LEADER 03749nam 2200661 450 001 9910463629603321 005 20181012003634.0 010 $a1-4623-9111-7 010 $a1-4527-8641-0 010 $a1-4518-7041-8 010 $a1-282-84134-3 010 $a9786612841347 035 $a(CKB)3170000000055083 035 $a(EBL)1607966 035 $a(SSID)ssj0000944161 035 $a(PQKBManifestationID)11503328 035 $a(PQKBTitleCode)TC0000944161 035 $a(PQKBWorkID)10983260 035 $a(PQKB)10048888 035 $a(OCoLC)761981611 035 $a(MiAaPQ)EBC1607966 035 $a(EXLCZ)993170000000055083 100 $a20140227h20082008 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aKernel density estimation based on grouped data $ethe case of poverty assessment /$fCamelia Minoiu and Sanjay G. Reddy 210 1$a[Washington, District of Columbia] :$cInternational Monetary Fund,$d2008. 210 4$dİ2008 215 $a1 online resource (36 p.) 225 0 $aIMF working paper ;$vWP/08/183 225 0$aIMF working paper ;$vWP/08/183 300 $aDescription based upon print version of record. 311 $a1-4519-1494-6 320 $aIncludes bibliographical references. 327 $aContents; I. Motivation; II. The Data Structure and the Bias of the Estimator; III. The Bandwidth and Kernels Considered; IV. Monte Carlo Study; A. Theoretical Distributions; B. Summary Statistics, Density Estimates and Diagrams; C. Poverty Estimates; V. Country Studies; VI. Global Poverty; VII. Conclusions; References; Appendix; Appendix Figures; 1. Distributions used in Monte Carlo analysis; 2. Bias of KDE-based density (log-normal distribution); Appendix Tables; 1. Summary statistics from KDE-based sample; 3. Bias of estimated density (multimodal distribution) 327 $a4. Bias of estimated density (Dagum distribution)2. Bias of poverty measures (Low and High Poverty Lines); 5. Bias in the poverty headcount ratio versus location of poverty line; 3. Bias of poverty measures (Triweight kernel, Poverty line: 0.25 x median); 4. Bias of poverty measures (Hybrid bandwidth, Poverty line: 0.5 x median); 5. Bias of poverty measures (Epanechnikov kernel, Silverman bandwidth); 6. Bias of poverty measures (Gaussian kernel, Poverty line: Capability); 6. Survey-based and grouped data KDE-based density estimates; 7. Global poverty rates (% poor) 327 $a8. Global poverty counts (millions) 330 $aWe 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 pove 606 $aPoverty$xMeasurement 606 $aIncome distribution$xEconometric models 606 $aKernel functions 608 $aElectronic books. 615 0$aPoverty$xMeasurement. 615 0$aIncome distribution$xEconometric models. 615 0$aKernel functions. 676 $a339.46 700 $aMinoiu$b Camelia$0874355 701 $aReddy$b Sanjay G$0602369 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910463629603321 996 $aKernel density estimation based on grouped data$91952256 997 $aUNINA