[comp.edu] <<< I.S. SURVEY II >>>

wvenable@spam.ua.oz (Bill Venables) (07/20/90)

In article <5533@uceng.UC.EDU> ddahmer@uceng.UC.EDU (Hello World!) writes:
>... I am posting this again as I need a larger number of responses to
>go by for statistical purposes. (At least 30 in a sample to model a
>population, etc.)  ...

I feel obliged to sound a warning of the dangers of drawing inferences
from self-selected rather than random samples.  Sample size by itself
is no safeguard against wildy erroneous conclusions.

-- 
  Bill Venables, Dept. Statistics,        | Email:   wvenable@spam.ua.oz.au
  Univ. of Adelaide,  South Australia.    | Phone:           +61 8 228 5412

dgoudge@nmsu.edu (Darrell Goudge) (07/28/90)

In article <345@spam.ua.oz> wvenable@spam.ua.oz (Bill Venables) writes:
>In article <5533@uceng.UC.EDU> ddahmer@uceng.UC.EDU (Hello World!) writes:
>>... I am posting this again as I need a larger number of responses to
>>go by for statistical purposes. (At least 30 in a sample to model a
>>population, etc.)  ...
>
>I feel obliged to sound a warning of the dangers of drawing inferences
>from self-selected rather than random samples.  Sample size by itself
>is no safeguard against wildy erroneous conclusions.
>
>-- 

I think the caution of using a convenience sample especially collection 
for the express purpose of increasing power is well founded, unless 
the sampling frame is the population of interest.  In this case the
population of interest could be the individuals who read this group and 
wish to participate in this survey.

Darrell Goudge
Marketing Department
New Mexico State University
Las Cruces, New Mexico 88003