01784cas a2200253 a 4500 AALejournalIMF005239 230101c9999 xx r poo 0 0eng d 5.00 USD 9781451870411 1018-5941 BD-DhAAL BD-DhAAL Minoiu, Camelia. Kernel Density Estimation Based on Grouped Data : The Case of Poverty Assessment / Camelia Minoiu, Sanjay Reddy. Washington, D.C. : International Monetary Fund, 2008. 1 online resource (34 pages) IMF Working Papers <strong>Off-Campus Access:</strong> No User ID or Password Required <strong>On-Campus Access:</strong> No User ID or Password Required Electronic access restricted to authorized BRAC University faculty, staff and students 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 USD 1/day poverty rate in 2000 varies by a factor of 1.8, while the USD 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. Mode of access: Internet Reddy, Sanjay. IMF Working Papers; Working Paper ; No. 2008/183 Full text available on IMF http://elibrary.imf.org/view/journals/001/2008/183/001.2008.issue-183-en.xml IMF e-Library