Hi everyone,
I am conducting a psychological experiment where participants have to judge either pairs of pictures of familiar objects or pairs of words representing familiar objects. There are three judging conditions: Posture (are the two objects are grasped for subsequent use in the same way?), Manipulation (are the two objects are manipulated ?), and function (are the two objects share the same function?). In each pair, the two objects/words can be compatible or incompatible.
To sum up, I have 3 within-subject factors:
- task (posture, manipulation, function)
- modality (word and pictures)
- compatibility (compatible and incompatible)
and 1 continuous DV = reaction times
I have another factor which is the rating for the visual similarity (lickert scale: range = 1-5) between the two objects of a pair. I would like to know how this visual similarity may influence RTs via compatibility or/and task. For instance, RTs may vary according to the task but it is may be possible that the visual shape of the objects influences more one condition (posture) than the others (manipulation and function).
I would like to use a linear mixed model and I guess my initial model is:
mod1
Hi,
Likert scale values are strictly Ordinal values as the distance between a point and the subsequent point is not measured. In such a case it a fixed effect.
Some of the researchers use the total or subscale values as a continuous variable, then in such a case, it could be a Random effect.
Dear Mathieu Lesourd. I would say it depends on your research question. If you are interested in estimating each category within Visual shape, I would interpret it as a fixed effect. The random structure, are you thinking about the covariance structure for visual shape as a random effect? Here, I think the best is to try out different structures and test which gives the best model fit. All the best
See these links:
https://www.theanalysisfactor.com/specifying-fixed-and-random-factors-in-mixed-models/
https://stats.idre.ucla.edu/other/mult-pkg/introduction-to-linear-mixed-models/
https://www.researchgate.net/post/How-to-define-fixed-and-random-factors-in-a-linear-mixed-model
- Badges
- Science topic
- Similar topics
- Correction