In this video, I show the process of estimating propensity score weights for propensity score analysis (inverse probability of treatment weights).
The success of propensity score weights to remove selection bias due to observed covariates can be measured by evaluate covariate balance. In the video below, I show how to examine covariate balance using propensity score weights.
If a satisfactory covariate balance was achieved using the propensity score weights, the next step is to estimate the treatment effect. In this video I show how to estimate the average treatment effect using inverse probability of treatment weighting.
Doubly-robust estimation is a method to obtain unbiased treatment effect estimates if either the propensity score model or the outcome model is misspecified, but not both. In this video I show an example of doubly-robust treatment effect estimation using inverse probability of treatment weighting.
R Code for Chapter 3 - Propensity Score Weighting:
R code for Chapter 3 Part 1 - Calculating Propensity Score Weights | |
File Size: | 3 kb |
File Type: | r |
R code for Chapter 3 Part 2 - Calculating Propensity Score Weights from GBM and Random Forests | |
File Size: | 2 kb |
File Type: | r |
chapter3_part3_dealing_with_extreme_propensity_score_weights.r | |
File Size: | 2 kb |
File Type: | r |
chapter3_part4_evaluating_covariate_balance.r | |
File Size: | 2 kb |
File Type: | r |
chapter3_part5_custom_function_to_evaluate_covariate_balance.r | |
File Size: | 4 kb |
File Type: | r |
chapter3_part6_estimation_of_treatment_effect_with_propensity_score_weights.r | |
File Size: | 2 kb |
File Type: | r |
chapter3_part7_estimation_of_treatment_effect_with_multiple_imputed_datasets.r | |
File Size: | 1 kb |
File Type: | r |
chapter3_part8_doubly_robust_estimation_with_propensity_score_weights.r | |
File Size: | 2 kb |
File Type: | r |
Data Files for Example in Chapter 3:
chapter3_els_data_imputed_example_career_academy.rdata | |
File Size: | 3044 kb |
File Type: | rdata |
chapter3_els_data_imputed_with_weights.rdata | |
File Size: | 1584 kb |
File Type: | rdata |
chapter3_els_all_imputed_datasets_with_weights.rdata | |
File Size: | 2807 kb |
File Type: | rdata |
Related Research:
Bishop, C. D., Leite, W. L., Snyder, P. (2018). Using Propensity Score Weighting to Reduce Selection Bias in Large-Scale Data Sets. Journal of Early Intervention, 40(4), 347-362.
Leite, W. L., Aydin, B. & Gurel, S. (in press) A Comparison of Propensity Score Weighting Methods for Evaluating the Effects of Programs with Multiple Versions. The Journal of Experimental Education, DOI: 10.1080/00220973.2017.1409179
Bishop, C. D., Leite, W. L., Snyder, P. (2018). Using Propensity Score Weighting to Reduce Selection Bias in Large-Scale Data Sets. Journal of Early Intervention, 40(4), 347-362.
Leite, W. L., Aydin, B. & Gurel, S. (in press) A Comparison of Propensity Score Weighting Methods for Evaluating the Effects of Programs with Multiple Versions. The Journal of Experimental Education, DOI: 10.1080/00220973.2017.1409179
Proudly powered by Weebly