[R-sig-ME] Changing reference level in clmm() ordinal regression

[Jessie Barker]

Hi Thierry,

Thank you for your reply.

I see that when changing the reference from say, a1 to a2, the estimate for
a3 will be different.
However, I'm still not sure why, when I change the reference of the other
factor from, say, q1 to q2, the estimate for a3 will be different (because
a3 is is still being compared to the same reference level of a, regardless
of what the reference level of q is). Or am I misinterpreting that?

Thanks again,

Jessie

On 22 September 2017 at 14:38, Thierry Onkelinx <thierry.onkelinx at inbo.be>
wrote:

> Dear Jessie,
>
> All models have an identical fit. They only differ in the
> parametrisation. "a3" estimates the difference between "a3" and the
> reference. Hence, changing the reference results in a different
> interpretation of the parameter and thus a different estimate.
>
> Best regards,
>
> ir. Thierry Onkelinx
> Statisticus/ Statiscian
>
> Vlaamse Overheid / Government of Flanders
> INSTITUUT VOOR NATUUR- EN BOSONDERZOEK / RESEARCH INSTITUTE FOR NATURE
> AND FOREST
> Team Biometrie & Kwaliteitszorg / Team Biometrics & Quality Assurance
> thierry.onkelinx at inbo.be
> Kliniekstraat 25, B-1070 Brussel
> www.inbo.be
>
> ////////////////////////////////////////////////////////////
> ///////////////////////////////
> To call in the statistician after the experiment is done may be no
> more than asking him to perform a post-mortem examination: he may be
> able to say what the experiment died of. ~ Sir Ronald Aylmer Fisher
> The plural of anecdote is not data. ~ Roger Brinner
> The combination of some data and an aching desire for an answer does
> not ensure that a reasonable answer can be extracted from a given body
> of data. ~ John Tukey
> ////////////////////////////////////////////////////////////
> ///////////////////////////////
>
>
> Van 14 tot en met 19 december 2017 verhuizen we uit onze vestiging in
> Brussel naar het Herman Teirlinckgebouw op de site Thurn & Taxis.
> Vanaf dan ben je welkom op het nieuwe adres: Havenlaan 88 bus 73, 1000
> Brussel.
>
> ////////////////////////////////////////////////////////////
> ///////////////////////////////
>
>
>
> 2017-09-22 11:41 GMT+02:00 Jessie Barker <jessiebarker at gmail.com>:
> > I have a couple of questions that I asked on StackExchange and someone
> > suggested that I ask this mailing list. The post on StackExchange is
> here (
> > https://stats.stackexchange.com/questions/304092/changing-
> reference-level-in-clmm-ordinal-regression-in-r),
> > but I am summarizing it below:
> >
> > I’m analyzing data from a questionnaire where participants had to rank
> > three answers to each question (e.g. 1 = most likely, 3 = least likely).
> > They had to give a different rank to each answer, so each question has
> one
> > answer ranked 1, one ranked 2, and one ranked 3. The set of three answers
> > is the same for each questions, and there were seven questions.
> >
> > I want to know whether participants give different ranks to different
> > answers, and whether that is affected by question. Here's my model:
> >
> > model1 <- clmm(rank ~ answer + answer:question + (1+answer|participant),
> > data = mydata)
> >
> > (I don’t have question as a fixed effect, because for each question
> > participants had to give a 1, 2 and 3 rank, so question alone does not
> > affect rank.)
> >
> > My first question is whether I’ve set up the model correctly, as I don’t
> > have any experience with ordinal regression. When I look at coef(model1),
> > all participants seem to have the same intercepts and coefficients for
> the
> > different answers, which is not what I thought should happen (I thought I
> > was setting up a model with random intercepts and random slopes).
> >
> > My second question is about changing the reference level of question and
> > answer. When I look at summary(model1), it uses answer a1 and question q1
> > as the reference levels, so I ran the model again using different answers
> > and questions as reference levels.
> >
> > When I run the model again using a different answer as the reference
> level,
> > the coefficients for the fixed effects are the same, but the random
> effects
> > and threshold coefficients are quite different.
> > When I run the model using a different question as the reference level,
> the
> > coefficients for the fixed effects are quite different, but the random
> > effects are exactly the same, and the threshold coefficients relatively
> > similar.
> >
> > Could someone please help me understand what’s going on here?
> >
> > Thanks in advance,
> > Jessie Barker
> >
> >         [[alternative HTML version deleted]]
> >
> > _______________________________________________
> > R-sig-mixed-models at r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>

	[[alternative HTML version deleted]]