TY - JOUR
T1 - A test of linearity against functional-coefficient autoregressive models
AU - Matsuda, Yasumasa
PY - 1999
Y1 - 1999
N2 - Our object in this paper is to propose a powerful test for detecting a broad class of nonlinearity of time series as one application of the method by Matsuda (1998). Consider autoregressive models Xt = φ1Xt-1 + ⋯ + φpXt-p + εt and we propose a statistic for testing whether or not φi depends on delayed values Xt-d for some i. We compare the power of our test with that of tests proposed by Luukkonen, Saikkonen and Teräsvirta (1988a) and Hjellvik and Tjøstheim (1995) by simulation studies and our test is shown to be satisfactory.
AB - Our object in this paper is to propose a powerful test for detecting a broad class of nonlinearity of time series as one application of the method by Matsuda (1998). Consider autoregressive models Xt = φ1Xt-1 + ⋯ + φpXt-p + εt and we propose a statistic for testing whether or not φi depends on delayed values Xt-d for some i. We compare the power of our test with that of tests proposed by Luukkonen, Saikkonen and Teräsvirta (1988a) and Hjellvik and Tjøstheim (1995) by simulation studies and our test is shown to be satisfactory.
KW - Autoregressive models
KW - Nonlinear time series
KW - Ordinary least squares estimator
KW - Weighted least squares estimator
UR - http://www.scopus.com/inward/record.url?scp=28244488225&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=28244488225&partnerID=8YFLogxK
U2 - 10.1080/03610929908832437
DO - 10.1080/03610929908832437
M3 - Article
AN - SCOPUS:28244488225
SN - 0361-0926
VL - 28
SP - 2539
EP - 2551
JO - Communications in Statistics - Theory and Methods
JF - Communications in Statistics - Theory and Methods
IS - 11
ER -