Statistical inference in massive datasets by empirical likelihood

Weighted empirical likelihood inference

A weighted empirical likelihood approach is proposed to take account of the heteroscedastic structure of the data. The resulting weighted empirical likelihood ratio statistic is shown to have a limiting chisquare distribution. A limited simulation study shows that the associated con*dence intervals for a population mean or a regression coe+cient have more accurate coverage probabilities and mor...

statistical inference via empirical bayes approach for stationary and dynamic contingency tables

چکیده ندارد.

Schema Inference for Massive JSON Datasets

Cloud computing is a novel and very popular computing paradigm that aims at building extremely scalable and elastic applications working on huge datasets. This paradigm is based on the idea of using hundreds or thousands of low-end, unreliable, and cheap machines connected through standard network switches. The most popular incarnation of this paradigm is the Map/Reduce architecture, first intr...

In All Likelihood - Statistical Modeling and Inference Using Likelihood

Extended Empirical Likelihood Estimation and Inference

We extend the empirical likelihood method of estimation and inference proposed by Owen and others and demonstrate how it may be used in a general linear model context and to mitigate the impact of an ill-conditioned design matrix. A dual loss information theoretic estimating function is used along with extended moment conditions to yield a data based estimator that has the usual consistency and...