A note on marginalization of regression parameters from mixed models of binary outcomes

A note on marginalization of regression parameters from mixed models of binary outcomes IntroductionMixed‐effects models are a popular approach for analysis of longitudinal and/or clustered binary outcomes, with many texts either devoted to or with substantial treatment on the topic (Raudenbush and Bryk, ; Demidenko, ; Skrondal and Rabe‐Hesketh, ; Molenberghs and Verbeke, ; Brown and Prescott, ; Hedeker and Gibbons, ; McCulloch et al., ; Fitzmaurice et al., ; Goldstein, ). Such models are often referred to as belonging to the class of models known as generalized linear mixed models (GLMMs). It is well known that the regression parameters in such models have the “subject‐specific” (SS) or conditional interpretation (Neuhaus et al., ), representing effects of the covariates controlling for, or holding constant, the random effects. This is in contrast to the marginal or “population‐averaged” (PA) estimates of, most notably, the GEE approach (Zeger and Liang, ) and the marginalized multilevel model (Heagerty and Zeger, ). The SS and PA regression parameters generally differ in meaning and value, and the SS regression parameters depend on how many random effects are included in the model (e.g., conditional on random intercepts only or conditional on random intercepts and trends). Thus, Zeger et al. () recommend that SS models are useful when the focus http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Biometrics Wiley

A note on marginalization of regression parameters from mixed models of binary outcomes

Loading next page...
 
/lp/wiley/a-note-on-marginalization-of-regression-parameters-from-mixed-models-Tm80MSOICQ
Publisher
Wiley
Copyright
© 2018, The International Biometric Society
ISSN
0006-341X
eISSN
1541-0420
D.O.I.
10.1111/biom.12707
Publisher site
See Article on Publisher Site

Abstract

IntroductionMixed‐effects models are a popular approach for analysis of longitudinal and/or clustered binary outcomes, with many texts either devoted to or with substantial treatment on the topic (Raudenbush and Bryk, ; Demidenko, ; Skrondal and Rabe‐Hesketh, ; Molenberghs and Verbeke, ; Brown and Prescott, ; Hedeker and Gibbons, ; McCulloch et al., ; Fitzmaurice et al., ; Goldstein, ). Such models are often referred to as belonging to the class of models known as generalized linear mixed models (GLMMs). It is well known that the regression parameters in such models have the “subject‐specific” (SS) or conditional interpretation (Neuhaus et al., ), representing effects of the covariates controlling for, or holding constant, the random effects. This is in contrast to the marginal or “population‐averaged” (PA) estimates of, most notably, the GEE approach (Zeger and Liang, ) and the marginalized multilevel model (Heagerty and Zeger, ). The SS and PA regression parameters generally differ in meaning and value, and the SS regression parameters depend on how many random effects are included in the model (e.g., conditional on random intercepts only or conditional on random intercepts and trends). Thus, Zeger et al. () recommend that SS models are useful when the focus

Journal

BiometricsWiley

Published: Jan 1, 2018

Keywords: ; ; ; ;

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off