Garst posted on Tuesday, January 27, 2004 - 12:49 pm
Dear Prof. Muthen,
I recall that you once wrote that random slopes are hard to predict by external variables. Now I want to cite you in an article, but unfortunately I can't find the statement anymore. The contributions you made to the literature is so vast, that maybe you can help me finding the source of the disappointing R2 for predicting slopes.
Bmuthen posted on Tuesday, January 27, 2004 - 5:14 pm
This is my data analysis experience. I don't think I have written it anywhere quotable.
Consistently throughout my growth modelling of different psychiatric attributes, I've become aware that intercept effects far outweigh slope effects, both as direct predictors and as mediators. I would be grateful if you would confirm that this is to be expected, in your experience. Thanks for your time.
That seems to be a common finding. See also the paper on our website:
Muthén, B., Khoo, S.T., Francis, D. & Kim Boscardin, C. (2003). Analysis of reading skills development from Kindergarten through first grade: An application of growth mixture modeling to sequential processes. Multilevel Modeling: Methodological Advances, Issues, and Applications. S.R. Reise & N. Duan (Eds). Mahaw, NJ: Lawrence Erlbaum Associates, pp.71-89. download paper contact first author show abstract