Maximum Entropy Estimation for Survey sampling
Methodology
2009-09-23 v1 Statistics Theory
Statistics Theory
Abstract
Calibration methods have been widely studied in survey sampling over the last decades. Viewing calibration as an inverse problem, we extend the calibration technique by using a maximum entropy method. Finding the optimal weights is achieved by considering random weights and looking for a discrete distribution which maximizes an entropy under the calibration constraint. This method points a new frame for the computation of such estimates and the investigation of its statistical properties.
Cite
@article{arxiv.0909.4046,
title = {Maximum Entropy Estimation for Survey sampling},
author = {Fabrice Gamboa and Jean-Michel Loubes and Paul Rochet},
journal= {arXiv preprint arXiv:0909.4046},
year = {2009}
}
Comments
25 pages