MARC Record from Library of Congress

LEADER: 02252nam a22002897a 4500
001 2007616545
003 DLC
005 20070922103013.0
007 cr |||||||||||
008 070921s2007 mau sb 000 0 eng
010 $a 2007616545
040 $aDLC$cDLC
050 00 $aHB1
100 1 $aGabaix, Xavier.
245 10 $aRank-1/2$h[electronic resource] :$ba simple way to improve the ols estimation of tail exponents /$cXavier Gabaix, Rustam Ibragimov.
260 $aCambridge, MA :$bNational Bureau of Economic Research,$cc2007.
490 1 $aNBER working paper series ;$vworking paper . 342
538 $aSystem requirements: Adobe Acrobat Reader.
538 $aMode of access: World Wide Web.
500 $aTitle from PDF file as viewed on 9/21/2007.
530 $aAlso available in print.
504 $aIncludes bibliographical references.
520 3 $a"Despite the availability of more sophisticated methods, a popular way to estimate a Pareto exponent is still to run an OLS regression: log(Rank)=a-b log(Size), and take b as an estimate of the Pareto exponent. The reason for this popularity is arguably the simplicity and robustness of this method. Unfortunately, this procedure is strongly biased in small samples. We provide a simple practical remedy for this bias, and propose that, if one wants to use an OLS regression, one should use the Rank-1/2, and run log(Rank-1/2)=a-b log(Size). The shift of 1/2 is optimal, and reduces the bias to a leading order. The standard error on the Pareto exponent zeta is not the OLS standard error, but is asymptotically (2/n)^(1/2) zeta. Numerical results demonstrate the advantage of the proposed approach over the standard OLS estimation procedures and indicate that it performs well under dependent heavy-tailed processes exhibiting deviations from power laws. The estimation procedures considered are illustrated using an empirical application to Zipf's law for the U.S. city size distribution"--National Bureau of Economic Research web site.
700 1 $aIbragimov, Rustam.
710 2 $aNational Bureau of Economic Research.
830 0 $aWorking paper series (National Bureau of Economic Research : Online) ;$vworking paper no. . 342.
856 40 $uhttp://papers.nber.org/papers/t0342