Accuracy vs. Precision

Carl:

Ok, here is what NIST (National Institute of Standards and Technology) has to say about it, and I would tend to put more faith in their interpretation than other Usenet sources.

====================================================================

D.1.1.1 accuracy of measurement [VIM 3.5] closeness of the agreement between the result of a measurement and the value of the measurand

NOTE "Accuracy" is a qualitative concept.

The term "precision" should not be used for "accuracy."

TN 1297 Comments:

1. The phrase "a true value of the measurand" (or sometimes simply "a true value"), which is used in the VIM definition of this and other terms, has been replaced here and elsewhere with the phrase "the value of the measurand." This has been done to reflect the view of the Guide, which we share, that "a true value of a measurand" is simply the value of the measurand. (See subclause D.3.5 of the Guide for further discussion.)

1. Because "accuracy" is a qualitative concept, one should not use it quantitatively, that is, associate numbers with it; numbers should be associated with measures of uncertainty instead. Thus one may write "the standard uncertainty is 2 µ?" but not "the accuracy is 2 µ?."

2. The VIM does not give a definition for "precision" because of the many definitions that exist for this word. For a discussion of precision, see subsection D.1.2.

D.1.1.2 repeatability (of results of measurements) [VIM 3.6] closeness of the agreement between the results of successive measurements of the same measurand carried out under the same conditions of measurement.

D.1.1.3 reproducibility (of results of measurements) [VIM 3.7] closeness of the agreement between the results of measurements of the same measurand carried out under changed conditions of measurement

D.1.2 As indicated in subsection D.1.1.1, TN 1297 comment 4, the VIM does not give a definition for the word "precision." However, ISO

3534-1 [D.2] defines precision to mean "the closeness of agreement between independent test results obtained under stipulated conditions." Further, it views the concept of precision as encompassing both repeatability and reproducibility (see subsections D.1.1.2 and D.1.1.3) since it defines repeatability as "precision under repeatability conditions," and reproducibility as "precision under reproducibility conditions." Nevertheless, precision is often taken to mean simply repeatability. ====================================================================

Note the very last sentence.

======== In the context of improvised live tooling would this news item be of any help?

Unka' George [George McDuffee]

------------------------------------------- He that will not apply new remedies, must expect new evils: for Time is the greatest innovator: and if Time, of course, alter things to the worse, and wisdom and counsel shall not alter them to the better, what shall be the end?

Francis Bacon (1561-1626), English philosopher, essayist, statesman. Essays, "Of Innovations" (1597-1625).

Unka George:

We got some serious thread drift here. Let me get it back to metalworking - well at least with using a metalworking device - a belt sander.

Was it in here I saw the story about someone masturbating by using the friction of the inside nonabrasive side of a belt sander and had an orgasm which jerked him toward the belt more and got his testicles caught between the belt and roller and flipped him across the room? Then he (being the tough machinist he was and embarrassed too) he stapled his scrotum together and went back to work. When he got a major infection and finally went to emergency the doctor had to remove the rusty staples and then found out there was one testicle missing.

I'd pretty much call that "dead nuts", or rather a singular dead nut.

I would have to say that there are exceptions to this -- not because of style, but because of the possible significance of a period if it is taken to be literal.

If you are quoting something which should be entered into a field in a computer program -- for example a URL -- you want *all* punctuation which is not a part of that URL (or other something) to be outside the quote marks -- to prevent accidentally entering the period as part of the field. I don't know whether the latest edition of the document in question makes that exception -- but if it does not, it should. Even worse are things like question marks, which can be treated as wildcards making the actual entry rather unpredictable. :-)

Please not when quoting URLs or other input data to computer programs.

:-)

Enjoy, DoN.

[ ... ]

It was not a sanding belt, but rather a belt driven machine tool (from overhead lineshafts with long leather drive belts) -- probably a lathe, though other machine tools might put the belt more within reach.. The rest is pretty close.

And yes, I have seen it here -- and various other places too. I think even in Snopes' urban legend site.

Here it is -- and it is marked as true:

Enjoy, DoN.

You didn't think I was going to say mine did you? Hehe.

DoN:

Why the capital "N" at the end of your first name?

Anyway, your point above certainly wasn't covered in the punctuation and style guide, but it was a 1995 edition.

The British don't don't put the period inside the quotation marks. Here's a little historical excerpt of the reason why Americans feel it belongs inside the quotation marks.

======================================================================== And just why, you may ask, do they belong there? Well, it seems to be the result of historical accident. When type was handset, a period or comma outside of quotation marks at the end of a sentence tended to get knocked out of position, so the printers tucked the little devils inside the quotation marks to keep them safe and out of trouble. But apparently only American printers were more attached to convenience than logic, since British printers continued to risk the misalignment of their periods and commas. ========================================================================

I dont reply to your posts..because frankly...most of them are WAY over my head, on things I dont know anything about. Cad/Cam etc etc

Dont have a clue how to use a Cad/Cam program. Shrug...Ive got several..but still dont know how to use em.

Im a service tech, not a machiniest. I can turn cranks pretty well...but CNC, except for lathes such as the OmniTurn, is out of my league for setup/programming etc.

So I keep my mouth shut and leave it to the pros, and try to soak up as much as I can.

Gunner

Hairy Balls on an old, ugly, fat man, with no money.

Tom

Accuracy refers to the closeness between measurements (observations) and their expectations ("true" values). The farther a measurement is from its expected value, the less accurate it is.

Precision:

Precision pertains to the closeness to one another of a set of repeated observations of a random variable. Thus, if such observations are closely clustered together, then these observations are considered to have been obtained with high precision.

Well, from subsequent comments, that may be good English, but to us Yobbo high school graduates, it requires too much thought to comprehend.

From my (admittedly limited) engineering trade lessons, what I was taught was

Accuracy - the ability to measure or layout to the tolerances needed for the job. Precision - the ability to be able to work to those measurements and tolerances.

Andrew VK3BFA

I think of it like shooting a gun. To hit the target takes accuracy. To hit the target every freaking time takes precision.

Unfortunately, I have seen these two terms misused even in advertising for otherwise good products. I think firms for which these terms are important ought to have technical people approve their ads, but I guess that is too much to hope for in today's business world.

And here I thought that the target illustration in BottleBob's first post was clear and self-explanatory!

I'd used that analogy in my work measurement class and the students seemed to grasp the idea.

Silly 'ol me!

Wolfgang

It started a *long* time ago, when a teacher told of one person in the (rather small) town whose name was "H. B. ", but who was in the habit of making his periods as small circles, so he became known as "Hobo ".

Combine that with the fact that my initials, if written with an open period for the first one, and a closed one for the second one spells the short form of my first name. So -- I got into the habit of writing my initials in that form, and over years of having to initial security containers (I worked for an Army R&D lab for most of my working life) I got so accustomed to doing that that I kept it going with computer operations as well -- except that I could not make the 'o' as small as I would like to make it clearer.

And I don't know whether a more recent edition takes this into consideration or not. I suspect not. :-)

Interesting.

Any clue to the origin of the difference in number formats between the UK and the US? Two that I can think of are:

1) We write a large number with commas breaking it into groups of three digits and periods separating the integers from the decimal fractional part.

The UK interchanges those two usages.

US UK 200,000.00 200.000,00

2) The significance of the words for larger numbers is quite different once you get past a million:

TERM US UK million 1,000,000 1.000.000 billion 1,000,000,000 1.000.000.000.000 trillion 1,000,000,000,000 1.000.000.000.000.000.000

I actually think that the UK pattern makes more sense, as each increment multiplies the number of zeros in a million by the number in the prefix. But this is why you will hear the UK residents speak of "a thousand million", while the in the US, we would say "a billion" with no need for the "a thousand" part.

Enjoy, DoN.

maybe my memory is fading, but I seem to recall, back in the good old days of slide rules, that we used the word "precision" to mean "Resolutoin" as you define it - I tend to think of resolution as something lenses have, not micrometers, but I can be comfortable with it meaning "precision"

** Posted from **

DoN:

Thanks for that little bit of personal history. I wonder if I can adapt that to my online handle "BB", and turn it into "BoB". Hmmmmm, somehow it just doesn't seem to have the same effect.

I don't know about the origin of that, but a lot of foreign countries seem to do it (countries other than America), I keep forgetting I'm cross posting to rcm a more cosmopolitan group. Personally, it's irritating. When I, on rare occasions, get German or foreign prints that have commas where the periods are normally, and vice versa, I just overwrite them with a pen so I don't accidentally make a mistake.

===========================================================================

Long and short scales

The long and short scales are two different numerical systems used throughout the world:

Short scale is the English translation of the French term échelle courte. It refers to a system of numeric names in which every new term greater than million is 1,000 times the previous term: "billion" means "a thousand millions", "trillion" means "a thousand billions", and so on.

Long scale is the English translation of the French term échelle longue. It refers to a system of numeric names in which every new term greater than million is 1,000,000 times the previous term: "billion" means "a million millions", "trillion" means "a million billions", and so on.

For most of the 19th and 20th centuries, the United Kingdom uniformly used the long scale, while the United States of America used the short scale, so that usage of the two systems was often referred to as "British" and "American" respectively. In 1974 the government of the UK abandoned the long scale, so that the UK now applies the short scale interpretation exclusively in mass media and official usage. Although some residual usage of the long scale continues in the UK, the phrases "British usage" and "American usage" are no longer accurate or helpful characterizations. The two systems can be a subject of controversy and can arouse emotion. Usage changes can evoke resentment in adherents to the older system, while national differences of any kind can acquire patriotic overtones. ===========================================================================

There are plenty of other numerical ambiguities throughout the world, and that's not even counting metrification. You'd think the powers that be would have all those discrepancies worked out by now.

B°B ? Can't find a subscript version of that char.

Wayne...

Wayne:

Hey, that's pretty cute.

One other thing, for some reason Thunderbird automatically stripped off the (was: Re: Accuracy vs. Precision), I've never know it to do that before. Must be something to do the combination of opening parenthesis and the two colons.