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

Showing results for

- JMP User Community
- :
- Discussions
- :
- Trying to work out a 2/3 sigma failure rule on a s...

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

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

Nov 13, 2012 4:20 PM
(583 views)

Hi there,

I was wondering if someone could help me out. I have a raw data pull and I would like to try to manually work out if 2 out of the last 3 points is above 3 sigma. I already have worked out my control limits via control charts based on 4 pseudo screened data. If my UCL was 3.75 and I had the following values 2,3.9,4.2 (may not be in that order) then how would I be able to apply this rule to populate a variable to trigger the rule.

3 REPLIES

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

Nov 14, 2012 7:16 AM
(418 views)

Try something like this:

n = N Row(:Data Table);

c = 0;

if(:Column

if(:Column[n-1] > 3.75,c <- c+1);

if(:Column[n-2] > 3.75,c <- c+1);

if(c >= 2, [Do whatever you want as a response here]);

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

Nov 14, 2012 7:36 AM
(418 views)

A condensed version of the same idea (utilizing element-wise comparison):

If**(** Sum**(** :Column**[**n - **2** :: n**]** > **3.75** **)** >= **2**, [Do whatever you want as a response here]**)**;

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

Nov 16, 2012 1:51 PM
(418 views)