Estimating Transition Probabilities from Aggregate Samples Plus Partial Transition Data

Longitudinal studies often collect only aggregate data, which allows only inefficient transition probability estimates. Barring enormous aggregate samples, improving the efficiency of transition probability estimates seems to be impossible without additional partial-transition data. This paper discu...

Full description

Saved in:
Bibliographic Details
Published in:Biometrics 2000-09, Vol.56 (3), p.848-854
Main Authors: Hawkins, D.L, Han, Chien-Pai
Format: Article
Language:English
Subjects:
Acquired Immunodeficiency Syndrome - prevention & control
Biometrics
Biometry - methods
Categorical data
Consistent estimators
Constrained linear model
Covariance
Covariance matrices
Data combination
Estimation methods
Finite-population sampling
Health Knowledge, Attitudes, Practice
HIV Infections - prevention & control
Humans
Inverse sampling
Linear models
Longitudinal Studies
Longitudinal study design
Matrices
Models, Statistical
Multicenter Studies as Topic
Probability
Research Design
Sample Size
Substance Abuse, Intravenous - prevention & control
Transition probabilities
Volunteer
Volunteerism
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Longitudinal studies often collect only aggregate data, which allows only inefficient transition probability estimates. Barring enormous aggregate samples, improving the efficiency of transition probability estimates seems to be impossible without additional partial-transition data. This paper discusses several sampling plans that collect data of both types, as well as a methodology that combines them into efficient estimates of transition probabilities. The method handles both fixed and time-dependent categorical covariates and requires no assumptions (e.g., time homogeneity, Markov) about the population evolution.
ISSN:0006-341X
1541-0420
DOI:10.1111/j.0006-341X.2000.00848.x