"Dear Mei Yi,
I am afraid that I don't know any simple guidelines. If fact, I don't think that it is easy to derive such guidelines. There are a couple of factors affecting it. For example, the no. of variables, the percentages of missing…"
"Dear Mei Yi Ng & Katherine,
It is not easy to give a simple rule. You may consider a random-effects meta-analysis as a simple analysis in estimating the means and covariance matrix of the effect sizes.
There are 7 variables in your model. Thus,…"
I was not aware that you had created a discussion on this topic. Thus, I created another one at "MASEM on the indirect and direct effects."
Anyway, one additional comment is that there is only one group with raw data in…"
Hi Elizabeth,If you use Mplus, you may use a fixed-effects model whereas the TSSEM approach allows both a fixed- and random-effects models.There are two approaches to conduct the analysis: (1) obtain an average correlation matrix and fit the path model on the average correlation matrix; (2) fit the path model on each correlation matrix and meta-analyze the indirect and direct effects. We have compared the pros and cons of these two approaches in the following paper. The R code for the analysis…See More
There is only 1 study in many of these cells. It is not possible to estimate the heterogeneity variances.
pattern.na(MASEM$Data, show.na = FALSE) x1 x2 x3 x4 x5 x6 x7 x8 x9x1 4 2 1 1 …"
Are you using a fixed- or random-effects model? A complete study is only required in the fixed-effects model.
My guess is that there is not enough studies in the subset of your data.