Document Detail

Likelihood methods for binary responses of present components in a cluster.
MedLine Citation:
PMID:  20825395     Owner:  NLM     Status:  MEDLINE    
In some biomedical studies involving clustered binary responses (say, disease status), the cluster sizes can vary because some components of the cluster can be absent. When both the presence of a cluster component as well as the binary disease status of a present component are treated as responses of interest, we propose a novel two-stage random effects logistic regression framework. For the ease of interpretation of regression effects, both the marginal probability of presence/absence of a component as well as the conditional probability of disease status of a present component, preserve the approximate logistic regression forms. We present a maximum likelihood method of estimation implementable using standard statistical software. We compare our models and the physical interpretation of regression effects with competing methods from literature. We also present a simulation study to assess the robustness of our procedure to wrong specification of the random effects distribution and to compare finite-sample performances of estimates with existing methods. The methodology is illustrated via analyzing a study of the periodontal health status in a diabetic Gullah population.
Xiaoyun Li; Dipankar Bandyopadhyay; Stuart Lipsitz; Debajyoti Sinha
Related Documents :
17626225 - A penalized latent class model for ordinal data.
16855855 - Hierarchical clustering analysis of flexible gbr 12909 dialkyl piperazine and piperidin...
18531985 - Influences of manner and voicing on articulatory coordination in german and french init...
20817785 - Mapping health data: improved privacy protection with donut method geomasking.
10323185 - Methods to estimate genetic components of variance for quantitative traits in family st...
21538885 - A posteriori quality control for the curation and reuse of public proteomics data.
Publication Detail:
Type:  Journal Article; Research Support, N.I.H., Extramural     Date:  2010-09-03
Journal Detail:
Title:  Biometrics     Volume:  67     ISSN:  1541-0420     ISO Abbreviation:  Biometrics     Publication Date:  2011 Jun 
Date Detail:
Created Date:  2011-06-21     Completed Date:  2011-11-09     Revised Date:  2014-09-24    
Medline Journal Info:
Nlm Unique ID:  0370625     Medline TA:  Biometrics     Country:  United States    
Other Details:
Languages:  eng     Pagination:  629-35     Citation Subset:  IM    
Copyright Information:
© 2010, The International Biometric Society.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Biometry / methods*
Cluster Analysis
Computer Simulation
Diabetes Complications
Likelihood Functions
Logistic Models
Models, Statistical*
Periodontal Diseases / epidemiology
Grant Support
1R01LM009153/LM/NLM NIH HHS; P20 RR017696/RR/NCRR NIH HHS; P20 RR017696-06/RR/NCRR NIH HHS; P20RR017696-06/RR/NCRR NIH HHS; R01 CA069222/CA/NCI NIH HHS; R01 CA069222-11/CA/NCI NIH HHS; R01 CA069222-12/CA/NCI NIH HHS; R01 CA074015/CA/NCI NIH HHS; R01 CA074015-12/CA/NCI NIH HHS; R01 MH054693/MH/NIMH NIH HHS; R01 MH054693-12/MH/NIMH NIH HHS; R01A160373//PHS HHS; R01CA69222/CA/NCI NIH HHS; U10 DA013727/DA/NIDA NIH HHS; U10 DA013727-09/DA/NIDA NIH HHS; U10DA013727-09/DA/NIDA NIH HHS

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  A spatial dirichlet process mixture model for clustering population genetics data.
Next Document:  Bladder preservation multimodality therapy as an alternative to radical cystectomy for treatment of ...