OpenMx Structural Equation Modeling

Hi everyone,

I have a problem running multilevel model using a SEM framework to get a likelihood-based CI of the effect size. I have two factors representing (random) intercept and (fixed) slope. I attach my data file here. Use the following code to get the dataset:

datawide <- read.csv("datawide.csv")

The dataset has been transformed into a wide format. Y is the response variable. X is the upper-level predictor. Z is the lower-level predictor without any centering. My target model is

L1: Y = B_0 + B_1 * Z + r
L2: B_0 = X + u

I would like to be able to handle Poisson counts. The only lead to doing this in OpenMx seems to involve using mxRowObjective. I was wondering if any one could share some examples.

I wrote a simple OpenMx script to do LCA on ordinal variables. It works fine on simulated data. When I run it on real data, the estimated thresholds are not in order. I then included constraints on the thresholds (simple enough to do) so that they are monotonically increasing. This seems to work as the threshold estimates monotonically increase. From reading the manual, I was sure constraints weren't necessary.

I've asked about this before but I don't think I ever received any replies. Can OpenMx handle Poisson counts as observed variables? I have counts that are too small to treat as continuous Normally distributed outcomes and I need a way to model them. Any insights would be greatly appreciated.

The data I have are censored at a value that is constant across all subjects. So y is Normal except that all values at or above 15 were coded as 15. I've created a simple LCA in OpenMx that works (treats the censored data as if it were simply Normal) but the censored data affect the detection of clusters. I'd like to model the data as truncated. I'm familiar with thresholds for ordinal data but it's not clear to me if OpenMx can handle truncated Normal data where y* = y if y <= 15 and y* = 15 if y > 15.

At a recent workshop, someone asked how to obtain standardized estimates from OpenMx. Using the path-style input this is straightforward, and can be done with a couple of mxEval() statements and an omxRAMtoML() call:


# Now standardize solution
mxEval((solve(vec2diag(sqrt(diag(S)))))%&%S,threeLatentMultipleReg1Out)
mlthreeLatentMultipleReg1Out<-omxRAMtoML(threeLatentMultipleReg1Out)
mxEval(solve(vec2diag(sqrt(diag(solve(I-A)%&%S))))%*%A%*%vec2diag(sqrt(diag(solve(I-A)%&%S))),mlthreeLatentMultipleReg1Out,compute=T)


Hi,
Snuffling around in MxPPMLR I see
# IN DEVELOPMENT
# Fake Latents
# There are multiple ways to specify the error variance terms. There is the
# usual, direct way of allowing the term in the S matrix to be free, but it
# can also be specified using latent variables.
#
# This segment adjusts the model so that all error variance is specified using
# only the S matrix, without any latent variables

This raised a question for me.

I guess this is designed to do change this:

Into this:

hi all,
Running a 2 group RAM model. Both sub-models return their fit indices in summary(), and the supermodel runs fine, with a summed objective.

However... while the supermodel knows about the submodel's observations etc (as shown in the print out below) it doesn't compute an AIC for the the supermodel

Bug/Missing code?


observed statistics: 156
estimated parameters: 79
degrees of freedom: 77
-2 log likelihood: 46372.74
saturated -2 log likelihood: NA
number of observations: 6000
chi-square: NA
p: NA
Information Criteria: