Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier



Open Access Dissertation

Document Type


Degree Name

Doctor of Philosophy (PhD)

Degree Program

Public Health

Year Degree Awarded


Month Degree Awarded


First Advisor

Edward J. Stanek III

Subject Categories

Biostatistics | Nutrition | Public Health


The accurate estimation of an individual’s usual dietary intake is important since the estimates are essential to uncover the diet-disease relationships. This study explores a more accurate method to estimate an individual’s latent value of usual dietary intake when it is repeatedly measured using a 24-hour dietary recall (24HR) and seven day dietary recall (7DDR), accounting for random measurement error and bias. The performance of the (empirical) predictor of subject’s latent value obtained under the finite population mixed model (FPMM) framework is compared with those obtained under the usual mixed model and the measurement error model through a simulation study. The performance of (empirical) predictors based on the 24HR and 7DDR combined data are compared with those based on the 24HR data. We analyze the predictor of latent value in two cases – for a randomly selected subject and for a specific subject. The simulation results reveal the (empirical) predictor based on a FPMM is optimal for a randomly selected subject, but not uniformly optimal for a specific subject. For a randomly selected subject, the predictor from the combined data is better. For a specific subject, the (empirical) predictor from the combined data is better except for those subjects with relatively larger bias in 7DDR measures. This study provided guidance for predicting subject’s latent value of usual saturated fat intake using two source data; examined the performance of predictors conditional on sampled subject; and showed that WLS estimator is a biased estimator of the average latent value of the population when within-subject variances vary.