topic Multivariate vs. Graph builder in Discussions

Multivariate vs. Graph builder

nac — Mon, 04 May 2020 11:49:13 GMT

Hi,

When I try to find correlation between Age and Height by using multivariate analysis R2=0.9807

When I apply the same thing by using Graph Builder R2=0.962

What is the reason of this change. This difference will be increase based on results.

Could someone help on this?

You can also see jmp file on enclosed.

Re: Multivariate vs. Graph builder

Mark_Bailey — Mon, 04 May 2020 12:58:10 GMT

I verified the Pearson linear correlation coefficient = 0.9807 from Multivariate with Bivariate and by hand. I do not know how the estimate provided by Graph Builder is calculated. You might send this example to JMP Technical Support (support@jmp.com) for investigation. Please report here what you learn.

Re: Multivariate vs. Graph builder

Dan_Obermiller — Mon, 04 May 2020 14:21:30 GMT

I think you are confusing the Pearson correlation coefficient (r) with the Coefficient of Determination (RSquare).

From Fit Y by X, Multivariate, AND Graph Builder, I get the same value for r, which is -0.981. I have included the Graph Builder report that shows this in the upper-left of the graph.

If I fit a linear regression line to the data I get an RSquare of 0.962 from both Graph Builder and Fit Y by X.

Graph Builder report for RSquare.