Confidence intervals for the odds ratio of two independent binomial proportions using data with one type of misclassification

We derive a confidence interval for the odd ratio of two independent binomial proportion parameters with one type of misclassification using an easy-to-implement closed- form algorithm based on the Maximum Likelihood Estimator (MLE) and its asymptotic variance. The model identifiability is obtained...

Full description

Saved in:
Bibliographic Details
Published inJournal of statistics & management systems Vol. 19; no. 2; pp. 259 - 268
Main Authors Rahardja, Dewi, Wu, Han, Huang, Shuguang, Chu, Jianxiong
Format Journal Article
LanguageEnglish
Published New Delhi Taylor & Francis 03.03.2016
Taru Publications
Subjects
Asymptotic properties
Binary data
Confidence intervals
False positive misclassification
Identifiability
Maximum likelihood estimators
Odds ratio
Sampled data
SIDS
Sudden infant death syndrome
Online AccessGet full text
ISSN0972-0510
2169-0014
DOI10.1080/09720510.2015.1047572

Cover

More Information
Summary:We derive a confidence interval for the odd ratio of two independent binomial proportion parameters with one type of misclassification using an easy-to-implement closed- form algorithm based on the Maximum Likelihood Estimator (MLE) and its asymptotic variance. The model identifiability is obtained via doubly sampled data. For illustration, we apply our methods to a sudden infant death syndrome (SIDS) dataset.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0972-0510
2169-0014
DOI:10.1080/09720510.2015.1047572