[R] 2 time dependend states and probability transition matrix

Christian Schulz ozric at web.de
Thu Sep 18 17:34:11 CEST 2003


Thanks, yes a good and simple starting point, how  to
integrate Bayes  should my own challenge.

christian


----- Original Message -----
From: "Spencer Graves" <spencer.graves at pdf.com>
To: "Christian Schulz" <ozric at web.de>
Cc: <r-help at stat.math.ethz.ch>
Sent: Thursday, September 18, 2003 4:25 PM
Subject: Re: [R] 2 time dependend states and probability transition matrix


> I don't know if I understand what you want, but I wonder if the
> following might help:
>
>  > Ptrans <- data.frame(Jan=LETTERS[rep(1:2, 5)],
> + June=LETTERS[rep(1:2, each=5)])
>  > (table(Ptrans$Jan, Ptrans$June)/dim(Ptrans)[1])
>
>       A    B
>   A 0.3 0.2
>   B 0.2 0.3
>
> hope this helps.  spencer graves
>
> Christian Schulz wrote:
>
> >Hi,
> >
> >have got anybody experience or a starting
> >point for me, how i can program a function
> >which calculate me a probability transition matrix with a data.frame and
two states.
> >
> >I have some independend variable and  a class variable
> >for two states - in example one from Jan2003 and the same variables from
June2003.
> >
> >Now i  would like to calculate the probability that PERSON X change
> >from classA to classB  between this time-period dependend from
> >the independend variables.
> >
> >Until now i think about an "easy" function  what use the Bayes-Theorem,
but it's too bad that i'm
> >not a mathematican.
> >
> >Thanks for any starting point, idea, link or paper!
> >
> >P.S.
> >I now the msm package, but think it's complex for my intention!?
> >
> >
> >Regards,Christian
> >
> >
> >
> > [[alternative HTML version deleted]]
> >
> >______________________________________________
> >R-help at stat.math.ethz.ch mailing list
> >https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> >
> >
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help




More information about the R-help mailing list