Panel treatment effects measurement: Factor or linear projection modelling?
Document Type
Article
Publication Date
11-1-2024
Abstract
We discuss methods of measuring the treatment effects of a unit through the use of other units in panel data by either the factor-based (FB) approach or the linear projection (LP) approach under different sample configurations of cross-sectional dimension (Formula presented.) and time series dimension (Formula presented.). We show that the LP approach in general yields smaller mean square prediction error than the FB approach when either both (Formula presented.) and (Formula presented.) are large or (Formula presented.) fixed and (Formula presented.) or (Formula presented.) fixed and (Formula presented.) large. The Monte Carlo simulation and empirical example are also conducted to consider their finite sample performances.
Publication Source (Journal or Book title)
Journal of Applied Econometrics
First Page
1332
Last Page
1358
Recommended Citation
Hsiao, C., & Zhou, Q. (2024). Panel treatment effects measurement: Factor or linear projection modelling?. Journal of Applied Econometrics, 39 (7), 1332-1358. https://doi.org/10.1002/jae.3081