Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

- JMP User Community
- :
- Discussions
- :
- Concordance analysis with continous variable

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

May 7, 2017 5:43 AM
(5793 views)

Hello,

I am trying to solve the following statistical problem in jmp:

1. I got a gold standard fixed variable y (for example: y = 100)

2. I got three data sets x1,x2,x3: (for example x1=92;94;99 / x2=92;94;99;101;103 / x3=92;94;99;101;103;107;100;99;100)

please note: the data sets have similar data, but the number of data points are different. all variables are continuous.

I am looking for with a statistical test or function, to evaluate which dataset x1, x2 or x3 has the closest mean AND the lowest SD to match the gold standard y ? - please note: the gold standard y has no sd, just a fixed value. Looking at ther samples for concordance analysis I just could do this was nominal variables; mine are ordinal or continous.

Any advice much appreciated. Many thanks, Marc

2 ACCEPTED SOLUTIONS

Accepted Solutions

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Created:
May 7, 2017 2:00 PM
| Last Modified: May 7, 2017 2:01 PM
(6989 views)
| Posted in reply to message from Marc 05-07-2017

I understand your use of the word 'concordance' here but that word is also a statistical term that refers to measures of *agreement* among *categorical variables*.

I recommend using confidence interval estimates of the mean. The 'gold standard' is your *null hypothesis* H0: mean = 100) and therefore your alternative hypothesis is that the opposite (H1: mean not = 100). You compare the intervals to the gold standard and to each other using Analyze > Fit Y by X (Oneway platform). Here is your example in a data table laid out for Oneway:

\\

Here is the Oneway platform with a reference line for the gold standard and the results for ANOVA:

Now you compare the confidence interval for each sample. You can plot them in Graph Builder, too. Right-click on the Means for Oneway Anova table and select Make Into Data Table. It might look like this:

Learn it once, use it forever!

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Many thanks @markbailey !

4 REPLIES 4

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Created:
May 7, 2017 2:00 PM
| Last Modified: May 7, 2017 2:01 PM
(6990 views)
| Posted in reply to message from Marc 05-07-2017

I understand your use of the word 'concordance' here but that word is also a statistical term that refers to measures of *agreement* among *categorical variables*.

I recommend using confidence interval estimates of the mean. The 'gold standard' is your *null hypothesis* H0: mean = 100) and therefore your alternative hypothesis is that the opposite (H1: mean not = 100). You compare the intervals to the gold standard and to each other using Analyze > Fit Y by X (Oneway platform). Here is your example in a data table laid out for Oneway:

\\

Here is the Oneway platform with a reference line for the gold standard and the results for ANOVA:

Now you compare the confidence interval for each sample. You can plot them in Graph Builder, too. Right-click on the Means for Oneway Anova table and select Make Into Data Table. It might look like this:

Learn it once, use it forever!

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Many thanks @markbailey !

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Concordance analysis with continous variable

You need to change the "Accepted Solution" from your response to Mark Bailey's response. The marking of an "Accepted Solution" is not intended to just indicate that a solution to a Discussion Question has been found, but it need to point to the response that has the actual solution

Jim

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Concordance analysis with continous variable

hi

do you have any software for solve concordance analysis prpblems?

Article Labels

There are no labels assigned to this post.