Testing for Structural Breaks in Small Samples /

Testing for Structural Breaks in Small Samples /

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 t...

ver descrição completa

Detalhes bibliográficos
Autor principal: Antoshin, Sergei
Outros Autores: Berg, Andrew, Souto, Marcos
Formato: Periódico
Idioma:English
Publicado em: Washington, D.C. : International Monetary Fund, 2008.
Colecção:IMF Working Papers; Working Paper ; No. 2008/075
Assuntos:
Autocorrelation Coefficient
Prob K
Sample Size
Serial Correlation
WP
Acesso em linha:Full text available on IMF
LEADER 02083cas a2200325 a 4500
001 AALejournalIMF004968
008 230101c9999 xx r poo 0 0eng d
020 |c 5.00 USD 
020 |z 9781451869378 
022 |a 1018-5941 
040 |a BD-DhAAL  |c BD-DhAAL 
100 1 |a Antoshin, Sergei. 
245 1 0 |a Testing for Structural Breaks in Small Samples /  |c Sergei Antoshin, Andrew Berg, Marcos Souto. 
264 1 |a Washington, D.C. :  |b International Monetary Fund,  |c 2008. 
300 |a 1 online resource (27 pages) 
490 1 |a IMF Working Papers 
500 |a <strong>Off-Campus Access:</strong> No User ID or Password Required 
500 |a <strong>On-Campus Access:</strong> No User ID or Password Required 
506 |a Electronic access restricted to authorized BRAC University faculty, staff and students 
520 3 |a 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 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. 
538 |a Mode of access: Internet 
650 7 |a Autocorrelation Coefficient  |2 imf 
650 7 |a Prob K  |2 imf 
650 7 |a Sample Size  |2 imf 
650 7 |a Serial Correlation  |2 imf 
650 7 |a WP  |2 imf 
700 1 |a Berg, Andrew. 
700 1 |a Souto, Marcos. 
830 0 |a IMF Working Papers; Working Paper ;  |v No. 2008/075 
856 4 0 |z Full text available on IMF  |u http://elibrary.imf.org/view/journals/001/2008/075/001.2008.issue-075-en.xml  |z IMF e-Library 

Registos relacionados