On the Reliability of Chow Type Tests for Parameter Constancy in Multivariate Dynamic Models

B. Candelon; H. Lütkepohl

doi:10.1016/S0165-1765(01)00478-5

On the Reliability of Chow Type Tests for Parameter Constancy in Multivariate Dynamic Models

B. Candelon, H. Lütkepohl^*

^*Corresponding author for this work

Macro, International & Labour Economics

Research output: Contribution to journal › Article › Academic › peer-review

438 Downloads (Pure)

Abstract

The small sample properties of two types of chow tests are investigated in the context of multiple time series systems. It is found that the tests may have substantially distorted size if the sample size is not large relative to the number of parameters in the model under study. In particular the tests reject far too often in this situation. It is shown that bootstrap versions of the tests have much better properties in this respect. In other words, the bootstrap can be used to size-adjust the tests.

Original language	English
Pages (from-to)	155-160
Journal	Economics Letters
Volume	73
DOIs	https://doi.org/10.1016/S0165-1765(01)00478-5
Publication status	Published - 1 Jan 2001

Access to Document

10.1016/S0165-1765(01)00478-5

Full TextFinal published version, 60.1 KB

Cite this

@article{3886831306ba4ec88c4c3125b0e69061,

title = "On the Reliability of Chow Type Tests for Parameter Constancy in Multivariate Dynamic Models",

abstract = "The small sample properties of two types of chow tests are investigated in the context of multiple time series systems. It is found that the tests may have substantially distorted size if the sample size is not large relative to the number of parameters in the model under study. In particular the tests reject far too often in this situation. It is shown that bootstrap versions of the tests have much better properties in this respect. In other words, the bootstrap can be used to size-adjust the tests.",

author = "B. Candelon and H. L{\"u}tkepohl",

year = "2001",

month = jan,

day = "1",

doi = "10.1016/S0165-1765(01)00478-5",

language = "English",

volume = "73",

pages = "155--160",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Excerpta Medica, Elsevier Science",

}

TY - JOUR

T1 - On the Reliability of Chow Type Tests for Parameter Constancy in Multivariate Dynamic Models

AU - Candelon, B.

AU - Lütkepohl, H.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - The small sample properties of two types of chow tests are investigated in the context of multiple time series systems. It is found that the tests may have substantially distorted size if the sample size is not large relative to the number of parameters in the model under study. In particular the tests reject far too often in this situation. It is shown that bootstrap versions of the tests have much better properties in this respect. In other words, the bootstrap can be used to size-adjust the tests.

AB - The small sample properties of two types of chow tests are investigated in the context of multiple time series systems. It is found that the tests may have substantially distorted size if the sample size is not large relative to the number of parameters in the model under study. In particular the tests reject far too often in this situation. It is shown that bootstrap versions of the tests have much better properties in this respect. In other words, the bootstrap can be used to size-adjust the tests.

U2 - 10.1016/S0165-1765(01)00478-5

DO - 10.1016/S0165-1765(01)00478-5

M3 - Article

SN - 0165-1765

VL - 73

SP - 155

EP - 160

JO - Economics Letters

JF - Economics Letters

ER -