A Censored Maximum Likelihood Approach to Quantifying Manipulation in China’s Air Pollution Data

Dalia Ghanem, Shu Shen and Junjie Zhang

Journal of the Association of Environmental and Resource Economists, 2020, vol. 7, issue 5, 965 - 1003

Abstract: Data manipulation around cutoff points is observed in economics broadly and in environmental and resource economics in particular. This paper develops a simple and tractable censored maximum likelihood approach to quantify the degree of manipulation in China’s air pollution data around the “blue-sky day” cutoff. We construct annual measures of manipulation for 111 Chinese cities. For Beijing, we estimate 4%–16.8% of manipulation among reported blue-sky days annually, which translate to an estimated total of 208.1 manipulated blue-sky days between 2001 and 2010. For the remaining cities reporting pollution data over the 10-year period, we estimate a 93.9 average for the total number of manipulated blue-sky days with a 395.9 maximum. Using LASSO shrinkage, we examine the relationship between manipulation and local official characteristics, and find a positive correlation between manipulation and having an elite-educated party secretary, robust to numerous checks. Further empirical analysis suggests that promotion considerations may help explain this finding.

Date: 2020
References: Add references at CitEc
Citations: View citations in EconPapers (12)

Downloads: (external link)
http://dx.doi.org/10.1086/709649 (application/pdf)
http://dx.doi.org/10.1086/709649 (text/html)
Access to the online full text or PDF requires a subscription.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ucp:jaerec:doi:10.1086/709649

Access Statistics for this article

More articles in Journal of the Association of Environmental and Resource Economists from University of Chicago Press
Bibliographic data for series maintained by Journals Division ().