Can I read Analysis Strategies for Serial Multivariate Ultrasonographic Data That Are Incomplete on EtoBox?

Analysis Strategies for Serial Multivariate Ultrasonographic Data That Are Incomplete by Mark A. Espeland; Robert P. Byington; Donald Hire; Vicki G. Davis; Tyler Hartwell; Jeffrey Probstfield is a Mathematics article available to read on EtoBox.

What is Analysis Strategies for Serial Multivariate Ultrasonographic Data That Are Incomplete about?

Ultrasonographic measurement of intima-media thicknesses in the carotid artery has emerged as an important non-invasive means of assessing atherosclerosis, and has served to define primary outcome measures related to progression of arterial lesions in several large clinical trials and epidemiologic studies. It is characteristic that measurements often cannot be obtained from all sites during repeated examinations. This leads to incomplete multivariate serial data, for which the set and number of visualized sites may vary across time. We have contrasted several conditional and unconditional maximum likelihood analytical approaches, and have evaluated these with a simulation experiment based on characteristics of ultrasound measurements collected during the course of the Asymptomatic Carotid Artery Plaque Study. We examined analyses based on unweighted and generalized least squares regression in which we estimated cross-sectional summary statistics using raw means, unconditional maximum likelihood estimates and full maximum likelihood estimates. Since the genesis of missing data is not fully clear, and since the approaches we examined are based, to some degree, on the assumption that

Who reads Analysis Strategies for Serial Multivariate Ultrasonographic Data That Are Incomplete?

Author

Mark A. Espeland; Robert P. Byington; Donald Hire; Vicki G. Davis; Tyler Hartwell; Jeffrey Probstfield

Publisher

John Wiley and Sons; Wiley (John Wiley & Sons); John Wiley & Sons Inc.; Wiley (ISSN 0277-6715)

Published

1992

Language

EN

Field

Mathematics (Physical Sciences)