Income vulnerability of rural households in Bangladesh

a comparison between Bayesian and classical methods

authored by

Md Ershadul Islam, Ulrike Grote, Md Israt Rayhan

Abstract

The geographical location and the monsoon climate render Bangladesh highly vulnerable to natural hazards, deteriorating the country's socio-economic stability. This study is based on 500 randomly chosen rural households from the Household Income and Expenditure Survey [Bangladesh Bureau of Statistics, Planning Division, Ministry of Planning, Government of the People's Republic of Bangladesh, Dhaka, 2006]. The objectives are to estimate the income vulnerability of rural households and to check whether the Bayesian approaches (natural conjugate prior and non-informative prior estimates) have any superiority over the classical (feasible generalized least square (FGLS)) method. The poverty level, measured from the data, is 24%; whereas the vulnerability estimates, using FGLS, natural conjugate prior and non-informative prior are 31%, 69% and 82%, respectively. Vulnerability estimates by the Bayesian natural conjugate prior approach is found to have greater efficiency compared with FGLS and non-informative prior approaches.

Organisation(s)

Institute of Environmental Economics and World Trade

External Organisation(s)

University of Dhaka

Type

Article

Journal

Journal of Statistical Computation and Simulation

Volume

83

Pages

1179-1187

No. of pages

9

ISSN

0094-9655

Publication date

2013

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Statistics and Probability, Modelling and Simulation, Statistics, Probability and Uncertainty, Applied Mathematics

Sustainable Development Goals

SDG 13 - Climate Action

Electronic version(s)

https://doi.org/10.1080/00949655.2012.656310 (Access: Closed)