Big Data Analytics: A New Perspective

84 Pages Posted: 21 Apr 2016

See all articles by Alexander Chudik

Alexander Chudik

Federal Reserve Banks - Federal Reserve Bank of Dallas

George Kapetanios

King's College, London

M. Hashem Pesaran

University of Southern California - Department of Economics

Multiple version iconThere are 3 versions of this paper

Date Written: March 23, 2016

Abstract

Model specification and selection are recurring themes in econometric analysis. Both topics become considerably more complicated in the case of large-dimensional data sets where the set of specification possibilities can become quite large. In the context of linear regression models, penalised regression has become the de facto benchmark technique used to trade off parsimony and fit when the number of possible covariates is large, often much larger than the number of available observations. However, issues such as the choice of a penalty function and tuning parameters associated with the use of penalized regressions remain contentious. In this paper, we provide an alternative approach that considers the statistical significance of the individual covariates one at a time, whilst taking full account of the multiple testing nature of the inferential problem involved. We refer to the proposed method as One Covariate at a Time Multiple Testing (OCMT) procedure The OCMT has a number of advantages over the penalised regression methods: It is based on statistical inference and is therefore easier to interpret and relate to the classical statistical analysis, it allows working under more general assumptions, it is computationally simple and considerably faster, and it performs better in small samples for almost all of the five different sets of experiments considered in this paper. Despite its simplicity, the theory behind the proposed approach is quite complicated. We provide extensive theoretical and Monte Carlo results in support of adding the proposed OCMT model selection procedure to the toolbox of applied researchers.

Keywords: one covariate at a time, multiple testing, model selection, high dimensionality, penalized regressions, boosting, Monte Carlo experiments

JEL Classification: C520, C550

Suggested Citation

Chudik, Alexander and Kapetanios, George and Pesaran, M. Hashem, Big Data Analytics: A New Perspective (March 23, 2016). CESifo Working Paper Series No. 5824, Available at SSRN: https://ssrn.com/abstract=2767369 or http://dx.doi.org/10.2139/ssrn.2767369

Alexander Chudik

Federal Reserve Banks - Federal Reserve Bank of Dallas ( email )

2200 North Pearl Street
PO Box 655906
Dallas, TX 75265-5906
United States

George Kapetanios

King's College, London ( email )

30 Aldwych
London, WC2B 4BG
United Kingdom
+44 20 78484951 (Phone)

M. Hashem Pesaran (Contact Author)

University of Southern California - Department of Economics ( email )

3620 South Vermont Ave. Kaprielian (KAP) Hall 300
Los Angeles, CA 90089
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
214
Abstract Views
1,067
Rank
124,700
PlumX Metrics