turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- JMP User Community
- :
- Discussions
- :
- Discussions
- :
- ARIMA(1,0,0) output Parameter Estimates - I do not...

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Sep 20, 2017 9:08 AM
(1132 views)

I ran a simple AR(1) model on 24 rows of trending data just to see the output. It provided the AR(1) coefficient and the intercept - however, they made no sense to me. For example, I thought that if the output for an AR(1) is 0.8 and Intercept = 105, then the forecasting equation would be for y(t) = 105 + 0.8*y(t-1). But the output of the parameter estimates do not fit this. What am I missing? Thanks

Solved! Go to Solution.

1 ACCEPTED SOLUTION

Accepted Solutions

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Sep 25, 2017 6:55 PM
(1966 views)

According to ARIMA (http://www.jmp.com/support/help/13-2/Statistical_Details_for_ARIMA_Models.shtml#409330),

So, the AR(1) model you fit is: Y(t)-105=0.8*(Y(t-1)-105) +e(t), or Y(t)=21+0.8*Y(t-1)+e(t)

2 REPLIES

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Sep 25, 2017 6:55 PM
(1967 views)

According to ARIMA (http://www.jmp.com/support/help/13-2/Statistical_Details_for_ARIMA_Models.shtml#409330),

So, the AR(1) model you fit is: Y(t)-105=0.8*(Y(t-1)-105) +e(t), or Y(t)=21+0.8*Y(t-1)+e(t)

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Sep 30, 2017 4:19 PM
(1040 views)

Perfect! Thanks