Home
Resource
Higher order conditional inference using parallels with approximate Bayesian techniques
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(761.35 kb)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Zhang, Juan. Higher order conditional inference using parallels with approximate Bayesian techniques. Retrieved from https://doi.org/doi:10.7282/T3Q52PXG

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleHigher order conditional inference using parallels with approximate Bayesian techniques
NameZhang, Juan (author); Kolassa, John (chair); Cohen, Arthur (internal member); Strawderman, William (internal member); Scheetz, Linda (outside member); Rutgers University; Graduate School - New Brunswick
Date Created
Other Date2008-10 (degree)
SubjectStatistics and Biostatistics, Mathematical statistics, Probabilities, Bayesian statistical decision theory
Extentxi, 62 p. : ill.
DescriptionI consider parametric models with a scalar parameter of
interest and multiple nuisance parameters. The likelihood ratio statistic is frequently used in statistical inference. The standard normal approximation to the likelihood ratio statistic generally has error of order O(n-1/2), where "n" denotes the sample size. When "n" is small, the normal approximation may not be adequate to do accurate inference. In practice, the true error is more important than asymptotic order. The intention of this study is to find an approximation which is relatively easy to apply, but which is accurate under small sample size settings. Saddlepoint approximations are well-known for higher order accuracy properties and remarkably good relative error properties. There are several saddlepoint approximations. I look for one that is flexible in
application while keeping a satisfactory convergence rate.
I evaluate, via Monte Carlo, the accuracies of several saddlepoint approximations, and of some classical methods, when these approximations are used to approximate p-values for hypotheses about a scalar parameter. Based on the results, I find that DiCiccio and Martin's (1993) approximations are interesting and deserve more research. Approximations of DiCiccio and Martin (1993) involve exploiting the parallels between Bayesian and frequentist inference, and can be constructed from general log-likelihood functions with relatively easy calculation, while keep the accuracy property.
Two difficulties arise in the application of these approximations. One is the instability around a singularity. The other and far more significant is the construction of the prior density functions utilized in these approximations. These prior density functions are
also called matching priors.
To make DiCiccio and Martin's (1993) approximations applicable in practice, I successfully resolve the above two problems. I remove the instability and fix the numerical difficulties in applying these approximations. The matching prior is the solution to a first order partial differential equation. The solution of this equation is
non-trivial under the general parametrization. I use a procedure to solve the equation numerically given any initial conditions.
As a conclusion, I suggest the use of DiCiccio and Martin's (1993) approximations with the construction procedure and the correction that I provide in this thesis.
NotePh.D.
NoteIncludes bibliographical references (p. 53-55)
Noteby Juan Zhang
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/T3Q52PXG
Languageeng
CollectionGraduate School - New Brunswick Electronic Theses and Dissertations
Organization NameNjNbRU
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024