For example a scale on group cohesion has three dimensions that are: task cohesion, social cohesion and interpersonal attraction to the group and they have a score for each dimension but no total score for group cohesion. Does this mean it is a categorical variable?
Hello Prathiksha,
It DOES depend. For example. I am using DASS-21 scale comprising of 3 subscales (depression, anxiety, stress). Each subscale has 7 questions and scores range from 0 to 21. So then it is NOT a categorical variable but continuous. You have mentioned a scale in your research and I presume any dimensions has more than one or two items to measure... Hope it helps a bit
Prathiksha,
Each variable that has a Likert scale is categorical. If all variables together form a measure, then they could be combined as a single score. The score would have to be tested for normality and then validated for specific populations.
A Likert scale is the sum of responses on several Likert items. Whether the Likert items are interval-level data or whether they are ordinals data it is a hot topic in the literature, to the extent to which Likert items are interpreted as being ordinal data ( We can not add ordinal data )
The question are these dimensions are independent? In your case I think the answer is yes. You could treated each dimension independently to your objectives whether to use it as ratio variable (continuous) or you could generate your ordinal variables to each dimension. But I am agree with Joan it depend completely to your objectives
Dear Prathiksha,
the attached article might be of interest for you.
Best regards,
Felix
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics