Turn on suggestions

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

Showing results for

- JMP User Community
- :
- Discussions
- :
- Re: Help to develop script for normalized calcualtion

- 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

Aug 13, 2019 12:10 PM
(843 views)

Hello,

Could I get some help to develop a script which can calculate a normalized score. For example, in the attached sheet I have point scores for 5 people. It is difficult to compare them as is since each person's score seem to be on a different scale.

I would therefore normalize the data and compare. First, I compute the average score for each person and then divide each person's score with his average to come up with the normalized score, this is what is in the normalized points column. This is a tedious job if the size of the data set is large.

I was wondering if I can get some help to do this.

1 ACCEPTED SOLUTION

Accepted Solutions

Highlighted

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

You can calculate the standard scores by the following:

- Create a summary data table
- Tables==>Summary
- Specify to create the mean, standard deviation
- Group by the column that identifies each person

- Tables==>Summary
- Once the new table is created, go back to the original data table and
- Tables==>Join
- Match based upon the column that identifies each person

- Tables==>Join

- In the new table that is created, create a new column
- use the formula (:value-:mean)/:standard deviation

This will create the standardized value for each persons data

Jim

4 REPLIES 4

Highlighted
##

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

Re: Help to develop script for normalized calcualtion

Hi Raj,

Assuming that you have JMP14, have you tried the "Standardize" option in the "New Formula Column > Distribution" menu (accessible by right-clicking on the columns containing your raw scores)?

Assuming that you have JMP14, have you tried the "Standardize" option in the "New Formula Column > Distribution" menu (accessible by right-clicking on the columns containing your raw scores)?

Thierry R. Sornasse

Highlighted
##

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

Re: Help to develop script for normalized calcualtion

Hi Thierry,

It doesn't give me what I want since the calculation considers the whole data set at one. For example, it computes the average for all the values and uses it to standardize the data. What I want to do is that the average be computed for each person individually and use it to standardize the data for that particular person.

-Raj

Highlighted

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

You can calculate the standard scores by the following:

- Create a summary data table
- Tables==>Summary
- Specify to create the mean, standard deviation
- Group by the column that identifies each person

- Tables==>Summary
- Once the new table is created, go back to the original data table and
- Tables==>Join
- Match based upon the column that identifies each person

- Tables==>Join

- In the new table that is created, create a new column
- use the formula (:value-:mean)/:standard deviation

This will create the standardized value for each persons data

Jim

Highlighted
##

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

Re: Help to develop script for normalized calcualtion

Thank you Jim.

Article Labels

There are no labels assigned to this post.