Activity Number:
|
342
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
|
Sponsor:
|
JASA, Applications and Case Studies
|
Abstract - #300319 |
Title:
|
Latent Class Analysis of Complex Sample Survey Data: Application to Dietary Data
|
Author(s):
|
Blossom Patterson*+ and C. Dayton and Barry Graubard
|
Affiliation(s):
|
National Cancer Institute and University of Maryland and National Cancer Institute
|
Address:
|
EPN 3131 9000 Rockville Pike, Bethesda, Maryland, 20892-7354, U.S.A.
|
Keywords:
|
jackknife ; clustering ; design effect ; complex sample surveys ; sample weights ; informative sampling
|
Abstract:
|
High fruit and vegetable intake is associated with decreased cancer risk. However, national survey dietary recall data suggest that, on any given day, vegetable intake falls below the recommended three daily servings. There is no single widely accepted measure of "usual intake." Intake can be regarded as a mixture of "regular" (relatively frequent) and "non-regular"(relatively infrequent) consumers, using an indicator of whether an individual consumed the food of interest on the recall day. We estimate "usual" intake of vegetables using latent class analysis (LCA). The data consist of four 24-hour dietary recalls from the 1985 Continuing Survey of Intakes by Individuals collected from 1,028 women. Traditional LCA based on simple random sampling was extended to complex survey data by introducing sample weights into the latent class estimation algorithm and by accounting for the complex sample design through the use of jackknife standard errors. A two-class model showed that 18% do not regularly consume vegetables, compared to an unweighted estimate of 33%. Simulations showed that ignoring sample weights resulted in biased parameter estimates and that jackknife variances provided satisfactory confidence interval coverage. The methods proposed in this paper are readily implemented for the analysis of complex sample survey data.
|