A Panel Data Approach for Program Evaluation — Measuring the Benefits of Political and Economic Integration of Hong Kong with Mainland China
Cheng Hsiao, H. Steve Ching, Shui Ki Wan
Journal of Applied Econometrics
#002139 20131014 (published)
We propose a simple to implement panel data method to evaluate the impacts of social policy. The basic idea is to exploit the dependence among cross-sectional units to construct the counterfactuals. The cross-sectional correlations are attributed to the presence of some (unobserved) common factors. However, instead of trying to estimate the unobserved factors, we propose to use observed data. We use a panel of 24 countries to evaluate the impact of political and economic integration of Hong Kong (HK) with Mainland China. We find that the political integration hardly had any impact on the growth of the Hong Kong economy. However, the economic integration has raised HK’s annual real GDP by about 4%.
Keywords: panel data, factor model, cross-sectional dependence, program evaluation, ARMA models.

Download full text