Ciência-IUL
Publications
Publication Detailed Description
Power of edge exclusion tests in graphical Gaussian models
Journal Title
Biometrika
Year (definitive publication)
2005
Language
English
Country
United Kingdom
More Information
Web of Science®
Scopus
Google Scholar
This publication is not indexed in Google Scholar
Abstract
Asymptotic multivariate normal approximations to the joint distributions of edge exclusion test statistics for saturated graphical Gaussian models are derived. Non-signed and signed square-root versions of the likelihood ratio, Wald and score test statistics are considered. Noncentral chi-squared approximations are also considered for the non-signed versions. These approximations are used to estimate the power of edge exclusion tests and an example is presented.
Acknowledgements
--
Keywords
Likelihood ratio test,Overall power,Partial correlation,Score test,Signed square-root test,Wald test
Fields of Science and Technology Classification
- Mathematics - Natural Sciences
- Biological Sciences - Natural Sciences