OASIS Mailing List ArchivesView the OASIS mailing list archive below
or browse/search using MarkMail.

office-comment message

[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [List Home]

Subject: Re: [office-comment] ODFF: list of suggestions

• From: Leonard Mada <discoleo@gmx.net>
• To: office-comment@lists.oasis-open.org
• Date: Sun, 21 Dec 2008 22:20:04 +0200

```Hello everyone,

Eike Rathke wrote:
> Hi David,
>
> [...]
>> STDEVA
>> "Estimates the standard deviation" - no, it calculates the
>> standard deviation. The standard deviation *is* an estimate (of
>>
>
> Done for draft11.
>

This is slightly more complex:
Lets say there is an infinite population and a finite sample from this
infinite population. Suppose now that we *calculate* the standard
deviations for the sample and somehow do it for the population, too.

sd(sample) = sqr( ... / (n-1) )
sd(population) = sqr( ... / n )
[Notice the difference between the 2!]

More often than not, we cannot calculate the population sd, so we need
to *estimate* it. The best estimator of the population sd is actually
the sample sd. So:
sd(population) ~ sd(sample)

[This is the reason why sd(sample) is with (n-1), to get a value more
close to sd(population).]

Therefore, we calculate the sd for a *sample*, but we usually wish to
*estimate* the sd of the *population*.

Sincerely,

Leonard

```

[Date Prev] | [Thread Prev] | [Thread Next] | [Date Next] -- [Date Index] | [Thread Index] | [List Home]