uncertainty budget excel

[Irv1n]

can u help me with 1 question. I calibrate dmm (fluke 8508, agilent 3458) from 100 mV to 10V on my josephson voltage standard. And have result:
gain factor (example 1.00035 from -10 to 10V) and mean square error (example 23 nV). How i can use this results? how i can calcultae voltage for point like 3 V? How calculate uncertainty with this values?

[RFCAL]

Wow!! You need more help than I can give you!

[CalLabSolutions]

We have MET/CAL procedures available for both the HP 3458A and Fluke 8508A each with full uncertainty budgets based on the customer's standards. 
Irv1n, I'm sure we can help you with your uncertainty problem, but I need to know all the details about your test setup methodology.
You can shoot me an E-mail MSchwartz@CalLabSolutions.com
Mike

[Irv1n]

We have MET/CAL procedures available for both the HP 3458A and Fluke 8508A each with full uncertainty budgets based on the customer's standards. 
Irv1n, I'm sure we can help you with your uncertainty problem, but I need to know all the details about your test setup methodology.
You can shoot me an E-mail MSchwartz@CalLabSolutions.com
Mike

Okey tomorrow i give more info about this calibration.

Can anyone say, what program use Fluke for creating Calibration certificate? Metcal or excel?
If u know or have example of certificate can u say what fonts and size they used?

[Irv1n]

Can anyone say, how i can verify 3458a for 90day option 002?

[briansalomon]

For what it's worth I have been using Integrated Sciences Group "Uncertainty Analyzer" software. It took me about 4 months to go through the working exercises and I used actual instruments with their certificates of calibration. This worked. I now understand the basics and recognize the scope of what I do not.

For proficiency testing, I asked one of the proficiency testing providers if he really needed a "full blown" estimate of uncertainty and he gave me an excellent tool for on-the-spot uncertainty estimates.
1 - Square the tolerance of the UUT.
2 - Square the tolerance of the standard(s)
3 - Take 5 repeatability measurements, find the standard deviation, find the mean and square that.
4 - Add these together.
5 - Take the square root of that.
This estimate of uncertainty will be in the ballpark and will be useful but of course will not be what an ISO auditor is looking for.

Statistics and math are not my domain. I welcome any corrections to what I have added here.

[N79]

Yes, that will give you an estimated uncertainty. There is a somewhat tricky part before using your method in that you need to normalize your tolerances. Tricky because a lot of manufacturers do not specifically state what sort of confidence level or statistical distribution their specifications adhere to.

Fluke is somewhat good about this as they list specifications at the 95% (and 99%) confidence level but they also reference these same specifications as "approximately 95%" which should raise the eyebrows of anyone who knows the difference between the two statements. But compared to other manufacturers at least they give you something to work with.

Anyway, depending on if you know how your standard's tolerance is reported (whether K = 2, K = 3, 95%, 99%, 99.7%, etc.), you would simply divide your reported tolerance by a certain factor. If you can't find this information, it is recommended that you assume it has a uniform distribution and you can divide the standard tolerance by sqrt(3) or 1.732. This normalizes the spec so you can combine it with your standard deviation of repeated measurements.

It is arguable whether or not to include your UUT tolerance in your calculation. I typically don't, but maybe you have a good reason to.

[CalibratorJ]

... but they also reference these same specifications as "approximately 95%" which should raise the eyebrows of anyone who knows the difference between the two statements. But compared to other manufacturers at least they give you something to work with.
...It is arguable whether or not to include your UUT tolerance in your calculation. I typically don't, but maybe you have a good reason to.

Approximately 95% is K=2 (94 or 95.something is actually K=2, can't be bothered to find the exact number, it is Saturday night after all). It should raise some eyebrows if they don't state approximately 95%......

If it is your measurement uncertainty, the only thing from your UUT you should be using is the resolution, iirc - depending on the type of UUT of course.

[N79]

Approximately 95% is K=2 (94 or 95.something is actually K=2, can't be bothered to find the exact number, it is Saturday night after all). It should raise some eyebrows if they don't state approximately 95%......

There is a (albeit slight) difference between K = 2 and a 95% CL, and they shouldn't be interchanged. If Fluke is going to list specifications at 95%, they shouldn't later refer to it as approximately 95%. They should list them as 2σ or K = 2, but not 95%. Also listing 99% specs just makes it even more confusing because if one assumes 95% is K = 2, then 99% must really be K = 3 which is quite a bit different than a 99% CL.

[briansalomon]

Yes, I can see that the confidence factor(s) of the tolerances do have to be accounted for. I will make a note of this.

I grasp that the standards used to certify an instrument are a major contributor to the uncertainty of a measurement and had assumed the tolerance of the UUT was also part of this.


I sat in a couple of Measurement Science Conference workshops on uncertainty and gaurdbanding and the certificates look nice but most of what I actually understand about uncertainty is self taught.

The last ISO auditor we had mentioned Quametec and I have heard Excel mentioned. Is there any "industry standard" software that most accredited labs are using to report uncertainty?

[BamaKid]

I bought the book 'Statistics for Dummies' to better understand measurement uncertainty and its principles.

Standard Deviation 2 = 95.45% [If you use 95% you are at a K factor of 1.96; perhaps close enough]

Standard Deviation 3 = 99.73% [If you use 99% you are at a K factor of 2.58; not close enough]

[Irv1n]

How i can calculate stability (12 MONTH) of DC Voltage if i have calibration between 1 and 2: near 1 year 9 month?
(1 - 2)/ 1.9 ? What document describe this calculation? Thank You.

[RFCAL]

Irvin--you need formal training for uncertainty budgets. You need more help than anyone on this site can give you.Self taught is OK for some budgets, but not for the questions you are asking. You can take classes from NIST or the NCSLI or MSC conferences. After that, go to quametec.com and take their software classes.

[sbdata2009]

Here's an excellent resource:

http://www.isobudgets.com/