论文信息 - A method for testing the order of an autoregressive-moving average process

A method for testing the order of an autoregressive-moving average process

SUMMARY A procedure is suggested for testing the order of an autoregressive-moving average process which is based on the same set of residual serial correlations as the Box-Pierce test. However, the present method has advantages in terms of its sensitivity to discriminating between alternative models.

E. J. Godolphin

[1] G. Box,et al. On a measure of lack of fit in time series models , 1978 .

[2] J. Hosking. A Unified Derivation of the Asymptotic Distributions of Goodness‐Of‐Fit Statistics for Autoregressive Time‐Series Models , 1978 .

[3] J. Durbin,et al. Techniques for Testing the Constancy of Regression Relationships Over Time , 1975 .

[4] Chris Chatfield,et al. The Holt-Winters Forecasting Procedure , 1978 .

[5] M. Bartlett. On the Theoretical Specification and Sampling Properties of Autocorrelated Time‐Series , 1946 .

[6] Paul Newbold,et al. Some power studies of a portmanteau test of time series model specification , 1979 .

[7] A Large‐Sample Test for Detecting Gaps in Moving Average Models , 1978 .

[8] E. J. Godolphin,et al. Invariance Properties of Uncorrelated Residual Transformations , 1978 .

[9] H. Theil. Principles of econometrics , 1971 .

[10] A. M. Walker. Large-sample estimation of parameters for movingaverage models , 1961 .

[11] P. Whittle,et al. TESTS OF FIT IN TIME SERIES , 1952 .

[12] E. J. Godolphin. A Procedure for Estimating Seasonal Moving Average Models Based on Large‐Sample Estimation of the Correlogram , 1977 .