|
Activity Number:
|
336
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #309640 |
|
Title:
|
Profile Likelihood-Based Confidence Intervals in Repeated Categorical Data
|
|
Author(s):
|
Esa I. Uusipaikka*+
|
|
Companies:
|
University of Turku
|
|
Address:
|
Department of Statistics, Turku, 20014, Finland
|
|
Keywords:
|
Profile likelihood ; Confidence interval ; Repeated measurements ; Categorical data
|
|
Abstract:
|
Profile likelihood-based confidence intervals for components or more generally real-valued functions of parameter vector are approximate confidence intervals based on likelihood ratio statistic and its asymptotic chi square-distribution. The calculation of these intervals is possible if explicit expressions of the log-likelihood and score functions are available. Joint regression and association modeling of repeated categorical responses using dependence ratios provides explicit expressions for log-likelihood and score functions and thus the above mentioned way of constructing confidence intervals is available. The method is illustrated by constructing profile likelihood based confidence intervals for several parameter functions of interest in longitudinal dataset reporting the presence and absence of wheeze at ages 7, 8, 9, and 10 among 537 Steubenville children.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
