摘要
讨论了一类广义非正态时间序列模型——周期性新指数自回归模型SNEAR(2).利用升维的方法将其化为一随机系数的平稳自回归模型,并给出了模型参数的条件最小二乘估计.
One class of a general non-normal time series models--SNEAR(2) isdiscussed. It can be changed into a stationary autoregressive model with random coefficients by rising dimension method. The estimators of the parameters of the model are given with the help of conditional least square method.
出处
《石油大学学报(自然科学版)》
CSCD
1993年第3期102-111,共10页
Journal of the University of Petroleum,China(Edition of Natural Science)
关键词
指数
自回归模型
最小二乘估计
Exponential autoregressive models: Coutcovariance function: Conditional least square estimates