skip to main content

DOE PAGESDOE PAGES

Title: Multiple indicators, multiple causes measurement error models

Multiple indicators, multiple causes (MIMIC) models are often employed by researchers studying the effects of an unobservable latent variable on a set of outcomes, when causes of the latent variable are observed. There are times, however, when the causes of the latent variable are not observed because measurements of the causal variable are contaminated by measurement error. The objectives of this study are as follows: (i) to develop a novel model by extending the classical linear MIMIC model to allow both Berkson and classical measurement errors, defining the MIMIC measurement error (MIMIC ME) model; (ii) to develop likelihood-based estimation methods for the MIMIC ME model; and (iii) to apply the newly defined MIMIC ME model to atomic bomb survivor data to study the impact of dyslipidemia and radiation dose on the physical manifestations of dyslipidemia. Finally, as a by-product of our work, we also obtain a data-driven estimate of the variance of the classical measurement error associated with an estimate of the amount of radiation dose received by atomic bomb survivors at the time of their exposure.
Authors:
 [1] ;  [2] ;  [3] ;  [4]
  1. Texas A&M Univ., College Station, TX (United States). Dept. of Epidemiology and Biostatistics
  2. Univ. at Buffalo, NY (United States). Dept. of Biostatistics
  3. Radiation Effects Research Foundation, Hiroshima (Japan). Dept. of Statistics
  4. Texas A&M Univ., College Station, TX (United States). Dept. of Statistics
Publication Date:
Grant/Contract Number:
HS0000031; R27- CA057030
Type:
Accepted Manuscript
Journal Name:
Statistics in Medicine
Additional Journal Information:
Journal Volume: 33; Journal Issue: 25; Journal ID: ISSN 0277-6715
Publisher:
Wiley
Research Org:
Texas A&M Univ., College Station, TX (United States)
Sponsoring Org:
USDOE; National Cancer Inst.
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; atomic bomb survivor data; Berkson error; dyslipidemia; instrumental variables; latent variables; measurement error; MIMIC models
OSTI Identifier:
1343107

Tekwe, Carmen D., Carter, Randy L., Cullings, Harry M., and Carroll, Raymond J.. Multiple indicators, multiple causes measurement error models. United States: N. p., Web. doi:10.1002/sim.6243.
Tekwe, Carmen D., Carter, Randy L., Cullings, Harry M., & Carroll, Raymond J.. Multiple indicators, multiple causes measurement error models. United States. doi:10.1002/sim.6243.
Tekwe, Carmen D., Carter, Randy L., Cullings, Harry M., and Carroll, Raymond J.. 2014. "Multiple indicators, multiple causes measurement error models". United States. doi:10.1002/sim.6243. https://www.osti.gov/servlets/purl/1343107.
@article{osti_1343107,
title = {Multiple indicators, multiple causes measurement error models},
author = {Tekwe, Carmen D. and Carter, Randy L. and Cullings, Harry M. and Carroll, Raymond J.},
abstractNote = {Multiple indicators, multiple causes (MIMIC) models are often employed by researchers studying the effects of an unobservable latent variable on a set of outcomes, when causes of the latent variable are observed. There are times, however, when the causes of the latent variable are not observed because measurements of the causal variable are contaminated by measurement error. The objectives of this study are as follows: (i) to develop a novel model by extending the classical linear MIMIC model to allow both Berkson and classical measurement errors, defining the MIMIC measurement error (MIMIC ME) model; (ii) to develop likelihood-based estimation methods for the MIMIC ME model; and (iii) to apply the newly defined MIMIC ME model to atomic bomb survivor data to study the impact of dyslipidemia and radiation dose on the physical manifestations of dyslipidemia. Finally, as a by-product of our work, we also obtain a data-driven estimate of the variance of the classical measurement error associated with an estimate of the amount of radiation dose received by atomic bomb survivors at the time of their exposure.},
doi = {10.1002/sim.6243},
journal = {Statistics in Medicine},
number = 25,
volume = 33,
place = {United States},
year = {2014},
month = {6}
}