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
- :
- Re: Extend linear regression line in JMP version 1...

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

Feb 13, 2018 9:32 AM
(657 views)

Hi Julian,

The problem with your "trick" is this: Suppose I have a data table with three columns of data -- Age, Height, Weight. Sometimes I will plot Age vs Weight, sometimes I will plot Age vs Weight, sometimes I will plot Height vs Weight, and sometimes I will invert the X and Y values (Weight vs Age instead of Age vs Weight). Your trick works only if I have only a single X value for all plots. Correct? Or am I missing something? And, if I am correct, it becomes a real pain to manage as to which column (Age, Weight, Height) will be the X-value for the next plot that I will be making (or re-making via a script). Instead...JMP should -- at a minimum -- allow forced-fits (where I am prescribing the slope and intercept, for example) to extend to the limits of the X and Y plot window limits.

Highlighted

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

Feb 13, 2018 9:48 AM
(653 views)

Hi @nocaltim,

I see just what you mean! There are a few ways to go about this. Using rows with value ranges staggered by column you can achieve the same result, regardless of what variable is the X or Y:I agree that's not ideal, and in Fit Y by X in JMP 14 the line will extend by default. Another option: Graph Builder has a nice functionality for that sort of plotting using the Formula element, which might be useful to you in general. Write your own formula in a formula column, or for any model save your prediction formula for the mean, as well as the formula columns for the confidence intervals (if you want, but make sure to save the formula columns, not just the values), then pull up graph builder, use the same X as the X variable, then all your formula columns for the Y variable, and then click the Formula graph element. You can then change line colors and styles if you like.

I hope this helps some!

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

Feb 13, 2018 11:58 AM
(639 views)

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

Feb 13, 2018 3:42 PM
(632 views)

I just need to say this, to get it out of my system. I understand there are exceptions to almost every rule, but:

1. Most physical phenomena are described by sums and/or products of differential equations. These differential equations are usually nonlinear in the parameters by nature. (This means something different than "curved"!!)

2. Since these sums and/or products of differential equations are very difficult to model, we tend to fit Taylor Series approximations to them, since they are much easier to specify and can often do an acceptable job of fitting the data. These approximations are necessarily fit only over the range of the existing data.

3. Making predictions by extrapolating these approximations outside the existing data is like playing Russian Roulette.

Please don't be too upset if JMP and the responsible denizens of this community don't want to help you load your gun!

You can do anything your heart desires, no matter how statistically ill-considered or exceptional, by writing a JSL script. Scripts can be easily deployed across an enterprise. You may wish to consider writing some JSL to implement your procedures.

Good luck!

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

2 weeks ago
(75 views)

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

Jul 19, 2017 7:18 AM
(3149 views)

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

Jul 19, 2017 7:20 AM
(3139 views)

For large and complicated datasets the work-around is not feasible.

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

Jul 19, 2017 12:21 PM
(1049 views)

When first-generation food processors cut off fingers, responsible manufacturers added interlocks to the covers.

When Taylor Series approximations were improperly used to extrapolate beyond the range of the data, responsible manufacturers disabled that functionality.

I think Jim and Dan are right. Just say no to the workarounds. If you simply must extrapolate, fit a deterministic (usually nonlinear) model.

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

Dec 14, 2017 4:13 PM
(800 views)

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

Dec 14, 2017 4:43 PM
(793 views)

While there are almost always exceptions to rules, I believe JMP has taken the most prudent road with the way they have implemented the platform.

Jim