Display options
Cite
Dekker D, Krackhardt D, Snijders TA. Sensitivity of MRQAP Tests to Collinearity and Autocorrelation Conditions. Psychometrika. 2007;72(4):563-581doi: 10.1007/s11336-007-9016-1.
Dekker, D., Krackhardt, D., & Snijders, T. A. (2007). Sensitivity of MRQAP Tests to Collinearity and Autocorrelation Conditions. Psychometrika, 72(4), 563-581. https://doi.org/10.1007/s11336-007-9016-1
Dekker, David, et al. "Sensitivity of MRQAP Tests to Collinearity and Autocorrelation Conditions." Psychometrika vol. 72,4 (2007): 563-581. doi: https://doi.org/10.1007/s11336-007-9016-1
Dekker D, Krackhardt D, Snijders TA. Sensitivity of MRQAP Tests to Collinearity and Autocorrelation Conditions. Psychometrika. 2007 Dec;72(4):563-581. doi: 10.1007/s11336-007-9016-1. Epub 2007 Aug 07. PMID: 20084106; PMCID: PMC2798974.
Copy Download .nbib Format: NLM
Share it on

Psychometrika. 2007 Dec;72(4):563-581. doi: 10.1007/s11336-007-9016-1. Epub 2007 Aug 07.

Sensitivity of MRQAP Tests to Collinearity and Autocorrelation Conditions.

Psychometrika

David Dekker, David Krackhardt, Tom A B Snijders

PMID: 20084106 PMCID: PMC2798974 DOI: 10.1007/s11336-007-9016-1

Abstract

Multiple regression quadratic assignment procedures (MRQAP) tests are permutation tests for multiple linear regression model coefficients for data organized in square matrices of relatedness among n objects. Such a data structure is typical in social network studies, where variables indicate some type of relation between a given set of actors. We present a new permutation method (called "double semi-partialing", or DSP) that complements the family of extant approaches to MRQAP tests. We assess the statistical bias (type I error rate) and statistical power of the set of five methods, including DSP, across a variety of conditions of network autocorrelation, of spuriousness (size of confounder effect), and of skewness in the data. These conditions are explored across three assumed data distributions: normal, gamma, and negative binomial. We find that the Freedman-Lane method and the DSP method are the most robust against a wide array of these conditions. We also find that all five methods perform better if the test statistic is pivotal. Finally, we find limitations of usefulness for MRQAP tests: All tests degrade under simultaneous conditions of extreme skewness and high spuriousness for gamma and negative binomial distributions.

References

  1. J Pers Soc Psychol. 2003 Feb;84(2):340-51 - PubMed
  2. Evolution. 1994 Oct;48(5):1487-1499 - PubMed
  3. Cancer Res. 1967 Feb;27(2):209-20 - PubMed

Publication Types