and to how many decimal places?

[fumei]

Just read some text that mentioned a "precise estimation".

Hmmmmm.

I can understand an estimation being as precise as possible, but a precise estimation?

However, I found one definition to be - "conforming strictly to rule or proper form". So if a protocol can only return an estimation, if one follows, strictly, the forms and rules of the procedure, can it really be called precise?

Gerry
My paintings and sculpture

 

[fumei]

And it IS fun...never mind what Jenny feels about it.

So...really...just to confirm. My original quiver about "precise estimate" is correct? Because precise is process, accuracy is result, then - because the estimate IS the result, it really should be "accurate estimate". Right?

Never mind any "subjective" (and I agree it is not subjective) aspect. Never mind what would have been acceptable - and let's face it, standing around at 17,000 feet in high wind would make ANYONE alter what is "acceptable"; ie. yeah, yeah...whatever...looks good enough for me...let's get the hell OUT of here. I know, I have hiked to 19,600 (...hmmmm...approximately) feet in the Himalayas, and really...unless you are one of those peculiar people who LIKE gasping for breath, you just want to keep moving.

Gerry
My paintings and sculpture

 

[Gooser]

[Lifts trap door, drops flash-bang down hole, backs away.]

Precise estimate, pretty much any way you look at it, is a poor choice of words. 'Accurate' would have made for more precise speech.

v/r

Gooser

Why do today
that which may not need to be done tomorrow --me

 

[Lunatic]

Wow, I'm getting really confused.

Precision - isn't this a way of defining if the measurement is descriptive enough for your use.

For example if you were building a cabinet, you wouldn't want to use measurements of 'about 3 inches' because it would not be precise enough - being off by as little as 3/16ths of an inch could really distort the final appearence of the cabinet.

So in this example 'about 3 inches' isn't precise because it does not describe the absolute measurement in enough detail?

****

Accuracy seems much more basic to me, its whether or not you can measure. Accuracy defines the reliability of your measurement.

****

So Precision describes measure how 'good' the measurement is; and
Accuracy describes how reliable the measurement is at the level of precision you used to measure it.

****

So in terms of statistics, Precision would be the result (e.g. 7 out of 10) and accuracy would be the quality of the measurement (+/- 1 with a 95% degree of certainty)

****

Am I understanding what is being said here or am I way off?

 

[Scott24x7]

The recap:

Precision - About the Process
Accuracy - About the Outcome

Therefore, the Precise Estimate is the correct terminology, no matter how funky it looks.

Accurate Estimate - Suggests that it would in fact not be an estimate at all, but a fact. I can look at a bucket and to some degree of precision say, "That bucket can hold 980ml of liquid". If I knew the exact dimensions, and had the ability to calculate volume, I could accurately state, "It can hold 982.33337ml of water at 32degrees Celsius."


Best Regards,
Scott

"Everything should be made as simple as possible, and no simpler."

 

[CajunCenturion]

Precision - About the Process
Accuracy - About the Outcome

Therefore, the Precise Estimate is the correct terminology, no matter how funky it looks.

Is the "estimate", the process or the outcome?

--------------
Good Luck
To get the most from your Tek-Tips experience, please read FAQ181-2886
As a circle of light increases so does the circumference of darkness around it. - Albert Einstein

 

[Scott24x7]

The two words are not to be taken in isolation in this case. And so, "Precise Estimate" is the process.


Best Regards,
Scott

"Everything should be made as simple as possible, and no simpler."

 

[sbudzynski]

hear hear

----------

Steve Budzynski


"So, pass another round around for the kids. Who have nothing left to lose and for those souls old and sold out by the soles of my shoes"

 

[CajunCenturion]

==> The two words are not to be taken in isolation in this case.
Then the result is ambiguity.

--------------
Good Luck
To get the most from your Tek-Tips experience, please read FAQ181-2886
As a circle of light increases so does the circumference of darkness around it. - Albert Einstein

 

[Gooser]

I still would like to have more context on this too. Like the whole paragraph it is in, the one before, and the one after. Might make more sense in context.



v/r

Gooser

Why do today
that which may not need to be done tomorrow --me

 

[fumei]

Precision - About the Process
Accuracy - About the Outcome

Therefore, the Precise Estimate is the correct terminology, no matter how funky it looks.

Huh? Get real.

The estimate is the result. "This pass is at an estimated 17,100 feet." The estimate is what you are saying is the result.

Gerry
My paintings and sculpture

 

[sbudzynski]

I don't understand what the difficulty here is...I must be completely confused..

I think of this as a formula like I stated before

If you have a formula that guesses future growth based on past growth history then that is an estimate. The further back in history you collect your data then the more precise the estimate. The accuracy cannot be known until the event occurs.

Just because an estimate is more or less precise does not mean the outcome of that estimate will be accurate (since it is still an estimate). If you look at my example of future growth then you can see the difference between estimate and outcome. Precision has to do with the estimate whereas accuracy has to do with the outcome.

Scott makes complete sense to me...

----------

Steve Budzynski


"So, pass another round around for the kids. Who have nothing left to lose and for those souls old and sold out by the soles of my shoes"

 

[CajunCenturion]

If you have a formula that guesses future growth based on past growth history then that is an estimate. The further back in history you collect your data then the more precise the estimate.

The further back in history you collect your data then the more precise the formula or dataset, or if you will, and in terms of the MW dictionary, the more refined is your operation.

That hopefully results in a more accurate estimate, or again in terms of the dictionary definition, an estimate closer to the actual value.

--------------
Good Luck
To get the most from your Tek-Tips experience, please read FAQ181-2886
As a circle of light increases so does the circumference of darkness around it. - Albert Einstein

 

[sbudzynski]

The further back in history you collect your data then the more precise the formula

In my understanding the formula is the estimate. Which absolutely results in a more precise estimate and hopefully a more accurate estimate.

----------

Steve Budzynski


"So, pass another round around for the kids. Who have nothing left to lose and for those souls old and sold out by the soles of my shoes"

 

[CajunCenturion]

==> In my understanding the formula is the estimate.

That's where we differ. The formula is not the estimate. The answer is the estimate. The formula is the process used to determine the estimate.

A more precise formula should allow for a more accurate estimate.

--------------
Good Luck
To get the most from your Tek-Tips experience, please read FAQ181-2886
As a circle of light increases so does the circumference of darkness around it. - Albert Einstein

 

[sbudzynski]

A more precise formula will allow for a more precise estimate.

Accuracy cannot be known until the sales have incurred. It is not an accurate estimate until the data is collected. The estimate will be more precise but sales could be way off therefore the estimate is not accurate.

A more precise formula should allow for a more accurate estimate.

A more precise formula will allow for a more precise estimate.

----------

Steve Budzynski


"So, pass another round around for the kids. Who have nothing left to lose and for those souls old and sold out by the soles of my shoes"

 

[CajunCenturion]

==> A more precise formula will allow for a more precise estimate.
More precise than what? Once you introduce the comparative (more), then you're introducing a new process (a comparison), and a second estimated value. You cannot have one estimate more precise than other unless you have two estimates to compare, and a scale to compare them against.

Again, you cannot have precision without a process. An estimate, in and of iteslf, is simply a value. You can talk about precision in how you arrive (calculation process) at the value, or when comparing that value against some arbitrary scale (comparison process), but with respect to the estimate itself, it has no precision. It's simply a value.

--------------
Good Luck
To get the most from your Tek-Tips experience, please read FAQ181-2886
As a circle of light increases so does the circumference of darkness around it. - Albert Einstein

 

[Gooser]

A value can have precision! 1.0 is less precise than 1.0000

That is all I have to say about that.

--Gooser

 

[sbudzynski]

More precise then what?
Formula 1 - Future sales growth using data from last month
Formula 2 - Future sales growth using data from 10 years ago to the present.


Again, you cannot have precision without a process. An estimate, in and of iteslf, is simply a value. You can talk about precision in how you arrive (calculation process) at the value, or when comparing that value against some arbitrary scale (comparison process), but with respect to the estimate itself, it has no precision. It's simply a value.

This is where we differ, estimation (to me) includes how the value was derived.

----------

Steve Budzynski


"So, pass another round around for the kids. Who have nothing left to lose and for those souls old and sold out by the soles of my shoes"

 

[Gooser]

the degree of refinement with which an operation is performed or a measurement stated

So, if you pay particular attention to the word 'or',

You can restate this as:

the degree of refinement with which an operation is performed

OR...

the degree of refinement with which a measurement [is] stated

SO, if you can agree with that, then certainly you could agree that in one of the meanings of precision, (perhaps the author chose this meaning,) that 1.0 is less precise than 1.0000.

And, if you cannot agree with that, then why do we continue to debate this?

v/r

Gooser

 

[CajunCenturion]

To say that 1.0 is more precise to 1.000, you are comparing the values to each other, which is a process, and you're also compare against a scale.

1.000 is simply a value.
1.0 is simpy a value.

The notion of precision only comes into play when you compare these two values and comparision IS a process.

--------------
Good Luck
To get the most from your Tek-Tips experience, please read FAQ181-2886
As a circle of light increases so does the circumference of darkness around it. - Albert Einstein