G
Gauri Sankar Datta
Researcher at University of Georgia
Publications - 83
Citations - 2134
Gauri Sankar Datta is an academic researcher from University of Georgia. The author has contributed to research in topics: Prior probability & Small area estimation. The author has an hindex of 25, co-authored 82 publications receiving 1938 citations. Previous affiliations of Gauri Sankar Datta include University of Florida & United States Census Bureau.
Papers
More filters
Book
Probability Matching Priors: Higher Order Asymptotics
TL;DR: In this paper, the shrinkage argument was used to match the prior for distribution functions and for prediction in the case of posterior density regions, and for other credible regions for prediction.
Journal ArticleDOI
On measuring the variability of small area estimators under a basic area level model
TL;DR: In this paper, the Fay-Herriot method was used to estimate the model variance based on weighted residual sum of squares, which is unbiased to second-order mean squared error.
Journal ArticleDOI
Some remarks on noninformative priors
Gauri Sankar Datta,Malay Ghosh +1 more
TL;DR: In this article, a comparison between the reference priors of Berger and Bernardo and the reverse-reference priors suggested by J. K. Ghosh is made, and sufficient conditions are given that provide agreement between the two classes of priors.
Journal ArticleDOI
On the invariance of noninformative priors
Gauri Sankar Datta,Malay Ghosh +1 more
TL;DR: In this paper, the invariance of non-informative priors, including the reference prior of Berger and Bernardo, the reverse reference prior, and the probability-matching prior of Peers and Stein under reparameterization was explored.
Journal ArticleDOI
Bayesian Prediction in Linear Models: Applications to Small Area Estimation
Gauri Sankar Datta,Malay Ghosh +1 more
TL;DR: In this article, a hierarchical Bayes (HB) approach is proposed for prediction in general mixed linear models. But the results find application only in small area estimation, where the model unifies and extends a number of existing models.