OT: application statistics [was: Re: Evolution]

[Karl Larsen]

Mario Vukelic wrote:
> On Mon, 2008-07-28 at 14:32 -0600, Karl Larsen wrote:
>   
>> Lots of things can be wrong 
>>     
>
> There is one fatal flaw, which I already expected in my other mail a few
> minutes ago.
>
>   
>> What E-mail Client do we use on Ubuntu?
>>                                ^^^^^^^^
>>         Checked 100 of the last emails to this list and the results are 
>>                                 ^^^^^^^^^^^^^^^^^^^
>>     
>
> You are inferring the ratio of the whole Ubuntu population from the
> ratio on the list.
    That is false. I said it is what I got the way I showed you.


>  This is certainly completely invalid.
>
>   
It is not! It is a subset of the the whole set.
> Of course, your sample size does not help. Your post does not make clear
> whether you counted users or emails, either (though you did write
> "emails"). Counting emails (and thus probaby counting individual users
> more than once) would be a mistake, too, as far as  can tell.
>
>   
    Yes there were some times where the same person had email to the 
list in that 100 sample.

Karl

-- 

	Karl F. Larsen, AKA K5DI
	Linux User
	#450462   http://counter.li.org.
   PGP 4208 4D6E 595F 22B9 FF1C  ECB6 4A3C 2C54 FE23 53A7