[EMAIL PROTECTED] (Mobile Survey) wrote in message 
news:<[EMAIL PROTECTED]>...
> I had a few questions and would be grateful for any answers:
> 1.If I have non-normal distributions for variables measured using 7
> point Semantic differential scales, can I use normalized scores for
> the analysis? Are there any objections to doing this.
> 2. I have a dichotomous variable in my model. While validating the
> measurement model, which software would be the best for me to use? I
> understand that AMOS only returns Pearson correlations and may not be
> appropriate?
> Thanks
> Abul.

I have a few questions also, perhaps you want to think about them
before doing any analysis.  whatever entity you are measuring using
the semantic differential technique, is there any reason to believe
the variable is distributed normally in the population.  sample data
will never be normal, so you want to look to the population or to some
theoretical framework.  of course, you can use normalized scores, the
better question is should you?  ity might not matter.

regarding (2), the answer, it seems to me, is not the software to use,
but rather what are you doing?  what is the criterion measure?  are
there multiple predictors, one of which is binary?  is it truly binary
or a continuous variable that has been dichotomized?

it seems to me you need to step back and ask yourself several
conceptual questions about what you are doing and what is the purpose
of the investigation.  sorry to say that these questions typically
need to be answered before you collect data.  it looks as if you may
have put the cart before the horse!!!

JJ Diamond
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to