Hi All,
there may be an easy way to do this but I haven't figured it out yet. I just want the regression line to pass through the y-axis at the intercept. So far, I can only get results like what I included in the attachment.
thanks for any help!
If you're in Bivariate, just reset the X axis to include 0 before you add the Fit Line. The line will span all visible X values.
If you're in Bivariate, just reset the X axis to include 0 before you add the Fit Line. The line will span all visible X values.
Xan, is there a way to do this for Fit Spline, either here or for the smoother in Graph Builder? I.e. extend the smoother through x=0?
Hi @mia_stephens,
It seems neither Graph Builder nor Fit Y by X will extend a smoother out of the box. There is a way to this, but it requires a few steps:
Now, whether or not this is a good idea of course depends on the data and how flexible that model is. In the example below this particular extrapolation returns a prediction of -29,714 lbs for someone 0 inches tall :)
I hope this helps!
Thanks Julian, will pass posting this along.
Mia
Thanks so much! I knew it'd be a quick and easy one
If you happen to forget to reset the axis before fitting the line...
Click the red triangle menu on the linear fit, and then select "set alpha level", 0.05 is the default so click that.
This will redraw the regression line, and it will also redraw the confidence intervals of the individual and fit too.
Do you know how to do this using the JMP script?
All you have to do to get the JMP script for this, is to generate the bivariate plot interactively, and then go to the red triangle in the output, and select "Save Script". It will give you your script for reproducing the chart.