Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size

In adaptive optimal procedures, the design at each stage is an estimate of the optimal design based on all previous data. Asymptotics for regular models with fixed number of stages are straightforward if one assumes the sample size of each stage goes to infinity with the overall sample size. However...

Full description

Saved in:
Bibliographic Details
Main Authors: Adam Lane, Nancy Flournoy
Format: Article
Language:English
Published: Wiley 2012-01-01
Series:Journal of Probability and Statistics
Online Access:http://dx.doi.org/10.1155/2012/436239
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832555814578028544
author Adam Lane
Nancy Flournoy
author_facet Adam Lane
Nancy Flournoy
author_sort Adam Lane
collection DOAJ
description In adaptive optimal procedures, the design at each stage is an estimate of the optimal design based on all previous data. Asymptotics for regular models with fixed number of stages are straightforward if one assumes the sample size of each stage goes to infinity with the overall sample size. However, it is not uncommon for a small pilot study of fixed size to be followed by a much larger experiment. We study the large sample behavior of such studies. For simplicity, we assume a nonlinear regression model with normal errors. We show that the distribution of the maximum likelihood estimates converges to a scale mixture family of normal random variables. Then, for a one parameter exponential mean function we derive the asymptotic distribution of the maximum likelihood estimate explicitly and present a simulation to compare the characteristics of this asymptotic distribution with some commonly used alternatives.
format Article
id doaj-art-d2df0e2c10cd4870819bc4abc255b778
institution Kabale University
issn 1687-952X
1687-9538
language English
publishDate 2012-01-01
publisher Wiley
record_format Article
series Journal of Probability and Statistics
spelling doaj-art-d2df0e2c10cd4870819bc4abc255b7782025-02-03T05:47:15ZengWileyJournal of Probability and Statistics1687-952X1687-95382012-01-01201210.1155/2012/436239436239Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample SizeAdam Lane0Nancy Flournoy1Department of Statistics, University of Missouri, 146 Middlebush Hall, Columbia, MO 65203, USADepartment of Statistics, University of Missouri, 146 Middlebush Hall, Columbia, MO 65203, USAIn adaptive optimal procedures, the design at each stage is an estimate of the optimal design based on all previous data. Asymptotics for regular models with fixed number of stages are straightforward if one assumes the sample size of each stage goes to infinity with the overall sample size. However, it is not uncommon for a small pilot study of fixed size to be followed by a much larger experiment. We study the large sample behavior of such studies. For simplicity, we assume a nonlinear regression model with normal errors. We show that the distribution of the maximum likelihood estimates converges to a scale mixture family of normal random variables. Then, for a one parameter exponential mean function we derive the asymptotic distribution of the maximum likelihood estimate explicitly and present a simulation to compare the characteristics of this asymptotic distribution with some commonly used alternatives.http://dx.doi.org/10.1155/2012/436239
spellingShingle Adam Lane
Nancy Flournoy
Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size
Journal of Probability and Statistics
title Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size
title_full Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size
title_fullStr Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size
title_full_unstemmed Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size
title_short Two-Stage Adaptive Optimal Design with Fixed First-Stage Sample Size
title_sort two stage adaptive optimal design with fixed first stage sample size
url http://dx.doi.org/10.1155/2012/436239
work_keys_str_mv AT adamlane twostageadaptiveoptimaldesignwithfixedfirststagesamplesize
AT nancyflournoy twostageadaptiveoptimaldesignwithfixedfirststagesamplesize