Kernel Density Estimation Based on Grouped Data: The Case of Poverty Assessment

36 Pages Posted: 12 Sep 2008

See all articles by Camelia Minoiu

Camelia Minoiu

Federal Reserve Bank of Atlanta

Sanjay G. Reddy

The New School - Department of Economics

Multiple version iconThere are 2 versions of this paper

Date Written: July 2008

Abstract

We analyze the performance of kernel density methods applied to grouped data to estimate poverty (as applied in Sala-i-Martin, 2006, QJE). Using Monte Carlo simulations and household surveys, we find that the technique gives rise to biases in poverty estimates, the sign and magnitude of which vary with the bandwidth, the kernel, the number of datapoints, and across poverty lines. Depending on the chosen bandwidth, the $1/day poverty rate in 2000 varies by a factor of 1.8, while the $2/day headcount in 2000 varies by 287 million people. Our findings challenge the validity and robustness of poverty estimates derived through kernel density estimation on grouped data.

Keywords: Poverty, Economic models, Income distribution, Data analysis

Suggested Citation

Minoiu, Camelia and Reddy, Sanjay G., Kernel Density Estimation Based on Grouped Data: The Case of Poverty Assessment (July 2008). IMF Working Paper No. 08/183, Available at SSRN: https://ssrn.com/abstract=1266516

Camelia Minoiu (Contact Author)

Federal Reserve Bank of Atlanta ( email )

1000 Peachtree Street N.E.
Atlanta, GA 30309-4470
United States

Sanjay G. Reddy

The New School - Department of Economics ( email )

Room 1116
6 East 16th Street
New York, NY 10003
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
189
Abstract Views
1,526
Rank
93,273
PlumX Metrics