cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
JMP is taking Discovery online, April 16 and 18. Register today and join us for interactive sessions featuring popular presentation topics, networking, and discussions with the experts.
Choose Language Hide Translation Bar
DAS_Owen
Level I

Reduced Major Axis regression in JMP

Can you do a reduced major axis (RMA) regression in JMP Pro 14? I've been trying to figure it out. Is it one of the orthogonal regression models?

 

Thanks!

Dustin A.S. Owen
2 ACCEPTED SOLUTIONS

Accepted Solutions
gzmorgan0
Super User (Alumni)

Re: Reduced Major Axis regression in JMP

This link describes different types of 2 variable regression. I found it useful.

 https://www.unc.edu/courses/2007spring/biol/145/001/docs/lectures/Nov5.html 

 

RMA is used in different applications, however, depending upon the application it can represent Reduced Major Axis or Ranged Major Axis.  Note that "In standard major axis (SMA) regression (also called reduced major axis or RMA regression), the areas of the triangles formed by the observations and the regression line are minimized. The standard major axis regression is particularly common. "

 

Standard Major Axis  a.k.a. Reduced Major Axis regression is the same as the JMP principal components regressions with univariate variances. What many packages refer to as MA is principal components regression with equal variances.

 

I loaded the R3.3.3 package lmodel2 and verified examples.  For interested parties this link explains how to calculate  Ranged Major Axis regression. 

 

Attached is mod2ex5.jmp with 2 attached scripts. These were used to verify results that match this R output [note RMA in thie R package is Ranged Major Axis and SMA is Standard | Reduced Major Axis].

image.png

image.png

View solution in original post

gzmorgan0
Super User (Alumni)

Re: Reduced Major Axis regression in JMP

3 REPLIES 3
gzmorgan0
Super User (Alumni)

Re: Reduced Major Axis regression in JMP

This link describes different types of 2 variable regression. I found it useful.

 https://www.unc.edu/courses/2007spring/biol/145/001/docs/lectures/Nov5.html 

 

RMA is used in different applications, however, depending upon the application it can represent Reduced Major Axis or Ranged Major Axis.  Note that "In standard major axis (SMA) regression (also called reduced major axis or RMA regression), the areas of the triangles formed by the observations and the regression line are minimized. The standard major axis regression is particularly common. "

 

Standard Major Axis  a.k.a. Reduced Major Axis regression is the same as the JMP principal components regressions with univariate variances. What many packages refer to as MA is principal components regression with equal variances.

 

I loaded the R3.3.3 package lmodel2 and verified examples.  For interested parties this link explains how to calculate  Ranged Major Axis regression. 

 

Attached is mod2ex5.jmp with 2 attached scripts. These were used to verify results that match this R output [note RMA in thie R package is Ranged Major Axis and SMA is Standard | Reduced Major Axis].

image.png

image.png

DAS_Owen
Level I

Re: Reduced Major Axis regression in JMP

So basically I use "Fit Y by X", click "Fit Ornthogonal", and then "Univariate Variances, Prin Comp" to exicute a Reduced Major Axis regression?

Dustin A.S. Owen
gzmorgan0
Super User (Alumni)

Re: Reduced Major Axis regression in JMP

image.png