cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Try the Materials Informatics Toolkit, which is designed to easily handle SMILES data. This and other helpful add-ins are available in the JMP® Marketplace
Choose Language Hide Translation Bar
sjk13b
sjk13b
Level I

Is there a way to create a bland-altman analysis and have the mean be based on a theoretical value?

Mar 7, 2016 05:06 PM (8201 views)

So I have two trials of data and I want to analyze how far they are away from 0.667, is there a way to make 0.667 my x-line?

0 Kudos
1 ACCEPTED SOLUTION

Accepted Solutions
ian_jmp
ian_jmp
Level X
Solution

Re: Is there a way to create a bland-altman analysis and have the mean be based on a theoretical value?

Mar 8, 2016 10:58 AM (8369 views)  |  Posted in reply to message from sjk13b 03-07-2016

As conventionally understood, a Bland-Altman analysis is for testing the level of agreement between two different ways of measuring the same thing. See, for example:

http://www.stattutorials.com/SAS/TUTORIAL-BLAND-ALTMAN.htm

https://en.wikipedia.org/wiki/Bland–Altman_plot

https://community.jmp.com/docs/DOC-6171

So using this approach doesn't seem to stack up with your desire to 'analyze how far each trial is away from 0.667'.


Can you describe a little more how your data was measured, or better yet, supply a sample?

View solution in original post

1 REPLY 1
ian_jmp
ian_jmp
Level X
Solution

Re: Is there a way to create a bland-altman analysis and have the mean be based on a theoretical value?

Mar 8, 2016 10:58 AM (8370 views)  |  Posted in reply to message from sjk13b 03-07-2016

As conventionally understood, a Bland-Altman analysis is for testing the level of agreement between two different ways of measuring the same thing. See, for example:

http://www.stattutorials.com/SAS/TUTORIAL-BLAND-ALTMAN.htm

https://en.wikipedia.org/wiki/Bland–Altman_plot

https://community.jmp.com/docs/DOC-6171

So using this approach doesn't seem to stack up with your desire to 'analyze how far each trial is away from 0.667'.


Can you describe a little more how your data was measured, or better yet, supply a sample?