Using Large Data Sets to Forecast Sectoral Employment

57 Pages Posted: 13 Jan 2011 Last revised: 18 Mar 2015

See all articles by Rangan Gupta

Rangan Gupta

University of Pretoria - Department of Economics

Alain Kabundi

University of Johannesburg - Department of Economics

Stephen M. Miller

University of Nevada, Las Vegas - Department of Economics; University of Connecticut - Department of Economics

Josine Uwilingiye

University of Johannesburg

Date Written: January 5, 2011

Abstract

We implement several Bayesian and classical models to forecast employment for eight sectors of the US economy. In addition to standard vector-autoregressive and Bayesian vector autoregressive models, we also include the information content of 143 additional monthly series in some models. Several approaches exist for incorporating information from a large number of series. We consider two approaches – extracting common factors (principle components) in a factor-augmented vector autoregressive or vector error-correction, Bayesian factor-augmented vector autoregressive or vector error-correction models, or Bayesian shrinkage in a large-scale Bayesian vector autoregressive models. Using the period of January 1972 to December 1999 as the in-sample period and January 2000 to March 2009 as the out-of-sample horizon, we compare the forecast performance of the alternative models. Finally, we forecast out-of sample from April 2009 through March 2018 using the best forecasting model for each employment series. We find that factor augmented models, especially error-correction versions, generally prove the best in out-of-sample forecast performance, implying that in addition to macroeconomic variables, incorporating long-run relationships along with short-run dynamics play an important role in forecasting employment.

Keywords: Sectoral Employment, Forecasting, Factor Augmented Models, Large-Scale BVAR models

JEL Classification: C32, R31

Suggested Citation

Gupta, Rangan and Kabundi, Alain and Miller, Stephen M. and Uwilingiye, Josine, Using Large Data Sets to Forecast Sectoral Employment (January 5, 2011). Statistical Methods and Applications, June 2014, Available at SSRN: https://ssrn.com/abstract=1739243 or http://dx.doi.org/10.2139/ssrn.1739243

Rangan Gupta

University of Pretoria - Department of Economics ( email )

Lynnwood Road
Hillcrest
Pretoria, 0002
South Africa

Alain Kabundi

University of Johannesburg - Department of Economics ( email )

P.O. Box 524
Auckland Park 2006, Johannesburg
South Africa

Stephen M. Miller (Contact Author)

University of Nevada, Las Vegas - Department of Economics ( email )

4505 S. Maryland Parkway
Box 456005
Las Vegas, NV 89154
United States
702-895-3776 (Phone)
702-895-1354 (Fax)

HOME PAGE: http://faculty.unlv.edu/smiller/

University of Connecticut - Department of Economics

365 Fairfield Way, U-1063
Storrs, CT 06269-1063
United States

Josine Uwilingiye

University of Johannesburg ( email )

P.O. Box 524
Auckland Park 2006, Johannesburg
South Africa

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
52
Abstract Views
567
rank
411,851
PlumX Metrics