The comparative performance of logistic regression and random forest in propensity score methods: A simulation study
Propensity scores (PS) are typically estimated using logistic regression (LR). Machine learning techniques such as random forests (RF) have been suggested as promising alternatives for variable selection and PS estimation.
Автори: | Ali, M, Khalid, S, Collins, G, Prieto-Alhambra, D |
---|---|
Формат: | Conference item |
Опубліковано: |
Wiley
2017
|
Схожі ресурси
Схожі ресурси
-
Random effects modelling vs logistic regression for the inclusion of surgeon covariates in propensity scores for medical device epidemiology: A simulation study
за авторством: Du, M, та інші
Опубліковано: (2020) -
Random effects modelling versus logistic regression for the inclusion of cluster-level covariates in propensity score estimation: a Monte Carlo simulation and registry cohort analysis
за авторством: Du, MD, та інші
Опубліковано: (2023) -
The “propensity score paradox”: A threat to pharmaco-epidemiological studies?
за авторством: Ali, MS, та інші
Опубліковано: (2017) -
Comparing treatment effects between propensity scores and randomized controlled trials: improving conduct and reporting.
за авторством: Collins, G, та інші
Опубліковано: (2012) -
Machine learning methods as alternatives to regression modelling in propensity score and disease risk score based methods
за авторством: Guo, Y
Опубліковано: (2023)