Pearson-type goodness-of-fit test with bootstrap maximum likelihood estimation

Title Pearson-type goodness-of-fit test with bootstrap maximum likelihood estimation

Pearson-type goodness-of-fit test with bootstrap maximum likelihood estimation.

The Pearson test statistic is constructed by partitioning the data into bins and computing the difference between the observed and expected counts in these bins. If the maximum likelihood estimator (MLE) of the original data is used, the statistic generally does not follow a chi-squared distribution or any explicit distribution. We propose a bootstrap-based modification of the Pearson test stat...

Bootstrap Goodness - of - Fit Test for the Beta - BinomialModel STEVEN

Model STEVEN T. GARREN1, RICHARD L. SMITH2 &WALTERW. PIEGORSCH3, 1Department of Mathemati s and Statisti s, James Madison University, Harrisonburg, Virginia, USA, 2Department of Statisti s, University of North Carolina, Chapel Hill, USA and 3Department of Statisti s, University of South Carolina, Columbia, USA ABSTRACT A ommon question in the analysis of binary data is how to deal with overdisp...

An empirical likelihood goodness-of-fit test for time series

Standard goodness-of-fit tests for a parametric regression model against a series of nonparametric alternatives are based on residuals arising from a fitted model.When a parametric regression model is compared with a nonparametric model, goodness-of-fit testing can be naturally approached by evaluating the likelihood of the parametric model within a nonparametric framework. We employ the empiri...

Effects of parameter estimation on maximum-likelihood bootstrap analysis.

Bipartition support in maximum-likelihood (ML) analysis is most commonly assessed using the nonparametric bootstrap. Although bootstrap replicates should theoretically be analyzed in the same manner as the original data, model selection is almost never conducted for bootstrap replicates, substitution-model parameters are often fixed to their maximum-likelihood estimates (MLEs) for the empirical...