Household food expenditures in the United States: A Bayesian MCMC approach to censored equation systems

We apply a Bayesian Markov Chain Monte Carlo (MCMC) technique, along with data augmentation to accommodate censoring in the dependent variables, to the estimation of a large expenditure system of food expenditures. Our finding of significant error covariance estimates justifies estimation of the system in improving statistical efficiency. Income, household composition, regions and other socio-demographic variables are found to play significant roles in determining household food expenditures.


Issue Date:
2010-07
Publication Type:
Conference Paper/ Presentation
Record Identifier:
http://ageconsearch.umn.edu/record/61763
PURL Identifier:
http://purl.umn.edu/61763
Total Pages:
24
JEL Codes:
C11; C34; D12
Series Statement:
Selected Paper
11843




 Record created 2017-04-01, last modified 2018-01-22

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)