R help - Dec 2005 - how to construct an index or classify the cases with the combination of categorical and continuous variables

I have such a dataset.
x1 x2 x3 x4
1  1  0  2
0  1  1  10
1  0  1  30
......

x1,x2,x3 are categorical variable(the value can be 0 or 1),and x4 is a
continuous variable.
x1,x2,x3,x4 is the manifest(measurable) variables which reflect one immeasurable
variable.
If all of x1-x4 are continuous variables,I can do factor analysis to extract the
immeasurable "variable",but some of them are categorical variable
which violate the assumptions of factor analysis.So is there anyway to extract
the immeasurable "variable" or construct an index based on these
variable?

If NOT,then is there any way to classify the cases in to two categories? If all
the variables are binary,I can use latent class analysis to do it,but how about
binary variables plus countinuous variables?

It is not a R question,I just want some one help me out!
Thank you !
 

2005-12-06

------
Deparment of Sociology
Fudan University

My new mail addres is ronggui.huang at gmail.com
Blog:http://sociology.yculblog.com

there are possibilities to analyze such kind of data under an IRT 
framework, e.g., look at

Moustaki, I. (1996). A latent trait and a latent class model for mixed 
observed variables. British Journal of Mathematical and Statistical 
Psychology, 49

Moustaki, I. and Knott, M. (2000). Generalised Latent Trait Models. 
Psychometrika, 2000, 65, 391-411

I hope it helps.

Best,
Dimitris

----
Dimitris Rizopoulos
Ph.D. Student
Biostatistical Centre
School of Public Health
Catholic University of Leuven

Address: Kapucijnenvoer 35, Leuven, Belgium
Tel: +32/(0)16/336899
Fax: +32/(0)16/337015
Web: http://www.med.kuleuven.be/biostat/
     http://www.student.kuleuven.be/~m0390867/dimitris.htm


----- Original Message ----- 
From: "ronggui" <042045003 at fudan.edu.cn>
To: <r-help at stat.math.ethz.ch>
Sent: Monday, December 05, 2005 5:34 PM
Subject: [R] how to construct an index or classify the cases with the 
combination of categorical and continuous variables

>I have such a dataset.
> x1 x2 x3 x4
> 1  1  0  2
> 0  1  1  10
> 1  0  1  30
> ......
>
> x1,x2,x3 are categorical variable(the value can be 0 or 1),and x4 is 
> a continuous variable.
> x1,x2,x3,x4 is the manifest(measurable) variables which reflect one 
> immeasurable variable.
> If all of x1-x4 are continuous variables,I can do factor analysis to 
> extract the immeasurable "variable",but some of them are
categorical
> variable which violate the assumptions of factor analysis.So is 
> there anyway to extract the immeasurable "variable" or construct
an
> index based on these variable?
>
> If NOT,then is there any way to classify the cases in to two 
> categories? If all the variables are binary,I can use latent class 
> analysis to do it,but how about binary variables plus countinuous 
> variables?
>
> It is not a R question,I just want some one help me out!
> Thank you !
>
>
> 2005-12-06
>
> ------
> Deparment of Sociology
> Fudan University
>
> My new mail addres is ronggui.huang at gmail.com
> Blog:http://sociology.yculblog.com
>
>

--------------------------------------------------------------------------------

> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html 

Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm

There are a number of clustering routines available in R such as kmeans and
Mclust that may be applicable. Also on Cran is my depmix package which is
meant for analyzing dependent mixtures but can also be used to do latent
class analysis on mixed indicators, ie gaussian and binary indicators as you
seem to have.
hth, ingmar


On 12/5/05 5:34 PM, "ronggui" <042045003 at fudan.edu.cn> wrote:
> I have such a dataset.
> x1 x2 x3 x4
> 1  1  0  2
> 0  1  1  10
> 1  0  1  30
> ......
> 
> x1,x2,x3 are categorical variable(the value can be 0 or 1),and x4 is a
> continuous variable.
> x1,x2,x3,x4 is the manifest(measurable) variables which reflect one
> immeasurable variable.
> If all of x1-x4 are continuous variables,I can do factor analysis to
extract
> the immeasurable "variable",but some of them are categorical
variable which
> violate the assumptions of factor analysis.So is there anyway to extract
the
> immeasurable "variable" or construct an index based on these
variable?
> 
> If NOT,then is there any way to classify the cases in to two categories? If
> all the variables are binary,I can use latent class analysis to do it,but
how
> about binary variables plus countinuous variables?
> 
> It is not a R question,I just want some one help me out!
> Thank you !
>  
> 
> 2005-12-06
> 
> ------
> Deparment of Sociology
> Fudan University
> 
> My new mail addres is ronggui.huang at gmail.com
> Blog:http://sociology.yculblog.com
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
-- 
Ingmar Visser
Department of Psychology, University of Amsterdam
Roetersstraat 15, 1018 WB Amsterdam
The Netherlands
http://users.fmg.uva.nl/ivisser/
tel: +31-20-5256735