OpenMx Help
Purple Fish
Joined: 05/23/2024
ACE and ADE model returns the same AIC
Hello everyone:
I'm currently working on a project with twin data, and I encountered some weird results when fitting ACE and ADE models with OpenMx.
I fit both bivariate ACE, AE, and ADE models based on the script from Dr.Hermine Maes' website. However, our model returns unusual results. Specifically, the AIC values for ACE and ADE are the same. Also, the parameter estimates for the ADE model do not match the phenotypic correlations. Has anyone encountered similar problem before? Any kind of help is appreciated!!
- Read more about ACE and ADE model returns the same AIC
- 4 comments
- Log in or register to post comments
Victor Feagins
Joined: 05/02/2024
How to get estimates of latent random slopes and random intercept
Hello I fit a random slope and random intercept hlm and I am wondering how to get the latent values of the random slope and intercept. From what I can tell the issue is that the latent variables exist in second level so the function mxFactorScores does not know what to do. In this example U_00 is my random intercept and U_01 is my random slope.
Here is code to simulate HLM data
library(dplyr)
library(tidyr)
library(OpenMx)
jkarch
Joined: 03/15/2011
Product of Variables Identification
Hey,
my aim is to use product of variables to fit a random-intercept random-slope model with latent mean centering. To be precise, my model is as follows. $i$ indexes person, $t$ indexes observations within a person.
$$Y_{it} = \beta_i (X_{it}-meanX_i) + meanY_i + residualY_{ij}$$
$$X_{it} = meanX_i + residualX_{ij} $$
$$\beta_i \sim N(\mu_\beta, \sigma_\beta^2), \quad meanX_i \sim N(\mu_X, \sigma_X^2), \quad meanY_i \sim N(\mu_Y, \sigma_Y^2)$$
- Read more about Product of Variables Identification
- 3 comments
- Log in or register to post comments
Manuel Rein
Joined: 04/01/2024
Sampling weights for mxFitFunctionMultigroup()
Hi all,
I was wondering if there is a way to specify sampling weights in a multi-group model? I want all observations in a certain group to be weighed equally, but groups with a larger weight should have more influence on the estimation of parameters that are shared/equal between groups.
Best,
Manuel
koudzo
Joined: 03/21/2024
installation problem of OpenMX3.9 and patch3.9.9 in Ubuntu 22.04
Hi,
I am trying to install the openMX3.9 + patch3.9.9 in my Ubuntu machine (22.04)
I got an error as below:
mpif90 -O3 -fopenmp -I./elpa-2018.05.001 -c elpa1.f90
/opt/intel/oneapi/mpi/2021.3.0/bin/mpif90: 729: [: Illegal number:
elpa1.f90:3345:62:
3345 | 2*n-1, 2*na, nblk, 2*nblk)
| 1
Error: Type mismatch in argument 'vmat_s' at (1); passed COMPLEX(8) to REAL(8)
elpa1.f90:3345:62:
Tugce Yildiz
Joined: 01/15/2024
NA CIs for Bivariate Model
Hi, I am trying to run a bivariate model with two variables and 2 covariates. However, I get NA !!! for BivA, BivC and BivE. Can you help me solve this issue?
Here is the script:
### SELECT VARIABLES HERE
data_file <- "Cerebellum_volumes.csv"
variable_input1 <- "lsas_total"
variable_input2 <- "Vermis_VII"
cov1 <- "Total_Cerebel_Vol"
cov2 <- "age"
### Import data
dat <- read.csv(file=data_file, header=TRUE, sep = ";")
- Read more about NA CIs for Bivariate Model
- 1 comment
- Log in or register to post comments
Paul Hoon
Joined: 02/17/2024
Seek copy of MX varimax rotation code posted years ago at VA Tech web site
Hi to Administrators Neale,
Several years back we posted a varimax - quartimax script that worked well under an earlier implementation of MX.
1) Can you direct me to a site so I can retrieve this script and its documentation?
2) Would like to revise the script so it will run under R (Win 11) in the latest MX configuration. Could we get permission to get help from Neale and other administrators to guide us in making revisions to get the script to work in 2024?
Thank you for your advice and direction, best, Paul Hoon
gkirk
Joined: 10/24/2022
installation fails for openMX -> index not found
OS -> Ubuntu 22.04.3 LTS
R version 4.1.2 (2021-11-01)
error message:
Warning: unable to access index for repository https://vipbg.vcu.edu/vipbg/OpenMx2/software/src/contrib:
cannot open URL 'https://vipbg.vcu.edu/vipbg/OpenMx2/software/src/contrib/PACKAGES'
Warning message:
package ‘OpenMx’ is not available for this version of R
pasting https://vipbg.vcu.edu/vipbg/OpenMx2/software/src/contrib:
into a browser returns Page not found
a very similar error I found in the forum by Ling Ahu
lior abramson
Joined: 07/21/2017
checking total h2 at time 2 in a longitudinal choelsky model with paths script
Hello,
I am conducting a longitudinal Cholesky model with one variable in two time points.
I use the script written below with paths.
How can I modify this script to find for the total h2 at time 2? that is, I want to find the heritability explained by both the genetic effect from time 1 and the genetic effect from time 2, and the confidence interval of this estimate.
Thank you very much for your help
Jaewonee
Joined: 10/02/2023
Can't solve dimname associated error
Hello. I am quite naive with OpenMx & R in general, and I can't find a way to solve this error. I'm trying to create a covariance matrix with my data.. I am aware that my code is probably very messy and has lots of other errors-I really need some help & advice on how to advance with this. Thank you so much in advance. This is my code:
pheno2 <- read.csv("pheno2.csv")
library(OpenMx)
colnames(pheno2) <- gsub("\\.", "_", colnames(pheno2))
any(is.na(pheno2))
- Read more about Can't solve dimname associated error
- 9 comments
- Log in or register to post comments