If Richard 's comment "Who's to say that all respondents do this
coding the same?" is important, then could an ordinal unfolding or
ideal point model solve that problem? The unfolding model directly
deals with the issue whether you "respond from below" or "respond from
above". The latest gllamm article (which is available from
http://www.gllamm.org/pub.html) has an example of a unidimensional
ordinal unfolding model:
Rabe-Hesketh, S. and Skrondal, A. (2007). Multilevel and latent
variable modelling with composite links and exploded likelihoods.
Psychometrika, in press.
I sure would like to see the .do file for the example in their
article, because theoretically I think unfolding models often make
sense but a big problem is the implementation. Unfolding models also
tend to require a fairly large sample size, so what sample size does
Marco have?
Anders Alexandersson
[email protected]
Marcos <[email protected]> wrote:
Basically, I have an ordered categorical model (ordered probit) where,
theoretically, people tend to overstate the values of the dependent
variable for higher values. That is, y can take for values 1, 2, 3 or 4
and my assumption is that certain people in my sample (i.e., with
some >> particular values of covariates) tend to answer most often
say, 3 or 4; >> so I am facing a measurement error problem in the
dependent variable,
and by modelling the cut-points as function of those covariates I
would >> be able to take this into account. However, as mentioned by
Stat
Kolenikov's reply, I would face an identification problem if the
covariates I use to measure these errors in the cut points are not
different from the one in the main equation.
Richard Williams <[email protected]> commented, in part:
In general, I think this is the kind of issue
that could make you want to give up quantitative
research altogether. :) You are counting on
respondents to code themselves as "above
average", "average", "below average" or
whatever. Who's to say that all respondents do
this coding the same? If we see differences by
gender, how do we know whether these differences
are real as opposed to just being differences due
to the fact that different people use different standards when coding?
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
