OpenMx Help
rabil
Joined: 01/14/2010
Standard Errors versus Confidence Intervals
When I run this code (a threshold model for ordinal data), the standard errors are incredibly large but the confidence intervals are relatively narrow. Are any of the results trustworthy? I've tried simplifying the thresholds (using labeling to reduce the number of parameters) but it doesn't help. I'm not sure why this data is so hard to model.
If I treat the ordinal data as if it were quantitative, I have no trouble fitting a common factor model.
- Read more about Standard Errors versus Confidence Intervals
- 6 comments
- Log in or register to post comments
rabil
Joined: 01/14/2010
Interpreting Output from mxTryHardOrdinal
The output below says a solution was found, but was it?
Begin fit attempt 21 of at maximum 21 tries
- Read more about Interpreting Output from mxTryHardOrdinal
- 2 comments
- Log in or register to post comments
rabil
Joined: 01/14/2010
Constrain Total Variance instead of Residual Variance in Ordinal Threshold Path Mdel
The path specification for an ordinal model in the documentation constrains the residual variances for the ordinal variables to 1. I would like to instead constrain the total variance for the ordinal variables to 1. But I'm not sure how to accomplish this. When the total variance is constrained to 1, there residual variance is constrained to 1 minus the factor loading squared (the factor loadings are constrained to be between -1 and 1) as I understand it.
Charlotte
Joined: 07/02/2012
Installation of OpenMx version 2.5.2; No rule to make target `omxSymbolTable.cpp'
Dear all,
I am trying to install OpenMx version 2.5.2 and I get the following error message:
"*** No rule to make target `omxSymbolTable.cpp', needed by `omxSymbolTable.o'. Stop."
What does this mean and how can I solve this?
Best regards
Charlotte
Charlotte
Joined: 07/02/2012
Simplex models with thresholds - CIs?
Dear all,
I have fitted a simplex model with six time points. It's a threshold model with 2 thresholds. I fixed the thresholds and freely estimated the means. I used the CSOLNP optimizer.
I get stable estimates, they are in accordance with what I would expect based on the univariate results, and the gradients look ok.
As a next step, I wanted to calculate confidence intervals, but I only get this:
confidence intervals:
lbound estimate ubound note
atm21 NA 0.4871751 NA !!!
- Read more about Simplex models with thresholds - CIs?
- 6 comments
- Log in or register to post comments
rabil
Joined: 01/14/2010
How to use "mxFitFunctionAlgebra" instead of "mxAlgebraObjective"
This code used to work using "mxAlgebraObjective", but now says I have to use "mxFitFunctionAlgebra" instead of "mxAlgebraObjective".
###############
models_1_v4 <- mxModel("Models_1",
Model_1_t1_v4,
Model_1_t2_v4,
mxAlgebra(
Model_1_t1_v4.objective+
Model_1_t2_v4.objective,
name="multi"),
# mxAlgebraObjective("multi"),
mxFitFunctionAlgebra(algebra = "multi")
)
m1_fit_v4 <- mxRun(models_1_v4)
##################
rabil
Joined: 01/14/2010
Output from mxFactorScores - Order of rows?
In the help file for mxFactorScores, it says:
The rows are in the order of the _sorted_ data.
I'm not sure what this means. The data I have is in order by date and it's clear that the estimated factor scores for "ML" are no longer in the same order. There are two correlated factors each with 2 indicators (and nothing else). How can I get the factor scores into the same order as the rest of the data?
- Read more about Output from mxFactorScores - Order of rows?
- 5 comments
- Log in or register to post comments
Luntary
Joined: 02/17/2016
Error: The data object 'MZ.data' contains an observed matrix that is not of type 'double'
Hi Everybody!!!
I'm really naive using OpenMx. So probably my question is a silly mistake. Any way;
I try to perform a twin analysis with sex and age as covariates. I have used the script "UnivariateTwinAnalysis_MatrixRaw-3" from Dr. neale that I found in this forum. But I don't want generate sex and age data because I have mine. So I changed a bit the script.
*******************************************************************
summary(test)
selVars <- c('hear1','hear2')
mzData <- as.matrix(subset(test, zyg==1, c(hear1,hear2,sex1,sex2,age1,age2)))
rabil
Joined: 01/14/2010
Handling Exogenous Latent Variables in OpenMx
Suppose you have two exogenous latent variable. (There will be directed paths from them to a response variable.) Is the covariance between the two exogenous latent variables part of the model? That is, do I have to include a path specification for the covariance or otherwise the covariance will be constrained to zero? I understand that the covariances among exogenous manifest variables are not part of the model.
- Read more about Handling Exogenous Latent Variables in OpenMx
- 1 comment
- Log in or register to post comments
AshleeM
Joined: 01/20/2016
Error in if (class(fit) == "try-error" || is.na(fit$output$minimum) || : missing value where TRUE/FALSE needed
I'm running a measurement model (two time point common factor model) and I am getting an error message I've never seen before when I drop a parameter. I talked to AdminRobK about this, and he suggested I post it to the forums. The error reads:
Error in if (class(fit) == "try-error" || is.na(fit$output$minimum) || : missing value where TRUE/FALSE needed
In addition: Warning message:
In is.na(fit$output$minimum) : is.na() applied to non-(list or vector) of type 'NULL'