×

On estimating thresholds in autoregressive models. (English) Zbl 0596.62085

Summary: The problem of estimating the threshold parameter, i.e., the change point, of a threshold autoregressive model is studied. By introducing smoothness into the model, sampling properties of the conditional least- squares estimate may be obtained. Artificial and real data are used for illustrations.

MSC:

62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62M20 Inference from stochastic processes and prediction
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] DOI: 10.1093/biomet/58.3.525 · Zbl 0224.62035 · doi:10.1093/biomet/58.3.525
[2] Brillinger D. R., Lectures on Mathematics in the Life Sciences (Amer. Math. Soc.) 13 pp 65– (1980)
[3] Browne R. L., Roy. Statist. Soc. 37 pp 149– (1975)
[4] DOI: 10.2307/1427125 · Zbl 0573.60056 · doi:10.2307/1427125
[5] DOI: 10.1214/aos/1176342999 · Zbl 0324.62014 · doi:10.1214/aos/1176342999
[6] DOI: 10.1214/aos/1176343000 · Zbl 0324.62015 · doi:10.1214/aos/1176343000
[7] Feller W., An Introduction to Probability Theory and its Applications (1966) · Zbl 0138.10207
[8] DOI: 10.1137/0710036 · Zbl 0258.65045 · doi:10.1137/0710036
[9] DOI: 10.1214/aos/1176344207 · Zbl 0383.62055 · doi:10.1214/aos/1176344207
[10] Ozaki T., On the Fitting of Non-stationary Autoregressive Models in Time Series Analysis (1975) · Zbl 0343.62080
[11] DOI: 10.2307/3213639 · Zbl 0541.62073 · doi:10.2307/3213639
[12] DOI: 10.1093/comjnl/7.2.155 · Zbl 0132.11702 · doi:10.1093/comjnl/7.2.155
[13] DOI: 10.2307/4241 · doi:10.2307/4241
[14] DOI: 10.1007/BF00533299 · Zbl 0209.49004 · doi:10.1007/BF00533299
[15] Tong H., Threshold Models in Non-linear Time Series Analysis. (1983) · Zbl 0527.62083 · doi:10.1007/978-1-4684-7888-4
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.