Counterfactual Analysis Based on Grouped Data: Application to Poverty and Material Deprivation

15:30-17:00, Friday, April 1, 2022

Tencent Meeting (Meeting ID: 295 281 907)

Dr. Minghai Mao is the assistant professor of the Advanced Institute of Finance and Economics at Liaoning University. He was granted the Ph.D. in Economics with a specialization in Econometrics from Universidad Carlos III de Madrid in 2021. His research focuses on Program Evaluation, Machine Learning, Spatial Econometrics and Labor Economics.

We propose a non-parametric approach to estimate the counterfactual decomposition of distributional statistics based on a data grouping. The estimation of the grouped counterfactual is a two-step procedure: first, we group the data; then, we evaluate a mean (or a regression) in each group and re-weight them for the groups' composition of a reference population. We obtain the decomposition by adding and subtracting the grouped counterfactual to the difference in functional. Our approach allows for a path independent detailed decomposition, highlighting the contributions of each group. We propose using data-driven approaches to form the groups. The estimator built in this way is a good approximation of the true counterfactual and can deal with troublesome settings characterized by numerous non-ordered characteristics and data sparsity. In the last section, we apply the newly proposed methodology to decompose the Great recession effects on poverty indices in Spain.

For more information of the seminar, scan the following QR code(s) to join Tencent QQ group (904 544 292) or WeChat group named "IAER Seminar (3)", please.

QQ Group

WeChat Group (QR code is valid until 3/25/2022)