cc wrote:
> On Aug 30, 5:23 am, Roy Schestowitz <newsgro...@xxxxxxxxxxxxxxx>
> wrote:
>> Playing the numbers game: how many Linux installations and users are out
>> there?
>>
>> ,----[ Quote ]
>> | But smolt is only an opt-in tool and is not offered during text
>> | installations (Servers, etc.) at all. According to Fedora's statistics
>> | page the estimated ratio between smolt data and reality is 1 to 10.
>> | This would result in 1.25 million Fedora users - and therefore in 25
>> | million Linux users.
>> |
>> | Looks nice, especially considering the fact that Apple's userbase was
>> | around 22 million half a year ago.
>> | Ubuntu
>> |
>> | There is another possible approach to these numbers: Ubuntu's Mark
>> | Shuttleworth estimated 8 million Ubuntu users in an interview in late
>> | December 2006. And both the Linux Desktop Survey and the web server
>> | logs from Distro Watch gave Ubuntu roughly 30 % of the cake. This makes
>> | more than 26.6 million Linux users 8 month ago.
>> `----
>>
>> http://liquidat.wordpress.com/2007/08/29/playing-the-numbers-game-how...
>>
>> Many Linux PCs are not connected (or appliance-ed), so it's probably much
>> higher than this.
>
>
> So, Mark Shuttleworth makes an estimate off the top of his head with
> no stats to back it up, and now that's the basis for counting Linux
> users? He could have easily estimated 1 million, or 10 million. He
> just guessed! Fedora's ratio is the exactly the same: a guess. All
> statistical samples show that the usage is not that high yet, which is
> exactly how an estimate is supposed to be made. You can't make
> statistical observations off of blind guesses.
>
If every actual used system was counted it wouldn't be a statistic, it would
be a sum.
Statistics use the best available information they can find to make an
informed guess. That's what the science is all about, improving the ability
to guess the sum from a portion.
But I do think the text of that article was naff though, it wasn't even
statistical analysis, it was just a sort of it n=1 then assume y=24million,
with nothing to base it on.
I still think that google is likely to have one of the best guides for stats
at it's disposal, simply because so much traffic goes their way. But
without that, then really those sites that take ten or so popular but
unrelated sites and build stats from that are the best source.
W3schools OS section still has Linux higher than Vista, but Mac has made
some ground too and has over taken Linux. For browsers though Firefox is
ahead of IE7 and very close to taking over IE6.
|
|
