This article proposes an approximate conditional dynamic finite mixture hurdle model for panel count data with excess of zeros and endogenous initial conditions. We provide parameter estimates by using the Expectation-Maximization (EM) algorithm in a Nonparametric Maximum Likelihood (NPML) framework. An application to a unique data set on traffic violation counts of a subpopulation of Italian drivers is given.
This article proposes an approximate conditional dynamic finite mixture hurdle model for panel count data with excess of zeros and endogenous initial conditions. We provide parameter estimates by using the Expectation-Maximization (EM) algorithm in a Nonparametric Maximum Likelihood (NPML) framework. An application to a unique data set on traffic violation counts of a subpopulation of Italian drivers is given. © 2013 Taylor & Francis.
A dynamic hurdle model for zero-inflated panel count data / Filippo, Belloc; Bernardi, Mauro; Maruotti, Antonello; Petrella, Lea. - In: APPLIED ECONOMICS LETTERS. - ISSN 1350-4851. - STAMPA. - 20:9(2013), pp. 837-841. [10.1080/13504851.2012.750447]
A dynamic hurdle model for zero-inflated panel count data
BERNARDI, MAURO;MARUOTTI, Antonello;PETRELLA, Lea
2013
Abstract
This article proposes an approximate conditional dynamic finite mixture hurdle model for panel count data with excess of zeros and endogenous initial conditions. We provide parameter estimates by using the Expectation-Maximization (EM) algorithm in a Nonparametric Maximum Likelihood (NPML) framework. An application to a unique data set on traffic violation counts of a subpopulation of Italian drivers is given.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
