🚀 go-pugleaf

>In article <NEWTNews.4814.782702587.woolfson@woolfson.unicom.net> Eric Woolfson <woolf@unicom.net> writes:
>>      That is the problem with "estimates" - they vary so widely
>>    widely as to make them quesses at best.
>>      Side note - Kleck called up 4965 households and asked the 
>>    anonymous respondents if they had ever had a "defensive gun
>>    experience" and when 52 said yes, he jumps to the conclusion that
>>    there must be 2.5 million such uses a year.
>>      Now you do the same poll, changing the words "defensive gun
>>    experience" to "UFO abduction" or "Elvis sighting", and then
>>    publish the results as proof.
>>      See the problem? Think 52 anonymous responses "proves" that
>>    Elvis is alive and sacking groceries in Des Moines?  


In article <1994Oct21.025027.3236@rpp386>,
John F. Haugh II <jfh@rpp386.cactus.org> wrote:
>
>This is a perfectly valid means for conducting such a survey.  The
>science of statistics tells us that if you select a reasonably sized
>sample at random, that the properties of that sample apply to the
>entire population as a whole.
>-- 



Excuse me John but do you mind if I fix this?

The
>science of statistics tells us that if you select a reasonably sized
>sample at random, that the properties of that sample PROBABLY apply to the
>entire population as a whole.