Dear colleagues,
I am working on an intervention study with 3 different groups of students. One group represents the intervention group and consists of a seminar with a practical phase and computer science content. Another group has only a theory seminar with computer science content and the last group has a seminar with other content. The last group is used to check how stable the constructs are. The 3 measurement points are equally spaced as pre-inter-post-tests in a quasi-experimental setting. Latent growth curve modelling doesn´t fit! Is there a method that uses the strength of the 3 measurement time points with a small sample size?
Thank you
Martin
Hi Martin,
can you tell the sample size(s) of the group? If a growth curve model doesn't fit, it is probably that the error covariances are related. Perhaps this could solve the problem.
See
Bollen, K. A., & Curran, P. J. (2004). Autoregressive latent trajectory (ALT) models A synthesis of two traditions. Sociological Methods & Research, 32(3), 336-383. doi:10.1177/0049124103260222
Usami, S., Murayama, K., & Hamaker, E. L. (2019). A unified framework of longitudinal models to examine reciprocal relations. Psychological Methods, 24(5), 637-657. l relations. Psychological Methods.
As an alternative, applying a GAM might be an opportunity:
Sullivan, K. J., Shadish, W. R., & Steiner, P. M. (2015). An introduction to modeling longitudinal data with generalized additive models: Applications to single-case designs. Psychological Methods, 20(1), 26.
Best,
--Holger
If each intervention seems to gives a monotonic score improvement ( pre to inter to post) then you could do linear regressions of change of score of individuals on time for each intervention and test differences in slope, .
The non-parametric equivalent of the repeated measures ANOVA is the ARTool and the f1.ld.f1 test from the nparLD R package (see attachment).
ARTool: http://depts.washington.edu/acelab/proj/art/index.html.
In attachment a script for your design including the non-parametric tests.
- Badges
- Science topic
- Similar topics
- Cell Biology
- Methods