JointRegBC (version 0.1.1)

JointRegBC: Joint Modelling of Mixed Correlated Binary and Continuous Responses : A Latent Variable Approach.

Description

A joint regression model for mixed correlated binary and continuous responses is presented. In this model binary response can be dependent on the continuous response. With this model, the dependence between responses can be taken into account by the correlation between errors in the models for binary and continuous responses.

Usage

JointRegBC(ini = NA, X, y, z, p, q, ...)

Arguments

ini

Initial values

X

Design matrix

z

Continuous responses

y

Binary responses

p

Order of dimension of Binary responses

q

Order of dimension of continuous responses

...

Other arguments

Value

Binary response

Coefficient of ordinal response

Continuous Response

Coefficient of continuous response

Variance of Countinuous Response

Variance of continuous response

Correlation

Coefficient of continuous response

Hessian

Hessian matrix

convergence

An integer code. 0 indicates successful convergence.

Details

Models for JointRegBC are specified symbolically. A typical model has the form response1 ~ terms and response2 ~ terms where response1and response2 are the (numeric) binary and continuous responses vector and terms is a series of terms which specifies a linear predictor for responses. A terms specification of the form first + second indicates all the terms in first together with all the terms in second with duplicates removed. A specification of the form first:second indicates the set of terms obtained by taking the interactions of all terms in first with all terms in second. The specification first*second indicates the cross of first and second. This is the same as first + second + first:second.

References

Bahrami Samani, E. and Tahmasebinejad. Zh.(2011). Joint Modelling of Mixed Correlated Nominal, Ordinal and Continuous Responses. Journal of Statistical Research. 45(1):37-47.

See Also

nlminb,fdHess,clogit

Examples

data("Bahrami1")
gender<-Bahrami1$ GENDER
age<-Bahrami1$AGE
duration <-Bahrami1$ DURATION
y<-Bahrami1$ STEATOS
z<-Bahrami1$  BMI
sbp<-Bahrami1$ SBP
X=cbind(gender,age,duration ,sbp)
P<-lm(z~X)[[1]]
names(P)<-paste("Con_",names(P),sep="")
Q<-clogit(y~X)[[1]]
names(Q)<-paste("Binary",names(Q),sep="")
W=c(cor(y,z),var(z))
names(W)=c("Corr","Variance of Continous Response")
ini=c(P,Q,W)
p=5;
q=4;
JointRegBC(ini,X=X,y=y,z=z,p=p,q=q)
## The function is currently defined as
structure(function (x, ...) 
UseMethod("JointRegBC"), class = "JointRegBC")