An algorithm for constructing high dimensional distributions from distributions of lower dimension

C-Tier
Journal: Economics Letters
Year: 2014
Volume: 123
Issue: 3
Pages: 257-261

Score contribution per author:

0.335 = (α=2.01 / 3 authors) × 0.5x C-tier

α: calibrated so average coauthorship-adjusted count equals average raw count

Abstract

We propose a new sequential procedure for estimating multivariate distributions in cases when conventional maximum likelihood has too many parameters and is therefore inaccurate or non-operational. The procedure constructs a multivariate distribution and its pseudo-likelihood sequentially, in each step using lower-dimensional distributions with a small number of parameters. In an application, the procedure provides excellent fit when the dimension is moderate, and remains operational when the conventional method fails.

Technical Details

RePEc Handle
repec:eee:ecolet:v:123:y:2014:i:3:p:257-261
Journal Field
General
Author Count
3
Added to Database
2026-01-24