as bob hayden put it ... succinctly ... most of what you have are problems ...
there are two main ones i see:
1. the inability to define ... conceptually or operationally ... what is
the target population to which you want to generalize your results?
(assuming you do of course ... if not, statistics are irrelevant)
2. estimating some error term ... sampling error for the mean for example
... which is then applied (to as bob mentioned) things like confidence
intervals [what is the parameter mean?] or doing hypothesis tests [the null
is that the population mean is 100]
now, for some things ... whether you have a random sample or otherwise ...
might not make any difference ... such as, if you split even a convenience
sample RANDOMLY into two parts ... experimental and control ... this does
not effect the veracity of the difference you might see ... and tests done
on that difference ... ie, INTERNAL VALIDITY might be intact ... BUT, you
still get back to the intractable problem of #1 above ... that you might
find a 'statistical result' but ... to whom can you generalize those findings?
obviously ... the name 'convenience' rings true ... you get a sample easily
... or conveniently but, unfortunately ... this is NOT good enough for
statistical inferences ...
convenience sampling reminds me of the typical 'stand on the corner and ask
passersby a question' method .. that is done almost all the time by news
reporters doing their bit for the 11PM action news ... where they thrust
the mike into the faces of THOSE WHO HAPPEN TO BE COMING DOWN THAT STREET
AT THAT INTERSECTION POINT AT THAT MOMENT IN TIME ... and then the reporter
in his/her bit ... wants YOU to believe that the 'typical' response that is
AIRED ... is what the typical citizen feels ...
yeah, right!
your dissertation will suffer the same interpretation fate
At 07:13 AM 7/5/00 +0200, Susanne Muigg wrote:
>Hi there,
>
>now I'm about to finish my thesis, but still looking for some literature
>about the advantages and disadvantages of a (student) convenience sample,
>which I had used. Unfortunately, I couldn't find anything, even if I've done
>quite an extensive literature search in all big Austrian university
>libraries, in international databanks and via Internet.
>
>If you know where I could find something about the pros and cons of
>convenience sampling, please help me!
>
>
>Best regards,
>
>Susan
>
>
>
>
>
>===========================================================================
>This list is open to everyone. Occasionally, less thoughtful
>people send inappropriate messages. Please DO NOT COMPLAIN TO
>THE POSTMASTER about these messages because the postmaster has no
>way of controlling them, and excessive complaints will result in
>termination of the list.
>
>For information about this list, including information about the
>problem of inappropriate messages and information about how to
>unsubscribe, please see the web page at
>http://jse.stat.ncsu.edu/
>===========================================================================
==========================================================
Dennis Roberts, EdPsy, Penn State University
208 Cedar Bldg., University Park PA 16802
Email: [EMAIL PROTECTED], AC 814-863-2401, FAX 814-863-1002
WWW: http://roberts.ed.psu.edu/users/droberts/drober~1.htm
===========================================================================
This list is open to everyone. Occasionally, less thoughtful
people send inappropriate messages. Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.
For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===========================================================================
