[R] Alternative for correspondance analysis

[Gabor Grothendieck]

You could try plotting them with a parallel plot. See ?parallel
in lattice or ?ggpcp in ggplot2

On Thu, Sep 3, 2009 at 4:18 AM, Sannr<SanderSmit77 at hotmail.com> wrote:
>
> I am looking for an alternative way to inspect my data, other than doing an
> correspondance analysis.
>
> What I have is a list with 5 different measurements of a person and ratings
> that that person gave to a number of objects, so:
>
> person1.name, person1.score1, person1.score2, person1.score3,
> person1.score4, person1.score5, person1.ratingobject1,
> person1.ratingobject2, person1.ratingobject3, person1.ratingobject4, ...
>
> person2.name, person2.score1, person2.score2, person2.score3,
> person2.score4, person2.score5, person2.ratingobject1,
> person2.ratingobject2, person2.ratingobject3, person2.ratingobject4, ...
>
> person3.name, person3.score1, person3.score2, person3.score3,
> person3.score4, person3.score5, person3.ratingobject1,
> person3.ratingobject2, person3.ratingobject3, person3.ratingobject4, ...
>
> etc...
>
> Now I want to see how those 5 measurements match to certain high ratings for
> certain objects, so for example a character type high on score1,score2 and
> score3 and low on score5 & score6 generally rate object1 very high and
> object 2 very low. I want to do this using R.
>
> I thought about using correspondance analysis to tackle the problem, but
> this means I will need to first group those people. I prefer not to do so,
> because I feel I am loosing information when I do that. Is there any
> alternative I could use to measure correspondances in the data?
>
> Any suggestion is very welcome!
> --
> View this message in context: http://www.nabble.com/Alternative-for-correspondance-analysis-tp25271624p25271624.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>