Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: st: St: comparing survey pre- and post- results
From
Nick Cox <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
RE: st: St: comparing survey pre- and post- results
Date
Tue, 16 Nov 2010 19:15:40 +0000
Well, there are: measures of agreement such as kappa, for example. However, it seems difficult to relate them to a modelling approach.
Nick
[email protected]
Andrzej Niemierko
Thank you Austin for your advice and code. This is most useful, and
dichotomization is indeed a reasonable option. Of course, some information
is lost when we dichotomize 5-bin distributions. I was hoping that there are
methods that allow a more direct comparison of distributions of
corresponding ordinal variables.
Andrzej
On 11/15/10 11:42 AM, "Austin Nichols" <[email protected]> wrote:
> Andrzej Niemierko <[email protected]> :
> One method is to dichotomize the outcome and use a regression for
> binary outcomes to compare pre and post:
> clear
> input f0 f1
> 3 4
> 18 11
> 31 28
> 6 18
> 1 7
> end
> g a=_n
> reshape long f, i(a) j(post)
> g agree=a>3
> ta a agree
> logit agree post [fw=f], r
>
>
> On Mon, Nov 15, 2010 at 11:33 AM, Andrzej Niemierko
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/