Categorical Outcomes

ACE_Cholesky_Model <- mxModel("ACE_Cholesky",
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,label=c("a11", "a21", "a22"), name="a" ),
mxMatrix( type="Lower", nrow=nv, ncol=nv, free=TRUE, values=.6,label=c("c11", "c21", "c22"), name="c" ),

I am not sure how to specify thresholds when > 1, I was hoping for some help. I have run the ACE models with one threshold (binary response data) successfully and have tried to incorporate the correct code for thresholds >1 into my script from several different scripts but have had no luck.

It seems that I am not putting the right information into dimnames? My data contains one variable with 6 levels, for each twin. I'm also not sure how the specified matrices combine and any tips on how that occurs would be greatly appreciated.

Hmmmm. The lower bound for this integral is greater than or equal to the upper bound.
This will cause problems with the likelihood function.
Please check your thresholds are bounded appropriately

Is there an efficient way to input contingency tables as data? mxData does not seem to allow such a structure. If the raw data must be input, is there a way to assign multiple counts to an individual case? Thanks.

Hao

-Scott

I'd like to run an ACE model - one variable is categorical (2 thresholds) and the other is really continuous, but I thought I'd recode it into deciles (as the joint continuous/categorical implementation in OpenMx 1.1 seems a little way off - and I wouldn't know where to start with the coding).

I think can handle the case of the same number of thresholds across variables, but I was wondering if anyone had a script allowing for a differing number of thresholds for variables, that they'd be willing to share? +/- Independent/Common Pathways.

Prob (Y_gki <= c_l | Z_gi, U_gi)
= r_gk + (1 - r_gk)/(1 + exp(-(alpha_kl + beta_k*Z_gi + delta_k*U_gi)))

where
g = 1,2 indicating groups,
k = 1,..., K indicating K instrument items,
i indicating the subject number in each group,
so Y_gki is the response for item k from subject i in group g;

each item has a Likert scale with responses 0-5