全部版块 我的主页
论坛 计量经济学与统计论坛 五区 计量经济学与统计软件 EViews专版
1237 1
2015-08-01
Now, here are the rules for determining p and q from the plots of autocorrelations and partial
autocorrelations:
i. If the ACF plot “cuts off sharply” at lag k (i.e., if the autocorrelation is significantly
different from zero at lag k and extremely low in significance at the next higher lag and
the ones that follow), while there is a more gradual “decay” in the PACF plot (i.e. if
the dropoff in significance beyond lag k is more gradual), then set q=k and p=0. This
is a so-called “MA(q) signature.”
ii. On the other hand, if the PACF plot cuts off sharply at lag k while there is a more
gradual decay in the ACF plot, then set p=k and q=0. This is a so-called “AR(p)
signature.”
iii. If there is a single spike at lag 1 in both the ACF and PACF plots, then set p=1 and q=0
if it is positive (this is an AR(1) signature), and set p=0 and q=1 if it is negative (this is
an MA(1) signature).
附件列表

Notes_on_nonseasonal_ARIMA_models--Robert_Nau.pdf

大小:1.19 MB

只需: 1 个论坛币  马上下载

二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

全部回复
2015-8-24 17:09:45
谢谢楼主分享,欢迎以后分享更多好的资料
二维码

扫码加我 拉你入群

请注明:姓名-公司-职位

以便审核进群资格,未注明则拒绝

相关推荐
栏目导航
热门文章
推荐文章

说点什么

分享

扫码加好友,拉您进群
各岗位、行业、专业交流群