|
Activity Number:
|
515
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 2, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #308507 |
|
Title:
|
Birth Weight Distribution: Thinking Outside the Curve
|
|
Author(s):
|
Richard Charnigo*+ and Lorie W. Chesnut and Tony LoBianco
|
|
Companies:
|
University of Kentucky and The University of Alabama at Birmingham and University of Kentucky
|
|
Address:
|
851 Patterson Tower, Lexington, KY, 40506-0027,
|
|
Keywords:
|
|
|
Abstract:
|
Many challenging questions about birth weight, gestational age, and mortality have arisen in recent perinatal research. To address them requires a realistic characterization of a population's birth weight distribution. We propose using a normal mixture model in which the number of components is estimated from the data and can vary across populations. In our analysis of data from several populations, typically a four-component model was preferred; the first component mean fell in the extremely low birth weight range, while the other three component means fell in the normal range. This pattern and notable exceptions to it motivate further research to describe the mixture components in terms of observable covariates and to assess how birth weight-specific mortality varies between and within components.
|
