All Rights Reserved
AccessEcon LLC 2006, 2008.
Powered by MinhViet JSC

 
David E Giles
 
''Hermite regression analysis of multi-modal count data''
( 2010, Vol. 30 No.4 )
 
 
We discuss the modeling of count data whose empirical distribution is both multi-modal and over-dispersed, and propose the Hermite distribution with covariates introduced through the conditional mean. The model is readily estimated by maximum likelihood, and nests the Poisson model as a special case. The Hermite regression model is applied to data for the number of banking and currency crises in IMF-member countries, and is found to out-perform the Poisson and negative binomial models.
 
 
Keywords: Count data, multi-modal data, over-dispersion, financial crises
JEL: C4 - Econometric and Statistical Methods: Special Topics
C2 - Single Equation Models; Single Variables: General
 
Manuscript Received : Aug 19 2010 Manuscript Accepted : Nov 09 2010

  This abstract has been downloaded 1801 times                The Full PDF of this paper has been downloaded 166215 times