in the intervention period (15.3% vs 3.5%; P < .001). Using a propensity score model, 421 pairs of patients were matched. The care bundle intervention was independently associated with a reduced incidence of SSI-CRANs (adjusted odds ratio, 0.23; 95% confidence interval, .13–.40; P < .001). Conclusions The care bundle intervention was effective in reducing SSI-CRAN rates. The implementation of this multimodal preventive strategy should be considered in centers with high SSI-CRAN incidences.

Inadvertent Splenectomy During Resection for Colorectal Cancer Does Not Increase Long-term Mortality in a Propensity Score Model

2016 ◽  
Vol 59 (12) ◽  
pp. 1150-1159 ◽  
Author(s):  
Ida Lolle ◽  
Hans-Christian Pommergaard ◽  
David F. Schefte ◽  
Orhan Bulut ◽  
Peter-Martin Krarup ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Propensity Score ◽  
Propensity Score Model ◽  
Score Model ◽  
Long Term Mortality

A new weighted balance measure helped to select the variables to be included in a propensity score model

2015 ◽  
Vol 68 (12) ◽  
pp. 1415-1422.e2 ◽  
Author(s):  
Emmanuel Caruana ◽  
Sylvie Chevret ◽  
Matthieu Resche-Rigon ◽  
Romain Pirracchio
Keyword(s):  
Propensity Score ◽  
Propensity Score Model ◽  
Score Model

scholarly journals Comparison of Dizziness Factors for Mild Traumatic Brain Injury Patients with and without Dizziness: A Factor Analysis and Propensity Score Model Study

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Hon-Ping Ma ◽  
Jiann Ruey Ong ◽  
Ju-Chi Ou ◽  
Yung-Hsiao Chiang ◽  
Shoou-Yang Lian
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Propensity Score ◽  
Internal Validity ◽  
The United States ◽  
Chinese Version ◽  
English Version ◽  
Propensity Score Model ◽  
Model Study ◽  
Score Model

Traumatic brain injury (TBI) causes major socioeconomic problems worldwide. In the United States, nearly three-quarters of patients with TBI have mild TBI (mTBI). 32% of these patients may develop dizziness. In this study, we analyzed the factor structure of the traditional Chinese version of the DHI and evaluate the differences in DHI factors between dizziness and nondizziness groups. In total, 315 patients with mTBI, comprising 158 with self-reported dizziness and 157 without dizziness, were recruited from three hospitals. The responses for Beck Depression Inventory (BDI), Beck Anxiety Inventory (BAI), Epworth Sleepiness Scale (ESS), and Pittsburgh Sleep Quality Index (PSQI) demonstrated between-group differences. The Chinese DHI had internal validity and had four factors that differed from the English version (3 aspects). The group effects for the physical subscale remained significantly different even after adjustments in the propensity score model. For the Chinese version, two of four factors remained significantly different in the effects between self-reported dizziness and nondizziness groups. The factors of our Chinese DHI differed from those of the original English version of DHI. After adjustments using the propensity score model, the physical subscale demonstrated significant differences between the self-reported dizziness and nondizziness groups. Only two factors from our Chinese DHI were significantly different; moreover, it contained only three physical, five functional, and three emotional items.

Estimation of average treatment effects based on parametric propensity score model

2010 ◽  
Vol 140 (3) ◽  
pp. 806-816 ◽  
Author(s):  
Lili Yao ◽  
Zhihua Sun ◽  
Qihua Wang
Keyword(s):  
Propensity Score ◽  
Treatment Effects ◽  
Propensity Score Model ◽  
Average Treatment ◽  
Average Treatment Effects ◽  
Score Model

Survival Outcome Between Hepatic Resection and Transarterial Embolization for Hepatocellular Carcinoma More Than 10 cm: A Propensity Score Model

2015 ◽  
Vol 39 (6) ◽  
pp. 1510-1518 ◽  
Author(s):  
Yi-Chia Chan ◽  
Catherine S. Kabiling ◽  
Vinod G. Pillai ◽  
Gustavo Aguilar ◽  
Chih-Chi Wang ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Propensity Score ◽  
Hepatic Resection ◽  
Transarterial Embolization ◽  
Survival Outcome ◽  
Propensity Score Model ◽  
Score Model
Sign in / Sign up

Export Citation Format

Share Document