Asymptotic normality and valid inference for Gaussian variational approximation
Statistics Theory
2012-02-24 v1 Statistics Theory
Abstract
We derive the precise asymptotic distributional behavior of Gaussian variational approximate estimators of the parameters in a single-predictor Poisson mixed model. These results are the deepest yet obtained concerning the statistical properties of a variational approximation method. Moreover, they give rise to asymptotically valid statistical inference. A simulation study demonstrates that Gaussian variational approximate confidence intervals possess good to excellent coverage properties, and have a similar precision to their exact likelihood counterparts.
Cite
@article{arxiv.1202.5183,
title = {Asymptotic normality and valid inference for Gaussian variational approximation},
author = {Peter Hall and Tung Pham and M. P. Wand and S. S. J. Wang},
journal= {arXiv preprint arXiv:1202.5183},
year = {2012}
}
Comments
Published in at http://dx.doi.org/10.1214/11-AOS908 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)