M. M. Zenga (2010a) has recently proposed a new three-parameter family of density functions for non negative variables. The new family resembles common properties of economic size distributions: it has positive asymmetry, Paretian right tail and it may be zeromodal, unimodal and even bimodal. In this paper we explore some methods for fitting the new density to empirical income distributions from Italy, Swiss, US and UK. We will see that D’Addario’s invariants method clearly outperforms Pearson’s moments method, which does not seem to work well with heavy tailed distributions. Further, we propose some new method based on the minimization of measures for the goodness of fit subject to restrictions in order to ensure equality between some sample characteristics and model counterparts. The results show that the new density provides a good fit to the empirical income distributions we considered.
Zenga, M., Pasquazzi, L., Zenga, M. (2012). First applications of a new three-parameter distribution for non-negative variables. STATISTICA & APPLICAZIONI, 10(2), 131-147.
First applications of a new three-parameter distribution for non-negative variables
ZENGA, MICHELE;PASQUAZZI, LEO;ZENGA, MARIANGELA
2012
Abstract
M. M. Zenga (2010a) has recently proposed a new three-parameter family of density functions for non negative variables. The new family resembles common properties of economic size distributions: it has positive asymmetry, Paretian right tail and it may be zeromodal, unimodal and even bimodal. In this paper we explore some methods for fitting the new density to empirical income distributions from Italy, Swiss, US and UK. We will see that D’Addario’s invariants method clearly outperforms Pearson’s moments method, which does not seem to work well with heavy tailed distributions. Further, we propose some new method based on the minimization of measures for the goodness of fit subject to restrictions in order to ensure equality between some sample characteristics and model counterparts. The results show that the new density provides a good fit to the empirical income distributions we considered.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.