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

- JMP User Community
- :
- Discussions
- :
- Significance of polynomial fit

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

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Jun 18, 2019 7:06 AM
(989 views)

Could you check the above result? Is it not signigicant for polynomial (2-degree) regression, right? (p=0.3212)

Data points are near the polynomial fit line, and R-squared is 98%. However, due to insignificance, in my result, can't I use this polynomial regression? and I have to use simple linear regression?

Apparently, it seems polynomial regression line is more clear then linear line, but JMP says it's not significant. Could you guide me about this?

Thanks,

1 ACCEPTED SOLUTION

Accepted Solutions

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

The human visual system is a wonderful, amazing device. But it is also creative and makes up things that aren't really there. In this case, such a result (curved line) as your sample can easily occur from a linear response. The statistics are not meant to dictate your conclusions but your statistics suggest that the non-linear component has practically no support from the data.

Learn it once, use it forever!

2 REPLIES 2

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

The human visual system is a wonderful, amazing device. But it is also creative and makes up things that aren't really there. In this case, such a result (curved line) as your sample can easily occur from a linear response. The statistics are not meant to dictate your conclusions but your statistics suggest that the non-linear component has practically no support from the data.

Learn it once, use it forever!

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Significance of polynomial fit

Thank you for your reply. I also agree with you. Maybe I wanted to have non-linear model which looks like more supporting my conclusion. As the statistics indicated, I'll use linear model as it is. Many thanks!!!

Sincerely,

JK

Sincerely,

JK

Article Labels

There are no labels assigned to this post.