Fit Functions
Errors when implementing FML function
I’m trying to implement a slightly changed Maximum Likelihood function using mxFitfunctionR and ran into some problems that I wasn’t able to solve. Here is a short version of my current attempt at implementing a covariance-based FML function without any changes:
simple_FML <- function(model, state) {
obsCov <- model$data$observed# observed covariance
nmanif <- ncol(obsCov) # number of observed variables
Sigma_try_out <- try(mxGetExpected(model,"covariance")) # expected covariance matrix
- Read more about Errors when implementing FML function
- 3 comments
- Log in or register to post comments
bootstrap likelihood ratio test (BLRT) for GMM with definition variables
I would like to conduct BLRT test for 2 nested GMM model with definition variables. I referred to a previous post
https://openmx.ssri.psu.edu/node/4329 and it worked well on my computer. However, when I run the comparison of my model, it reported errors. I attached a screenshot of LRT without and with bootstrap in the attachment. And here is the information of my OpenMx Version:
Bootstrap Likelihood Ratio Test
- Read more about Bootstrap Likelihood Ratio Test
- 16 comments
- Log in or register to post comments
mxCompare function
I tried to compare two CFA models using the mxCompare function. Unfortunately, I received the message:
Error in refSummary$modelName : $ operator is invalid for atomic vectors
At first I thought I had some code error but I run an example located in the help for mxCompare function, that is:
- Read more about mxCompare function
- 10 comments
- Log in or register to post comments
RMSEA in multiple-group analysis
It seems that OpenMx uses the same formula of RMSEA for both single- and multiple-group analyses. According to Steiger (1998), the RMSEA should be adjusted by a factor of sqrt(K) where K is the no. of groups.
The attached PDF includes the test suggested by Steiger (1998, p. 417):
1. Construct two identical arbitrary data sets (random numbers will suffice).
2. Test one sample with a simple model, for example, a single factor model, and record the RMSEA value.
- Read more about RMSEA in multiple-group analysis
- 4 comments
- Log in or register to post comments
Scaled chi-square
Wondering if Satorra / Satorra-Bentler scaled chi-square is available in OpenMx or not? i.e., ML with robust corrections to the test statistics and standard errors in the case of non-normal data. Ideally, I'd like to see if the difference test for model comparisons is available. Only thing I found in the forums was this post from quite a while ago: http://openmx.psyc.virginia.edu/thread/530
Many thanks!
Carl
- Read more about Scaled chi-square
- 2 comments
- Log in or register to post comments
Equating means and variances across MZs, DZs and Siblings
CIs when RMSEA = 0
I noticed that when RMSEA = 0, the CIs come out as NA. Why is that? Is it a bug? Or are CIs theoretically undefined when RMSEA=0?
- Read more about CIs when RMSEA = 0
- 5 comments
- Log in or register to post comments
Custom R fit function with algebras - possible?
A <- mxMatrix(nrow = 4, ncol = 1, values = c(6:9), free = TRUE, name = 'A')
Pagination
- Page 1
- Next page