The Elsmar Cove Business Systems and Standards Discussion Forums Gage R&R (Ranges Method) - Reproducibility standard deviation
 Forum User Name Keep Me Logged In Password
 Register Photo Albums Blogs FAQ Registered Visitors Social Groups Calendar Search Today's Posts Mark Forums Read

 Elsmar Cove Forum Visitor Notice(s) Some people have been having Password Reset issues (especially "Hotmail" accounts). If you have a problem, contact the Peachfarm Internet Properties IT techs directly at peachfarmllc {at} neomailbox.ch (Switzerland) and we will resolve your problem(s) within 12 hours.

# Gage R&R (Ranges Method) - Reproducibility standard deviation

 Elsmar XML RSS Feed Monitor the Elsmar Forum Sponsor Links Courtesy Quick Links Links that Cove visitors will find useful in your quest for knowledge: International Standards Bodies - World Wide Standards Bodies ASQ - American Society for Quality International Standards Organization - ISO Standards and Information Howard'sInternational Quality Services Marcelo Antunes'SQR Consulting, andMedical Devices Expert Forum Bob DoeringBob Doering's Blogs and,Correct SPC - Precision Machining NIST's Engineering Statistics Handbook IRCA - International Register of Certified Auditors SAE - Society of Automotive Engineers Quality Digest IEST - Institute of Environmental Sciences and Technology
Post Number #1
17th October 2003, 12:25 PM
 Martin Kies Total Posts: 1
Gage R&R (Ranges Method) - Reproducibility standard deviation

I have an XL spreadsheet that someone forwarded me with the following details:

3 Operators
10 samples
3 trials

Operator A average (30 measurements) is 5.481
Operator B average (30 measurements) is 5.471
Operator C average (30 measurements) is 5.507

To get the reproducibility standard deviation, the following is used:

= (5.507 - 5.471) * 0.524

Question: where does the 0.524 come from? Actually, the full formula in the cell is a nested IF statement (if the operator sample averages were only 2 instead of 3, the constant would be 0.709), but I have shortened this for simplicity.

I have checked the usual SPC table of constants (A2, D4, d2, etc), but could not find where this one came from. I even tried some reciprocals of these constants to no avail.

Any help in where these came from would help, along with a table of this constant.

Thanks to anyone in advance who replies.

Martin

Post Number #2
17th October 2003, 12:49 PM
 ben sortin Total Posts: 59
"Spreadsheet that someone forwarded me" is the root cause of your problem. I wouldn't let Euclid forward me a spreadsheet without the algorithm(s).
Post Number #3
25th October 2003, 03:52 AM
 Atul Khandekar Total Posts: 1,457
Quote:
 In Reply to Parent Post by Martin Kies To get the reproducibility standard deviation, the following is used: = (5.507 - 5.471) * 0.524 Question: where does the 0.524 come from? I have checked the usual SPC table of constants (A2, D4, d2, etc), but could not find where this one came from. I even tried some reciprocals of these constants to no avail. Any help in where these came from would help, along with a table of this constant.
Martin,
First off, Welcome to the Cove!

I would suggest you get hold of the AIAG MSA Manual - third edition, where R&R procedures, formulas and constants are explained. ( http://www.aiag.org )

Appraiser Variation (AV) or reproducibility is calculated by dividing the range of appraiser averages by a constant d2*. K2 is the inverse of d2*. The manual gives the complete table for d2*.

AV = XBar_Diff *K2
K2 = 1 / d2*

For 2 operators: d2*= 1.41421; K2= 0.7071
For 3 operators: d2*= 1.91155; K2= 0.5231

The formula you have given appears incomplete. The reproducibility value obtained as above has to be adjusted to remove the 'contamination' by Equipment Variation (EV), because taking the appraiser averages does not completely isolate AV & EV. The complete formula is:

AV = Sqrt( (XBar_Diff *K2)^2 - (EV^2/nr) ), where
n = No of Samples
r = No of Trials

Hope this helps..

-Atul.
Post Number #4
28th October 2003, 04:53 AM
 candy_hy Total Posts: n/a

Sometimes I've use 1 operator in GR&R, But it's difficut to find these factor for 1 operator, m Samples and n Trials.

Please tell me how to get these factors?

Thank you.
Post Number #5
28th October 2003, 06:54 AM
 Atul Khandekar Total Posts: 1,457
Quote:
 In Reply to Parent Post by candy_hy Sometimes I've use 1 operator in GR&R, But it's difficut to find these factor for 1 operator, m Samples and n Trials. Please tell me how to get these factors?
candy_hy,

Welcome to the Cove Forums.

Reproducibility can be calculated only when you have more than one operator in a GRR study. For one operator, AV=0. So there should be no need to find out the value of K2 factor - its not given in the AIAG manual.

Also see: R&R study with one appraiser

Hope this helps.

- Atul.

 The Elsmar Cove Business Systems and Standards Discussion Forums Gage R&R (Ranges Method) - Reproducibility standard deviation

 Bookmarks

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

 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 Forum Rules

 Similar Discussion Threads Discussion Thread Title Thread Starter Forum Replies Last Post or Poll Vote Berg.Jlle Using Minitab Software 6 20th June 2012 01:01 PM rderoeck - 2006 Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 12 8th July 2011 04:35 AM Jim Thomson Using Minitab Software 5 8th May 2006 07:36 AM Rob Nix Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 13 30th December 2005 10:41 AM Benoit Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 2 22nd October 2002 10:44 AM

The time now is 01:03 PM. All times are GMT -4.