Frequentist Model Averaging in Structural Equation Modelling

Frequentist Model Averaging in Structural Equation Modelling psychometrika https://doi.org/10.1007/s11336-018-9624-y Shaobo Jin and Sebastian Ankargren UPPSALA UNIVERSITY Model selection from a set of candidate models plays an important role in many structural equation modelling applications. However, traditional model selection methods introduce extra randomness that is not accounted for by post-model selection inference. In the current study, we propose a model averaging technique within the frequentist statistical framework. Instead of selecting an optimal model, the contri- butions of all candidate models are acknowledged. Valid confidence intervals and a χ test statistic are proposed. A simulation study shows that the proposed method is able to produce a robust mean-squared error, a better coverage probability, and a better goodness-of-fit test compared to model selection. It is an interesting compromise between model selection and the full model. Key words: model selection, post-selection inference, coverage probability, local asymptotic, goodness- of-fit. 1. Introduction Many statistical applications involve the choice of an optimal model from a set of candidate models. To serve such a need, an extensive range of model selection techniques has been proposed in the literature, e.g. AIC (Akaike, 1973) and BIC (Schwarz, 1978). Traditional statistical inference is performed conditional on the selected “optimal” model. However, model selection methods are data-driven and http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Psychometrika Springer Journals

Frequentist Model Averaging in Structural Equation Modelling

Loading next page...
 
/lp/springer_journal/frequentist-model-averaging-in-structural-equation-modelling-Glk2vuSqY8
Publisher
Springer Journals
Copyright
Copyright © 2018 by The Psychometric Society
Subject
Psychology; Psychometrics; Assessment, Testing and Evaluation; Statistics for Social Science, Behavorial Science, Education, Public Policy, and Law; Statistical Theory and Methods
ISSN
0033-3123
eISSN
1860-0980
D.O.I.
10.1007/s11336-018-9624-y
Publisher site
See Article on Publisher Site

Abstract

psychometrika https://doi.org/10.1007/s11336-018-9624-y Shaobo Jin and Sebastian Ankargren UPPSALA UNIVERSITY Model selection from a set of candidate models plays an important role in many structural equation modelling applications. However, traditional model selection methods introduce extra randomness that is not accounted for by post-model selection inference. In the current study, we propose a model averaging technique within the frequentist statistical framework. Instead of selecting an optimal model, the contri- butions of all candidate models are acknowledged. Valid confidence intervals and a χ test statistic are proposed. A simulation study shows that the proposed method is able to produce a robust mean-squared error, a better coverage probability, and a better goodness-of-fit test compared to model selection. It is an interesting compromise between model selection and the full model. Key words: model selection, post-selection inference, coverage probability, local asymptotic, goodness- of-fit. 1. Introduction Many statistical applications involve the choice of an optimal model from a set of candidate models. To serve such a need, an extensive range of model selection techniques has been proposed in the literature, e.g. AIC (Akaike, 1973) and BIC (Schwarz, 1978). Traditional statistical inference is performed conditional on the selected “optimal” model. However, model selection methods are data-driven and

Journal

PsychometrikaSpringer Journals

Published: Jun 4, 2018

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