The Elsmar Cove Business Standards Discussion Forums More Free Files Forum Discussion Thread Post Attachments Listing Elsmar Cove Discussion Forums Main Page
Welcome to what was The Original Cayman Cove Forums!
This thread is carried over and continued in the Current Elsmar Cove Forums

Search the Elsmar Cove!

Wooden Line
This is a "Frozen" Legacy Forum.
Most links on this page do NOT work.
Discussions since 2001 are HERE

Owl Line

The New Elsmar Cove Forums   The New Elsmar Cove ForumsThe Elsmar Cove Forums
  Statistical Techniques and 6 Sigma
  Uncertainity & Student's T distribution

Post New Topic  Post A Reply
profile | register | preferences | faq

UBBFriend: Email This Page to Someone! next newest topic | next oldest topic
Author Topic:   Uncertainity & Student's T distribution
sergiop
Lurker (<10 Posts)

Posts: 1
From:Argentina!!!!
Registered: Aug 2001

posted 07 August 2001 02:18 PM     Click Here to See the Profile for sergiop   Click Here to Email sergiop     Edit/Delete Message   Reply w/Quote
Hi! I'm trying to introduce calculus of uncertainity in my calibration procedures, but I'm not sure of what value of F (based on the Student's T distribution a number of degrees of freedom) must use:

S1 = (SDEV / (N ^ 0.5)) * F

I have a table (Guide to Expression of Uncertainty in Measurements), but reading some paper (Implementing ISO 17025 Measurement Uncertainity Requeriments in Software, Matt Nicholas, Fluke Corporation), they use half the values shown in the 95.45% column of the table

What must I use? Entire value or half value of F to 95.45%??

Thanks

------------------
Sergioasdf

IP: Logged

KenK
Forum Contributor

Posts: 16
From:Northbrook, IL, USA
Registered: Jul 2001

posted 09 August 2001 11:46 AM     Click Here to See the Profile for KenK     Edit/Delete Message   Reply w/Quote
I not sure I understand exactly what you are doing or what you want to do.

I'm guessing you have calculated a mean, and want to provide a confidence interval - a measure of uncertainty.

If that's the case, then the formula's are pretty simple:

95% confidence interval:

mean +/- t[0.025,n-1]*stdev/SQRT(n-1)

where t[0.025,n-1] is a t-value taken from a t-table. Sematech/NIST has a table at
http://www.itl.nist.gov/div898/handbook/eda/section3/eda3672.htm

Find the column with 0.025 as the header and find n-1 in the first column.

If you're trying to do something else, please let us know.

IP: Logged

All times are Eastern Standard Time (USA)

next newest topic | next oldest topic

Administrative Options: Close Topic | Archive/Move | Delete Topic
Post New Topic  Post A Reply
Hop to:

Contact Marc Smith | The Elsmar Cove Home Page

Please Visit the new Elsmar Cove Forums! All these threads are there and much more!

Main Site Search
Y'All Come Back Now, Ya Hear?
Powered by FreeBSD!Made With A Mac!Powered by Apache!