日期精度：到日 3 篇 · 到月 25 篇 · 到年 5 篇
It is shown that two tests for the adequacy of a fitted ARMA ( p, q, ) model, based respectively on comparison through the Lagrange multiplier test with an ARMA ( p + k, q ) model and on analysis of the first k residual autocorrelations from the estimated model, are equivalent.
自回归移动平均模型中残差自相关的有限样本分布
We examine by simulation the finite sample properties of tests of model adequacy based on individual residual autocorrelations, and of portmanteau statistics based on several residual autocorrelations, for autoregressive-moving average models. Both nonseasonal and seasonal models are considered.
时间序列模型设定的综合检验功效研究
In this note we present simulation evidence on the power of a portmanteau statistic used to detect time series model misspecification. This is related to the loss in forecasting accuracy resulting from use of the incorrectly specified model. Our conclusion is that the statistic achieves a high level of success only when sample size is large.
ARMA 模型残差自相关的有限样本分布
We examine by simulation the finite sample properties of tests of model adequacy based on individual residual autocorrelations, and of portmanteau statistics based on several residual autocorrelations, for autoregressive-moving average models. Both nonseasonal and seasonal models are considered.
时间序列模型设定综合检验的若干功效研究
In this note we present simulation evidence on the power of a portmanteau statistic used to detect time series model misspecification. This is related to the loss in forecasting accuracy resulting from use of the incorrectly specified model. Our conclusion is that the statistic achieves a high level of success only when sample size is large.
混合自回归移动平均过程的精确似然函数
Box & Jenkins (1970) develop a strategy for the analysis and forecasting of time series, based on the construction, after suitable differencing, of autoregressive-moving average models. They present a model building procedure which works very well for most general purposes, and in addition derive the exact likelihood function for both pure autoregressive and pure moving average processes, in the latter case this being a new result. In this note it is shown that a similar…
混合自回归滑动平均过程的精确似然函数
Box & Jenkins (1970) develop a strategy for the analysis and forecasting of time series, based on the construction, after suitable differencing, of autoregressive-moving average models. They present a model building procedure which works very well for most general purposes, and in addition derive the exact likelihood function for both pure autoregressive and pure moving average processes, in the latter case this being a new result. In this note it is shown that a similar…
Box–Jenkins 传递函数—噪声模型的贝叶斯估计
Summary The problem of estimating the coefficients of the transfer function-noise models proposed by Box and Jenkins is considered. A Bayesian approach is taken and the exact posterior density function of the coefficients is derived. Because of the complexity of this function, inference about individual parameters is virtually impossible except in the most simple cases. Accordingly, it is desirable to consider certain approximations. In particular, it is shown that inference…