logo
Ponte Academic Journal
Nov 2016, Volume 72, Issue 11

Regression analyses performed on the number of cattle owned by breed type using Poisson, Quasi-Poisson and Negative Binomial models

Author(s): Gabotepele Madisa-Maseko ,T. Zewotir, D. North

J. Ponte - Nov 2016 - Volume 72 - Issue 11
doi: 10.21506/j.ponte.2016.11.24



Abstract:
The objective of this paper is to examine the effects of eleven predictor variables on the number of cattle owned by breed type of communal cattle farmers in Botswana. The response variable is the total number of cattle owned by breed type. The standard Poisson regression model was fitted to the data but was found to be inadequate.\\nThe results of the Negative Binomial regression model reveals that gender, marital status, farming status of the holder, economic activities undertaken in the holding, source of income for the holding, use of farm labour in the holding and educational level of the household head are significant factors affecting the number and the types of breeds of cattle owned. Female headed households, holdings with no other economic activities undertaken, holdings with other main source of income and holdings with no farm labour, on average have a smaller number of cross and exotic cattle breeds.
Download full text:
Check if you have access through your login credentials or your institution