Hello,
I have a question regarding which statistical test to use for my study and would really appreciate any advice.
I have a DEPENDENT VARIABLE which is a diet quality score that is based on quartile groups so ordinal (quartile 1, quartile 2, quartile 3, quartile 4). My INDEPENDENT VARIABLE is BMI, Weight, Waist circumference so continuous.
I want to conduct a test to see if there are any significant differences between the quartile groups and the independent variables.
Which statistical test should I conduct?
I have read that ANOVA is not appropriate because you need DEPENDENT VARIABLE which is continuous and an INDEPENDENT VARIABLE which is categorical (which is the reverse in my case).
Any help would be great.
Thanks!
Dear Emily,
Like Salvatore, i also think, ordinal logistic regression is the option for you.
Best,
Praheli
I agree with Salvatore S. Mangiafico .
In olden times we had to decide whether Ordered Logit or Ordered Probit were more appropriate. (There are some theoretical reasons for one over the other, but in practice they're interchangeable.)
Fortunately, nowadays, both approaches are applied in the one routine, and you can take your pick depending on what works best.
Check this How-To: https://www.statisticssolutions.com/ordinal-regression-2/
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA