[Date Prev][Date Next][Thread Prev][Thread Next] - [Date Index][Thread Index][Author Index]

Re: Survey

>Greg, I couldn't agree with you more. 
>A survey of 400 does not represent
>the entire membership as I see it.

I think we need someone to explain how statistical 
sampling works.  I'm no expert, but here are the salient

1) You can never get a full survey.
2) Even if you mail out 5000 forms to everyone,
    you will only get about 5% back.
3) Of those 5%, probably *most* (lets say 50%) of them 
    have an AX to grind or are strongly opinionated.
4) The 95% who didnt respond did not have an
     ax to grind and therefore probably are happy
     the way things are.  Otherwise they would
     have responded.
5)  Now, then, if you Take the survey at face value
     as representative of the group, then the 2.5%
     of the strongly opinionated guys with an AX to
     grind make up 50% of the response.  When in
     fact they only represent 2.5% of the MEMBERSHIP.

Thus, there is no such thing as a response from
the 5000, unless you got out and TALK to everyone
and force him to respond.

But, however, if you RANDOMLY select a small sample
(say 400, which is actually a LARGE number when it
comes to sampling theory).  Then you send out the
questionare to them and you still only get 5% back.
But then, you CALL everyone of them and work them
until you do get a response.  Then you DO have a
true sampling of what the average membership wants..

I th ink AMSAT did it the right  way.


Sent via amsat-bb@amsat.org. Opinions expressed are those of the author.
Not an AMSAT member? Join now to support the amateur satellite program!
To unsubscribe, send "unsubscribe amsat-bb" to Majordomo@amsat.org