dennis roberts wrote:
>
> At 05:33 AM 1/22/2003, you wrote:
> > Even when a qualitative researcher
>
It seems that you completely missed my point so I try to clarify a
little:
> first point ... one is not a qualitative researcher ... either you are a
> researcher or not a researcher
>
This is an insignifican detail, of course I meant a researcher doing
qualitative research.
> > studies one person very
> >thoroughly he cannot say what people are like in general. However, he
> >has created knowledge about what people may be like and how they should
> >be studied to learn something important about them.
>
> i disagree ... just like any n=1 study ... unless you replicate this with
> other n=1s ... to see if others do similar things or not ... all you have
> is a lot of (perhaps very good) information about 1 person
>
> what you can't get from an n=1 study is the RANGE of behaviors that you
> might see ACROSS people which, then, tells you something about what is
> typical of people ...
>
> if we were interested in some population characteristic ... and opted to
> take samples of size n=1 ... the sampling error you would see is the same
> as the entire range of behavior of the population characteristic you are
> studying so ... where does YOUR n=1 sample happen to be? you have no idea
Qualitative research is often not interested in the range of things or
the population characteristics. Of course it would be nice to be able
to study a lot of people very thoroughly but this is often not possible
in one study.
>
> >These aspects and
> >points of view can be adapted in studying other people, i.e. they are
> >generalizable.
>
> all you can pose as questions are: i wonder if what i see in this person
> will be seen in other people? to answer these kinds of questions ... you
> MUST examine other people ...
>
> so, in a real sense, the notion of generalization from one person is ...
> well, of little value
>
> there is nothing wrong with doing in depth case studies (ie ... n=1
> studies) but, one can't have it both ways ... you can't say that you have
> something meaningful ... AND that generalizes to larger groups of people
> ... at the same time
>
I did not say that. One researcher in one study seldom can have it
both ways. That is why a case study is not generalizable to larger
groups in the sense 'people are typically like this...' and an honest
researcher does not claim that, either. Finding something valuable in a
case study and not generalize to population is quite acceptable in one
study. The idea is, however, that in the long run this information
makes research better also in studies with bigger N:s. These studies
can be done by the same researcher or research community in general. So
you can say that in the original study the variables or objets of
interest may be "generalizable" to further research, not the properties
of the studied case to the population.
Kai Karma
Sibelius Academy
Helsinki, Finland
> >
> >
> > > .
> > > .
> > > =================================================================
> > > Instructions for joining and leaving this list, remarks about the
> > > problem of INAPPROPRIATE MESSAGES, and archives are available at:
> > > . http://jse.stat.ncsu.edu/ .
> > > =================================================================
> >.
> >.
> >=================================================================
> >Instructions for joining and leaving this list, remarks about the
> >problem of INAPPROPRIATE MESSAGES, and archives are available at:
> >. http://jse.stat.ncsu.edu/ .
> >=================================================================
>
> _________________________________________________________
> dennis roberts, educational psychology, penn state university
> 208 cedar, AC 8148632401, mailto:[EMAIL PROTECTED]
> http://roberts.ed.psu.edu/users/droberts/drober~1.htm
>
> .
> .
> =================================================================
> Instructions for joining and leaving this list, remarks about the
> problem of INAPPROPRIATE MESSAGES, and archives are available at:
> . http://jse.stat.ncsu.edu/ .
> =================================================================
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
