Testing for Structural Breaks in Small Samples

29 Pages Posted: 2 Apr 2008

See all articles by Sergei Antoshin

Sergei Antoshin

George Washington University, School of Business; International Monetary Fund

Andrew Berg

International Monetary Fund (IMF) - Developing Country Studies Division

Marcos Souto

George Washington University - School of Business; International Monetary Fund (IMF)

Date Written: March 2008

Abstract

In a recent paper, Bai and Perron (2006) demonstrate that their approach for testing for multiple structural breaks in time series works well in large samples, but they found substantial deviations in both the size and power of their tests in smaller samples. We propose modifying their methodology to deal with small samples by using Monte Carlo simulations to determine sample-specific critical values under the null each time the test is run. We draw on the results of our simulations to offer practical suggestions on handling serial correlation, model misspecification, and the use of alternative test statistics for sequential testing. We show that, for most types of data generating processes in samples with as low as 50 observations, our proposed modifications perform substantially better.

Keywords: Structural breaks, small samples, Monte Carlo simulation

JEL Classification: C29, C39, C59

Suggested Citation

Antoshin, Sergei and Berg, Andrew and Souto, Marcos, Testing for Structural Breaks in Small Samples (March 2008). IMF Working Paper No. 08/75, Available at SSRN: https://ssrn.com/abstract=1115606

Sergei Antoshin

George Washington University, School of Business ( email )

2023 G Street
Washington, DC 20052
United States
202-362-7008 (Phone)

HOME PAGE: http://savickas.net/cgi-bin/GWfinance/viewfaculty.cgi?fn=36

International Monetary Fund ( email )

700 19th Street NW
Washington, DC 20431
United States
202-623-7630 (Phone)

Andrew Berg

International Monetary Fund (IMF) - Developing Country Studies Division ( email )

700 19th Street NW
Washington, DC 20431
United States
202-623-8843 (Phone)
202-589-8843 (Fax)

Marcos Souto

George Washington University - School of Business ( email )

Washington, DC 20052
United States

International Monetary Fund (IMF) ( email )

700 19th Street NW
Washington, DC 20431
United States

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

Paper statistics

Downloads
302
Abstract Views
1,718
Rank
183,574
PlumX Metrics