Bayesian Variable Selection for Nowcasting Economic Time Series

23 Pages Posted: 25 Oct 2013 Last revised: 19 Jun 2023

See all articles by Steven L. Scott

Steven L. Scott

Google Inc.

Hal R. Varian

School of Information; University of California, Berkeley - Operations and Information Technology Management Group; National Bureau of Economic Research (NBER)

Date Written: October 2013

Abstract

We consider the problem of short-term time series forecasting (nowcasting) when there are more possible predictors than observations. Our approach combines three Bayesian techniques: Kalman filtering, spike-and-slab regression, and model averaging. We illustrate this approach using search engine query data as predictors for consumer sentiment and gun sales.

Suggested Citation

Scott, Steven L. and Varian, Hal R., Bayesian Variable Selection for Nowcasting Economic Time Series (October 2013). NBER Working Paper No. w19567, Available at SSRN: https://ssrn.com/abstract=2345062

Steven L. Scott (Contact Author)

Google Inc. ( email )

1600 Amphitheatre Parkway
Second Floor
Mountain View, CA 94043
United States

Hal R. Varian

School of Information ( email )

UC Berkeley
Berkeley, CA 94720-4600
United States
510-642-9980 (Phone)
510-642-5814 (Fax)

HOME PAGE: http://www.sims.berkeley.edu/~hal/people/hal/biography.html

University of California, Berkeley - Operations and Information Technology Management Group ( email )

545 Student Services Building
Berkeley, CA 94720
United States
510-643-6388 (Phone)

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

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

Paper statistics

Downloads
108
Abstract Views
1,017
Rank
428,099
PlumX Metrics