Page 1 of 1

Variable rated between 1 to 7

Posted: Tue Nov 19, 2019 9:23 pm
by MaFa
Hi all,

Do you know how we should include a variable that has been rated by survey respondents (e.g. from 1 to 7) in SEM as a moderator? Will this be considered as categorical? The variable can represent two situations actually; low values, for example, represents situation 1 and high values show situation 2.
I appreciate any help.
Thanks

Re: Variable rated between 1 to 7

Posted: Wed Dec 04, 2019 10:49 am
by jmbecker
Usually, researchers treat those 7-point Likert scales as quasi-metric and thus continuous. That would suggest using an interaction effect approach. In contrast, dichotomization using high and low values, for example, using a median split might lose information and is generally seen less favorably.
When you really think it is categorical, you would want to treat each category as a separate group.