Modelling Truncated and Clustered Count Data

Saei, Ayoub and Chambers, Ray (2005) Modelling Truncated and Clustered Count Data , Southampton, UK Southampton Statistical Sciences Research Institute 18pp. (S3RI Methodology Working Papers, M05/10).


[img] PDF s3ri-workingpaper-m05-10.pdf - Other
Download (395kB)


Count response data often exhibit departures from the assumptions of standard Poisson generalized linear models (McCullagh & Nelder 1989). In particular, cluster level correlation of the data and truncation at zero are two common characteristics of such data. In this paper we describe a random components truncated Poisson model that can be applied to clustered and zero-truncated count data. Residual maximum likelihood method estimators for the parameters of this model are developed and their use illustrated using a data set of non-zero counts of sheets with edge strain defects in iron sheets produced by the Mobarekeh Steel Complex, Iran. We also report on a small scale simulation study that supports the estimation procedure.

Item Type: Monograph (Working Paper)
Keywords: Cluster, Poisson, Random components, REML, Truncated.
ePrint ID: 14303
Date :
Date Event
10 February 2005Published
Date Deposited: 10 Feb 2005
Last Modified: 16 Apr 2017 23:43
Further Information:Google Scholar

Actions (login required)

View Item View Item