Hi there,
I am carrying out a study on factors affecting electric vehicle adoption. I am using a likert scale format (from strongly disagree to strongly agree) for all of the predictor variable such as price or range anxiety and then a continuous dependent variable (the likelihood they believe they will adopt EVs).
I would assume to treat it strictly as ordinal and non-parametric but I have seen some sources say you can use parametric tests if your DV is continuous.
I have to bear in mind i am doing a second regression analysis where I add in demographic variables on top of predictors . Could anyone assist me with what is preferred in statistics in my case?
Thank you in advance
Hello Thomas,
Are you using individual item responses as your variables? If so, it is safer to treat them as ordinally-scaled values rather than interval-scaled values. If, however, you're combining multiple, related item responses into a (summated) total score, then many folks would treat this as a pseudo-continuous variable. Indeed, that is the approach that Rensis Likert described in his 1932 monograph.
You could certainly use an ordinal regression approach (with individual item responses as variables).
Good luck with your work.
Hi there David,
Yes all but one are individual item responses so I am going to treat them as ordinally-scaled and use non-parametric tests.
I would have used ordinal regression but I have used a continuous scale for my dependent variable and so will use multiple regression (I didn't have prior knowledge of ordinal regression). I assume there's no real issue in me using that method?
In hindsight I perhaps should have used an ordinal scale for my DV and used ordinal regression but that will now form part of my evaluation.
Thank you for your help and good wishes
David Morse I am now coming to run the regression through spss. What test of fit should I use? I assumed I would use Pearson's chi-square test as I am treating it as ordinally-scaled. However my dependent variable is a continuous scale. Will this adversely affect that test?
I have read that ch-square assumes all data to be ordinal.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Regression