Download this Paper Open PDF in Browser

Regularized Regression Incorporating Network Information: Simultaneous Estimation of Covariate Coefficients and Connection Signs

Tinbergen Institute Discussion Paper 14-089/I

31 Pages Posted: 16 Jul 2014 Last revised: 21 Sep 2015

Matthias Weber

Bank of Lithuania - Center for Excellence in Finance and Economic Research (CEFER); Vilnius University

Martin Schumacher

University Medical Center Freiburg

Harald Binder

University of Mainz - University Medical Center

Date Written: June 28, 2014

Abstract

We develop an algorithm that incorporates network information into regression settings. It simultaneously estimates the covariate coefficients and the signs of the network connections (i.e. whether the connections are of an activating or of a repressing type). For the coefficient estimation steps an additional penalty is set on top of the lasso penalty, similarly to Li and Li (2008). We develop a fast implementation for the new method based on coordinate descent. Furthermore, we show how the new methods can be applied to time-to-event data. The new method yields good results in simulation studies concerning sensitivity and specificity of non-zero covariate coefficients, estimation of network connection signs, and prediction performance. We also apply the new method to two microarray time-to-event data sets from patients with ovarian cancer and diffuse large B-cell lymphoma. The new method performs very well in both cases. The main application of this new method is of biomedical nature, but it may also be useful in other fields where network data is available.

Keywords: high-dimensional data, gene expression data, pathway information, penalized regression

JEL Classification: C13, C41, C55

Suggested Citation

Weber, Matthias and Schumacher, Martin and Binder, Harald, Regularized Regression Incorporating Network Information: Simultaneous Estimation of Covariate Coefficients and Connection Signs (June 28, 2014). Tinbergen Institute Discussion Paper 14-089/I. Available at SSRN: https://ssrn.com/abstract=2466289 or http://dx.doi.org/10.2139/ssrn.2466289

Matthias Weber (Contact Author)

Bank of Lithuania - Center for Excellence in Finance and Economic Research (CEFER) ( email )

Totoriu g. 4
Vilnius, LT-01121
Lithuania

Vilnius University ( email )

Sauletekio ave. 11, Vilnius
Vilnius
Lithuania

Martin Schumacher

University Medical Center Freiburg ( email )

Freiburg
Germany

Harald Binder

University of Mainz - University Medical Center ( email )

Langenbeckstrasse 1
International Office Building 301
Mainz, D-55099
Germany

Paper statistics

Downloads
86
Rank
249,525
Abstract Views
467