The Elsmar Cove Wiki More Free Files The Elsmar Cove Forums Discussion Thread Index Post Attachments Listing Failure Modes Services and Solutions to Problems Elsmar cove Forums Main Page Elsmar Cove Home Page
Go Back   The Elsmar Cove Forum > Manufacturing, Service, and Business Systems Processes > Reliability Analysis - Predictions, Testing and Standards
Forum Username

Search the Elsmar Cove
Custom Search
Monitor the Elsmar Forum
Follow Marc & Elsmar
Elsmar Cove Forum RSS Feed  Marc Smith's Google+ Page  Marc Smith's Linked In Page   Marc Smith's Elsmar Cove YouTube Page  Marc Smith's Facebook Page  Elsmar Cove Twitter Feed
Elsmar Cove Groups
Elsmar Cove Google+ Group  Elsmar Cove LinkedIn Group  Elsmar Cove Facebook Group
Donate and $ Contributor Forum Access

Courtesy Quick Links

Links that Elsmar Cove visitors will find useful in your quest for knowledge:

Howard's
International Quality Services
Marcelo Antunes'
SQR Consulting
Bob Doering's
Correct SPC - Precision Machining

NIST's Engineering Statistics Handbook
IRCA - International Register of Certified Auditors
SAE - Society of Automotive Engineers
Quality Digest Portal
IEST - Institute of Environmental Sciences and Technology
ASQ - American Society for Quality

Related Topic Tags
grubbs test for outliers, z-values
Reply
 
Thread Tools Search this Thread Rate Thread Content Display Modes
  #1  
Old 1st February 2006, 02:40 AM
patric wessels's Avatar
patric wessels patric wessels is offline
Involved - Posts

 
Registration Date: May 2004
Location: Netherlands
Age: 50
 
Posts: 22
Thanks Given to Others: 0
Thanked 0 Times in 0 Posts
Karma Power: 44
Karma: 10
patric wessels has less than 100 Karma points so far.
I Say... Grubbs Test for Outliers and Why there are no Z-values for N>25

Dear all,

I am not sure if this is the right forum for this subject, but here's the question:

We are trying to assist our operators in determining whether a measured point is an outlier or not. We want to use the Grubbs test for this purpose. The problem is that in case of a large sample we measure 120 points and the tables with the Z-values (for 99% probability) only goes up to 25 samples points.

I am not an expert in statistics but I am sure there is a reason for this.

Can anyone help me out and explain why there are no Z-values for N>25?

Thanks.

Best regards,

Patric Wessels
QA Engineer

Sponsored Links
  #2  
Old 1st February 2006, 01:36 PM
Miner's Avatar
Miner Miner is offline
Forum Moderator

 
Registration Date: Apr 2002
Location: Greater Milwaukee area, Wisconsin
 
Posts: 3,507
Thanks Given to Others: 603
Thanked 2,044 Times in 1,300 Posts
Blog Entries: 16
Karma Power: 438
Karma: 18664
Miner is appreciated, and has over 1700 Karma points.Miner is appreciated, and has over 1700 Karma points.
Miner is appreciated, and has over 1700 Karma points.Miner is appreciated, and has over 1700 Karma points.Miner is appreciated, and has over 1700 Karma points.Miner is appreciated, and has over 1700 Karma points.Miner is appreciated, and has over 1700 Karma points.Miner is appreciated, and has over 1700 Karma points.
Quote:
In Reply to Parent Post by patric wessels

Dear all,

I am not sure if this is the right forum for this subject, but here's the question:

We are trying to assist our operators in determining whether a measured point is an outlier or not. We want to use the Grubbs test for this purpose. The problem is that in case of a large sample we measure 120 points and the tables with the Z-values (for 99% probability) only goes up to 25 samples points.

I am not an expert in statistics but I am sure there is a reason for this.

Can anyone help me out and explain why there are no Z-values for N>25?

Thanks.

Best regards,

Patric Wessels
QA Engineer
Unless I am misunderstanding your question, a z-table does not depend on sample size. You enter the table using a given z-value and obtain a p-value as an output.

The sample size does come into play when calculating the z-value. See http://www.changbioscience.com/stat/ztest.html for an online z calculator.

Are you sure that you want the z-value? The NIST guide (http://www.itl.nist.gov/div898/handb...on3/eda35h.htm ) shows that the t-value is used for Grubb's test.

__________________

"A fool can learn from his own experiences; the wise learn from the experience of others." - Democritus, 460-370 B.C.
Sponsored Links

  #3  
Old 1st February 2006, 03:02 PM
Tim Folkerts's Avatar
Tim Folkerts Tim Folkerts is offline
Super Moderator

 
Registration Date: Sep 2003
Location: Kansas, USA
Age: 51
 
Posts: 975
Thanks Given to Others: 29
Thanked 366 Times in 218 Posts
Karma Power: 153
Karma: 5879
Tim Folkerts is appreciated, and has over 1700 Karma points.
Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.
I found this table on line that goes up to N = 140. They claim it is for 95% certainty. I tried pasting it here, but it doesn't copy well.
http://www.graphpad.com/articles/grubbs.htm

Also, the NIST Statistics site mentioned on another thread recently has a discussion of Grubbs Test and the formula for calculating the "Critical Z"
http://www.itl.nist.gov/div898/handb...on3/eda35h.htm


I was curious, so I tried a spreadsheet to calculate this, which is attached. You can adjust the alpha level to whatever you want. By playing with the alpha value, I was able to reproduce the table at the first link, so that is pretty good assurance that the calculations are correct. (I included a variety o values for N from 3-1000. For other values you could either estimate between nearby values or just type the number you want in the first column somewhere).

For those, like me, who were rusty on the Grubbs test, basically you calculate the critical value in the table. Then any point more than that many standard deviations from the center is a likely outlier. For example, at N=6 and alpha=0.01, then Z = 2.0; so any point in a set of N=6 that is more than 2.0 standard deviations from the mean is likely an outlier.


Tim F
Attached Files: 1. Scan for viruses before using, 2. Please report any 'bad' files by Reporting this post, 3. Use at your Own Risk.
File Type: xls Grubbs Test.xls (30.0 KB, 532 views)

__________________

To wonder is to begin to understand.

Last edited by Tim Folkerts; 1st February 2006 at 03:08 PM.
Thanks to Tim Folkerts for your informative Post and/or Attachment!
  #4  
Old 1st February 2006, 03:10 PM
Tim Folkerts's Avatar
Tim Folkerts Tim Folkerts is offline
Super Moderator

 
Registration Date: Sep 2003
Location: Kansas, USA
Age: 51
 
Posts: 975
Thanks Given to Others: 29
Thanked 366 Times in 218 Posts
Karma Power: 153
Karma: 5879
Tim Folkerts is appreciated, and has over 1700 Karma points.
Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.Tim Folkerts is appreciated, and has over 1700 Karma points.
One other side note, some sites seem to call the parameter of interest "Z", others "G", and others "Y". That might be part of the confusion. The "Critical Z" here is not the same thing as the "Z" from the normal distribution tables.

Tim F

__________________

To wonder is to begin to understand.
  #5  
Old 5th February 2006, 03:23 PM
Statistical Steven's Avatar
Statistical Steven Statistical Steven is offline
Statistician

 
Registration Date: May 2005
Location: New Jersey
Age: 49
 
Posts: 974
Thanks Given to Others: 240
Thanked 362 Times in 252 Posts
Karma Power: 143
Karma: 4239
Statistical Steven is appreciated, and has over 1700 Karma points.
Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.Statistical Steven is appreciated, and has over 1700 Karma points.
Send a message via Yahoo to Statistical Steven
Quote:
In Reply to Parent Post by Tim Folkerts

One other side note, some sites seem to call the parameter of interest "Z", others "G", and others "Y". That might be part of the confusion. The "Critical Z" here is not the same thing as the "Z" from the normal distribution tables.

Tim F
Look into the ESD method.

__________________

Steven Walfish
When in doubt, ask your company statistician!
  #6  
Old 7th February 2006, 07:08 AM
patric wessels's Avatar
patric wessels patric wessels is offline
Involved - Posts

 
Registration Date: May 2004
Location: Netherlands
Age: 50
 
Posts: 22
Thanks Given to Others: 0
Thanked 0 Times in 0 Posts
Karma Power: 44
Karma: 10
patric wessels has less than 100 Karma points so far.
Dear All,

Thank you for your contribution to my question. Especially the excel sheet was very helpfull. I think I have a solution for my problem now.

Best regards,

Patric
  #7  
Old 14th August 2009, 02:47 PM
Campy Campy is offline
Inactive Registered Visitor

 
Registration Date: Aug 2009
Location: Ind
 
Posts: 2
Thanks Given to Others: 1
Thanked 1 Time in 1 Post
Karma Power: 21
Karma: 15
Campy has less than 100 Karma points so far.
Re: Grubbs Test for Outliers and Why there are no Z-values for N>25

Note also that ASTM E 178-08: Standard Practice for Dealing with Outlying Observations presents Grubb's test as one method of detecting outliers. Its table goes to n=147 for six different levels of alpha.
Reply

Lower Navigation Bar
Go Back   The Elsmar Cove Forum > Manufacturing, Service, and Business Systems Processes > Reliability Analysis - Predictions, Testing and Standards

Do you find this discussion thread helpful and informational?


Bookmarks


Visitors Currently Viewing this Thread: 1 (0 Registered Visitors (Members) and 1 Unregistered Guest Visitors)
 
Thread Tools Search this Thread
Search this Thread:

Advanced Forum Search
Display Modes Rate Thread Content
Rate Thread Content:

Forum Posting Settings
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off


Similar Discussion Threads
Discussion Thread Title Thread Starter Forum Replies Last Post or Poll Vote
Hampel's Test for Outliers and Swed Eisenhart Run Test gcpa81 Capability, Accuracy and Stability - Process, Machine, etc. 3 30th December 2011 05:27 PM
Z-values in Logistic Regression stem from a Wald test? Wicked Using Minitab Software 7 28th April 2010 02:02 PM
Grubbs test to determine one outlier to normalize data Benoit Statistical Analysis Tools, Techniques and SPC 4 17th August 2009 08:23 AM
Hampel Test for Outliers and how it differs from a Grubbs Test for Outliers SteveL Statistical Analysis Tools, Techniques and SPC 5 22nd November 2007 10:20 AM
Reporting As Found data - Actual before values or test points necessary? Charles Wathen ISO 17025 and related Metrology Topics - Measurement Devices, Calibration and Test Laboratories 2 16th March 2007 12:06 PM



The time now is 07:42 PM. All times are GMT -4.
Your time zone can be changed in your UserCP --> Options.


   


Marc Timothy Smith - Elsmar.com
8466 LeSourdsville-West Chester Road, Olde West Chester, Ohio 45069-1929
513 341-6272
NOTE: This forum uses "cookies".