On the identification of random variables from quantized observations
Probability
2016-12-07 v2
Abstract
We prove that the scale and shift parameters of a family of probability laws can be identified from quantized values, under appropriate assumptions. As an application, we show the consistency of the maximum likelihood estimator for the parameters of a quantized Gaussian autoregressive process.
Keywords
Cite
@article{arxiv.1608.04697,
title = {On the identification of random variables from quantized observations},
author = {Miklos Rasonyi},
journal= {arXiv preprint arXiv:1608.04697},
year = {2016}
}
Comments
Results substantially more general, proof of Lemma 2.4 radically simplified thanks to an anonymous referee