Description

This permutation based hypothesis test, suited for gaussian and binary data, assesses the difference between two networks based on several invariance measures (network structure invariance, global strength invariance, edge invariance). Network structures are estimated with l1-regularized partial correlations (gaussian data) or with l1-regularized logistic regression (eLasso, binary data). Suited for comparison of independent and dependent samples. For dependent samples, only supported for data of one group which is measured twice.

Details

Author(s)

Claudia D. van Borkulo, with contributions from Jonas Haslbeck, Sacha Epskamp, Payton Jones and Alex Millner

Maintainer: Claudia D. van Borkulo <cvborkulo@gmail.com>

References

Ernst, M.D. Permutation methods: A basis for exact inference. Stat Sci. 2004;19(4):676-685.

Good, P.I. Permutation, parametric and bootstrap tests of hypotheses. Vol. 3. New York:: Springer, 2005.

van Borkulo, C. D., Boschloo, L., Borsboom, D., Penninx, B. W. J. H., Waldorp, L. J., & Schoevers, R.A. (2015). Association of symptom network structure with the course of depression. JAMA Psychiatry. 2015;72(12). doi:10.1001/jamapsychiatry.2015.2079

van Borkulo, C. D., Boschloo, Kossakowski, J., Tio, P., L., Schoevers, R.A., Borsboom, D., & , Waldorp, L. J. (2016). Comparing network structures on three aspects: A permutation test. doi:10.13140/RG.2.2.29455.38569