Advanced search
2 files | 1.41 MB Add to list

A bootstrap version of the Hausman test to assess the impact of cluster-level endogeneity beyond the random intercept model

Wouter Talloen (UGent) , Tom Loeys (UGent) and Beatrijs Moerkerke (UGent)
Author
Organization
Abstract
In the random intercept model for clustered data, the random effect is typically assumed to be independent of predictors. Violation of this assumption due to unmeasured cluster-level confounding (endogeneity) induces bias in the estimates of effects of within-cluster predictors. Treating cluster-specific intercepts as fixed rather than random avoids this bias. The Hausman test contrasts the fixed effect estimator with the traditional random effect estimator in the random intercept model to test for the presence of cluster-level endogeneity and has a known asymptotic -distribution under correct model specification. Unmeasured cluster-level heterogeneity may, however, interact with predictors as well, necessitating random slope models. Relying on either cluster or residual resampling in a bootstrap procedure, we propose two extensions of the Hausman test that can easily be used beyond the random intercept model. We compare the original Hausman test and its robust version to the newly proposed bootstrap tests in terms of empirical type I error rate and power. Under additive unmeasured heterogeneity, all methods perform equally well, whereas the original and robust Hausman tests are too liberal or too conservative under additional slope heterogeneity, both bootstrap Hausman tests maintain appropriate performance. Moreover, both bootstrap tests show robustness against misspecification in the presence of unit-level heteroscedasticity and temporal correlation.
Keywords
Statistics and Probability, Experimental and Cognitive Psychology, Arts and Humanities (miscellaneous), General Medicine, Hausman test, multilevel, random effects, fixed effects, confounding

Downloads

  • (...).pdf
    • data factsheet
    • |
    • UGent only
    • |
    • PDF
    • |
    • 40.69 KB
  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.37 MB

Citation

Please use this url to cite or link to this publication:

MLA
Talloen, Wouter, et al. “A Bootstrap Version of the Hausman Test to Assess the Impact of Cluster-Level Endogeneity beyond the Random Intercept Model.” MULTIVARIATE BEHAVIORAL RESEARCH, vol. 54, Informa, 2019, pp. 1–14.
APA
Talloen, W., Loeys, T., & Moerkerke, B. (2019). A bootstrap version of the Hausman test to assess the impact of cluster-level endogeneity beyond the random intercept model. MULTIVARIATE BEHAVIORAL RESEARCH, 54, 1–14.
Chicago author-date
Talloen, Wouter, Tom Loeys, and Beatrijs Moerkerke. 2019. “A Bootstrap Version of the Hausman Test to Assess the Impact of Cluster-Level Endogeneity beyond the Random Intercept Model.” MULTIVARIATE BEHAVIORAL RESEARCH 54: 1–14.
Chicago author-date (all authors)
Talloen, Wouter, Tom Loeys, and Beatrijs Moerkerke. 2019. “A Bootstrap Version of the Hausman Test to Assess the Impact of Cluster-Level Endogeneity beyond the Random Intercept Model.” MULTIVARIATE BEHAVIORAL RESEARCH 54: 1–14.
Vancouver
1.
Talloen W, Loeys T, Moerkerke B. A bootstrap version of the Hausman test to assess the impact of cluster-level endogeneity beyond the random intercept model. MULTIVARIATE BEHAVIORAL RESEARCH. 2019;54:1–14.
IEEE
[1]
W. Talloen, T. Loeys, and B. Moerkerke, “A bootstrap version of the Hausman test to assess the impact of cluster-level endogeneity beyond the random intercept model,” MULTIVARIATE BEHAVIORAL RESEARCH, vol. 54, pp. 1–14, 2019.
@article{8589975,
  abstract     = {In the random intercept model for clustered data, the random effect is typically assumed to be independent of predictors. Violation of this assumption due to unmeasured cluster-level confounding (endogeneity) induces bias in the estimates of effects of within-cluster predictors. Treating cluster-specific intercepts as fixed rather than random avoids this bias. The Hausman test contrasts the fixed effect estimator with the traditional random effect estimator in the random intercept model to test for the presence of cluster-level endogeneity and has a known asymptotic -distribution under correct model specification. Unmeasured cluster-level heterogeneity may, however, interact with predictors as well, necessitating random slope models. Relying on either cluster or residual resampling in a bootstrap procedure, we propose two extensions of the Hausman test that can easily be used beyond the random intercept model. We compare the original Hausman test and its robust version to the newly proposed bootstrap tests in terms of empirical type I error rate and power. Under additive unmeasured heterogeneity, all methods perform equally well, whereas the original and robust Hausman tests are too liberal or too conservative under additional slope heterogeneity, both bootstrap Hausman tests maintain appropriate performance. Moreover, both bootstrap tests show robustness against misspecification in the presence of unit-level heteroscedasticity and temporal correlation.},
  author       = {Talloen, Wouter and Loeys, Tom and Moerkerke, Beatrijs},
  issn         = {0027-3171},
  journal      = {MULTIVARIATE BEHAVIORAL RESEARCH},
  keywords     = {Statistics and Probability,Experimental and Cognitive Psychology,Arts and Humanities (miscellaneous),General Medicine,Hausman test,multilevel,random effects,fixed effects,confounding},
  language     = {eng},
  pages        = {1--14},
  publisher    = {Informa},
  title        = {A bootstrap version of the Hausman test to assess the impact of cluster-level endogeneity beyond the random intercept model},
  url          = {http://dx.doi.org/10.1080/00273171.2018.1482192},
  volume       = {54},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: