Bivariate Cholesky - Continuous & Ordinal, with Covariates

Thank you! I'm making progress, I hope. I fixed this issue. However, now I am having a problem with specifying the number of thresholds. As I mentioned, my ordinal variable is "ogo." In twin1, values range from 0 to 6 (although only one person endorsed "6"), in twin2, values range from 0 to 5. I'm making notes about places that are different from my original script where I analyzed two continuous variables.

So, to set this up, I now have:

mydata$ogo1 <- mxFactor(mydata$ogo1, levels=c(0:6), ordered=TRUE)
mydata$ogo2 <- mxFactor(mydata$ogo2, levels=c(0:5), ordered=TRUE)

So, above, I tried to tell openMX how many levels my ordinal variables have.

mzData <- subset(mydata, ZYGOSITY=="0")
dzData <- subset(mydata, ZYGOSITY=="1")
# Select Variables for Analysis
Vars <- c('caster','ogo')
nv <- 2 # number of variables
ntv <- nv*2 # number of total variables
selVars <- c("caster1", "ogo1", "caster2", "ogo2")
bivACEModel <- mxModel("bivACE",
mxModel("ACE",
# Matrices a, c, and e to store a, c, and e path coefficients
mxMatrix( type="Lower", nrow=nv, ncol=nv, free=TRUE, values=.6, labels=c("a11","a21","a22"), name="a" ),
mxMatrix( type="Lower", nrow=nv, ncol=nv, free=TRUE, values=.6, labels=c("c11","c21","c22"),name="c" ),
mxMatrix( type="Lower", nrow=nv, ncol=nv, free=TRUE, values=.6, labels=c("e11","e21","e22"),name="e" ),

# Matrices A, C, and E compute variance components
mxAlgebra( expression=A+C+E, name="V" ),
mxMatrix( type="Iden", nrow=nv, ncol=nv, name="I"),
mxAlgebra( expression=solve(sqrt(I*V)), name="iSD"),

Below, I tried to add the constraint on the variance that needs to happen for the ordinal variable "ogo."

mxConstraint(V[1,2]==1, name="Vconst"),

Then onward.

mxAlgebra(iSD %*% a, name="sta"),
mxAlgebra(iSD %*% c, name="stc"),
mxAlgebra(iSD %*% e, name="ste"),
mxAlgebra(A/V, name="StandardizedA"),
mxAlgebra(C/V, name="StandardizedC"),
mxAlgebra(E/V, name="StandardizedE"),
mxAlgebra(solve(sqrt(I*A)) %&% A, name="CorA"),
mxAlgebra(solve(sqrt(I*C)) %&% C, name="CorC"),
mxAlgebra(solve(sqrt(I*E)) %&% E, name="CorE"),
mxAlgebra(solve(sqrt(I*V)) %&% V, name="CorP"),

Below, the expected means vector is different than my original script, as I'm fixing the mean of the ordinal variable to some value...then I have the threshold matrix.

# Matrix & Algebra for expected means vector
mxMatrix( type="Full", nrow=1, ncol=ntv, free=c(T,F,T,F), values=c(.6,0,.6,0), labels=c("caster1","ogo1","caster2","ogo2"), name="expMean"),

mxMatrix(type="Full", nrow=7, ncol=2, free=T, values=0.1, label="thre", name="expThre"),

And so on...

# Algebra for expected variance/covariance matrix in MZ
mxAlgebra( expression= rbind ( cbind(A+C+E , A+C),
cbind(A+C , A+C+E)), name="expCovMZ" ),
# Algebra for expected variance/covariance matrix in DZ, note use of 0.5, converted to 1*1 matrix
mxAlgebra( expression= rbind ( cbind(A+C+E , 0.5%x%A+C),
cbind(0.5%x%A+C , A+C+E)), name="expCovDZ" )
),

mxMatrix( type="Full", nrow=1, ncol=2, free=FALSE, label=c("data.ageT1", "data.ageT2"), name="obs_age" ),
mxMatrix( type="Full", nrow=1, ncol=2, free=FALSE, label=c("data.age2T1", "data.age2T2"), name="obs_age2" ),
mxMatrix( type="Full", nrow=1, ncol=2, free=FALSE, label=c("data.sexT1", "data.sexT2"), name="obs_sex" ),

Threshnames = ogo1 and ogo2

mxAlgebra( expression= ACE.expMean + obs_sex%x%ACE.betasex + obs_age%x%ACE.betaage + obs_age2%x%ACE.betaage2 , name="expMean"),
mxFIMLObjective( covariance="ACE.expCovMZ", means="expMean", dimnames=selVars, thresholds="ACE.expThre", threshnames=c('ogo1', 'ogo2') ) ),

mxAlgebra( expression=MZ.objective + DZ.objective, name="minus2sumloglikelihood" ),
mxAlgebraObjective("minus2sumloglikelihood"),
mxCI(c('ACE.sta', 'ACE.stc', 'ACE.ste')),
mxCI(c('ACE.StandardizedA', 'ACE.StandardizedC', 'ACE.StandardizedE')),
mxCI(c('ACE.CorA', 'ACE.CorC', 'ACE.CorE', 'ACE.CorP'))
)


When I try to run, I get an error message that says "Error: The job for model 'bivACE' exited abnormally with the error message: fit is not finite (Found 4 thresholds too close together in column 2.)"