【摘要】 先利用Bayes方法研究NGINAR(1)模型的参数估计问题,再利用条件分布预测方法进行模型预测.模拟结果表明,Bayes估计效果优于条件最小二乘估计和Yule-Walker估计,且条件分布预测方法比条件期望预测方法更适用于整数值序列.更多还原

【Abstract】 Firstly,the Bayesian method was used to study the problem of parameter estimation in the NGINAR(1)model,and then the method of conditional distribution prediction was used to predict the NGINAR(1)model.The simulation result shows that Bayesian estimation is better than the conditional least squares and Yule-Walker estimation,and the method of conditional distribution prediction is more suitable for integer-valued series than the method of conditional expectation prediction.更多还原