Regression Models with Time Series Errors
Journal of the American Statistical Association · 1984 · Volume 79 · Issue 385
DOI: 10.1080/01621459.1984.10477073
Abstract
The time series regression models in which the errors of regression equations follow stationary or nonstationary autoregressive moving average models are considered. Convergence properties of the sample autocorrelation function of observed series and the least squares estimates of the linear regression parameters are shown. Based upon these results, a procedure for specifying the tentative order of the mixed ARMA errors is proposed. Two examples are given.
Enable JavaScript for citation tools and additional paper interactions.