Estimation of Transition Probabilities Using Median Absolute Deviations

The probability-constrained minimum absolute deviations (MAD) estimator appears to be superior to the probability-constrained quadratic programming estimator in estimating transition probabilities with limited aggregate time series data Futhermore, one can reduce the number of columns in the probability-constrained MAD simplex tableau by adopting the median property


Issue Date:
1988
Publication Type:
Journal Article
Record Identifier:
http://ageconsearch.umn.edu/record/137484
PURL Identifier:
http://purl.umn.edu/137484
Published in:
Journal of Agricultural Economics Research, Volume 40, Number 4
Total Pages:
8




 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)