Simulation Study on Performance of Balance Metrics in Propensity Score Weighting Method

Journal Title: JOURNAL OF CONTEMPORARY MEDICINE - Year 2017, Vol 7, Issue 3

Abstract

Objective: In the situation that randomization is not avaliable, to minimize the biasness in treatment arm assignments, the use of propensity score weighting method and the assessment of performances related to results obtained from generalized boosted and multinomial logistic regression (MLR) of propensity score weighting are aimed. Method: Results obtained from MLR and GBM are to compare with the help of a simulation study. In simulation study, data with n=500, 1000, 2000 sample size will be derived using 1000 repetitions on seven scenarios with three categorized treatment group, continuous outcome variable and continuous/binary covariates. The propensity weights will be found with the help of Propensity scores obtained from MLR and GBM and using these weights, the balance will be assessed using balance metrics with average treatment effect estimation (ATE). In study, “twang” package in R program is used. Results: As the number of samples increases, the balance values decreases more, so it seems that the biasness has fallen. As the scenarios become more complex, GBM produces better balance results. There are better results for MLR at main effect model. Trimming or removing excess weights ensures improving of balance.

Authors and Affiliations

Osman Demir, Anıl Dolgun, İlker Etikan, Yunus Emre Kuyucu

Keywords

Related Articles

Evaluation of adherence to cardiovascular risks, admission to education / counseling and adherence to the recommendations of adult patients who apply to Family Health Centers: A multi-center cross-sectional study

Aim: Cardiovascular system diseases (CVD), especially coronary heart disease, are among the leading causes of death all over the world. . In this study, we aimed to evaluate the patients' lifestyle status and to find out...

SPECT Gama Kemera Sistemi için Çekim Parametre Değişikliğinin Görüntü Kalitesine Etkisi

GİRİŞ: Bu çalışmada amacımız gama kamera çekim parametre değişikliklerinin görüntü kalitesi üzerine etkilerini araştırmaktır. YÖNTEM: Miyokard perfüzyon sintigrafisi ve tiroid sintigrafisi tetkiki için gönderilen toplam...

Erzurum Palandöken Devlet Hastanesi Çalışanlarında HBV, HCV ve HIV Seroprevalansı

ÖZET AMAÇ: HBV, HCV ve HIV toplum sağlığını etkileyen önemli küresel bir sağlık sorunudur. Sağlık çalışanları kan ve vücut sıvılarıyla karşılaşmaları sebebiyle doğrudan risk altındadırlar. Bu çalışmada 2015-2017 tarihle...

Propensity Skor Ağırlıklandırma Yönteminde Denge Metriklerinin Performansı Üzerine Benzetim Çalışması

Amaç: Randomizasyonun sağlanamadığı durumlarda bireylerin tedavi kollarına atanmasında yanlılığı minimize etmek için propensity skor ağırlıklandırma yönteminin kullanılmasını ve bu yöntemin genelleştirilmiş boosted ve ço...

Time-Resolved Contrast-Enhanced Magnetic Resonance Angiography Versus Digital Subtraction Angiography in Internal Carotid Artery Stenosis

Objectives: In this study, digital subtraction angiography (DSA) being taken as a reference, the sensitivity, specificity, positive and negative predictive values (PPV and NPV), and diagnostic accuracy of time-resolved i...

Download PDF file
  • EP ID EP423313
  • DOI 10.16899/gopctd.349948
  • Views 110
  • Downloads 0

How To Cite

Osman Demir, Anıl Dolgun, İlker Etikan, Yunus Emre Kuyucu (2017). Simulation Study on Performance of Balance Metrics in Propensity Score Weighting Method. JOURNAL OF CONTEMPORARY MEDICINE, 7(3), 265-277. https://europub.co.uk/articles/-A-423313