metaSEM
Guoquan
Joined: 09/30/2019
Problem with TSSEM
Dear Mike & colleagues,
I am currently working on a TSSEM paper. However, some errors occur when I run the codes in R software. Please see data, my model and R codes in the attachments.
First, when I run TSSEM1, OpenMx status 1 is 6 and Warning message appears: "In print.summary.meta(x) : OpenMx status1 is neither 0 or 1. You are advised to 'rerun' it again." What should I do to solve it?
- Read more about Problem with TSSEM
- 1 comment
- Log in or register to post comments
raklein
Joined: 09/07/2019
OpenMX status1: 5 -- Problematic in this case?
Hi all,
I'm attaching some data and code to demonstrate my problem, but long story short I'm wondering if there is a fix for the 'OpenMX status1: 5' problem I'm having, AND/OR whether it is OK to report these values as-is? (perhaps with a grain of salt?) We're hoping to submit this paper for publication shortly.
Pruealexis
Joined: 08/18/2019
Outliers/Influential cases and Publication Bias
Hi all,
I am currently using metaSEM to create a pooled correlation matrix from 20 studies in my meta-analysis.
I previously used metafor to do this, conducting a metaanalysis via Hunter-Schmidt estimation/method on uncorrected data (maModel), and identified any outliers/influential cases. Using this method, I also completed a leave one out analysis. Metafor also enabled creating Forest Plots and Funnel Plots (to check for publication bias).
nastjuscha
Joined: 06/28/2016
TSSEM2 with different combinations of variables
Dear Mike,
I have a question about possibilities for model specification at stage 2 of MetaSEM.
So I have a dataset with 10 variables - at the end of stage 1 I get a pooled correlation matrix. In stage 2 I would like to test some models with different constellations of the variables, e.g. with variables V1, V2, V3, V4, V5, V6, V7 and V8 in the first model and with V1, V2, V3, V4, V5, V9, V10 in the second. Is that possible? And if it is possible, how should I specify this in the syntax?
Thanks for your help!
forscher
Joined: 03/05/2013
Best way to test constraints on parameters in metaSEM models
I have metaSEM model (fit using metaSEM::meta) for which I wish to test constraints on the estimated intercepts. I've been using car::linearHypothesis because it's extremely flexible -- it works on any model that provides a variance-covariance matrix (via vcov()) and a vector of estimated coefficients (via coef()). Given a metaSEM model, car::linearHypothesis seems to allow the testing of joint hypotheses (ex, the hypothesis that Intercept1 = 0 AND Intercept2 = 0) and complex hypotheses (ex, the hypothesis that Intercept1 = Intercept2).
Xin Lin
Joined: 06/10/2019
MetaSEM Error Message-Missing value where TRUE/FALSE needed
Hi Dr. Cheung,
I am trying to use my dataset to mimic your code “fixed1 <- tssem1(mat,n, method = "FEM")”
I got the error message “Error in if (!all(isPD)) warning(paste("Group ", (1:no.groups)[!isPD], :
missing value where TRUE/FALSE needed”
I have attached the first five correlation matrices and the sample size (n) for each study.
Xin Lin
Joined: 06/10/2019
Unable to read data
Hi Dr. Cheung and colleague,
I am trying to mimic your codes in your metaSEM article (cheung, 2018). I construct a fake dataset and try the tssem1 as following
- Read more about Unable to read data
- 2 comments
- Log in or register to post comments
Sepidehe
Joined: 05/24/2019
OpenMx status is 6
Dear Mike and colleagues,
I am trying to conduct a metaSEM analysis with 11 variables and 111 studies. However, I am stuck at the early stages as the OpenMX status is 6. Due to this issue, I removed all the studies with only one input (i.e., corrected correlation for unreliability) and performed the analysis again but the problem still persists. I am attaching my data as well as the results of my analyses. I would appreciate if you could help me figure this issue out.
Many thanks,
Sepideh
- Read more about OpenMx status is 6
- 3 comments
- Log in or register to post comments
nbl
Joined: 05/08/2019
Multiple Effect Sizes Within Studies - Prior to Step 1
Thank you for allowing me to join this community!
I want to conduct a small TSSEM using individual participant data from six studies. Since I have the raw data for each study, I am running into a problem with multiple measures of single constructs. Essentially, I have many relationships, but I don’t have many studies. Here is a simplified example of four constructs in one study, using different measures:
Predictor1 – Measure A
Predictor1 – Measure B
Predictor2 – Measure A
Predictor2 – Measure B
Predictor2 – Measure C
smh1003
Joined: 04/22/2019
Unable to run meta-SEM due to missing data
First of all, I am grateful for asking my question to this forum where gurus of meta-SEM are helping people like me.
I am currently conducting meta-SME with the theory of planned behavior by following the example of Scalco17 in this website.
https://cran.r-project.org/web/packages/metaSEM/vignettes/Examples.html#scalco17
It seems my dataset work pretty well, but something is messing up the analysis.
- Read more about Unable to run meta-SEM due to missing data
- 6 comments
- Log in or register to post comments