New answers tagged ordinal-data
0
votes
Dimension reduction to 1 ranked dimension
If your first component does not have this ranking, then it is a sign that your questionnaire isn't good and needs work.
There are other issues on using PCA on ordinal variables. These have been ...
- 125k
11
votes
Percentage changes versus absolute changes when comparing rankings
This question reminds me of this xkcd strip. All humor aside, comparing percentages which do not share the same basis (i.e. denominator) can be very misleading (as xkcd points out).
In addition, ...
- 3,312
2
votes
How to perform correlation & regression analysis using both 5-point likert scale and "Yes/No/Maybe" questionnaire?
One question I have is whether you consider your “Yes/Maybe/No” variable an “ordinal” such that Yes > Maybe > No. I assume that this is the case but my answer is in part contingent on this being ...
- 1,123
2
votes
How to perform correlation & regression analysis using both 5-point likert scale and "Yes/No/Maybe" questionnaire?
Ordinal logistic regression is the standard approach for this kind of data. We have many related threads on this topic. This one may be a good place to start:
Ordinal regression: logit, probit, ...
- 19.8k
4
votes
Can I retain the ordinal nature of a predictor while answering a question about it that is inherently binary?
To expand and complement Frank Harrell's answer:
Providing an answer to the binary question based on the full model
First, I think there is value in giving your collaborator a bit of pushback on ...
- 2,974
-2
votes
Can I retain the ordinal nature of a predictor while answering a question about it that is inherently binary?
I will go out on a limb here (but I feel that limb is pretty strong), and say that your predictor $X$ is a Likert score. It looks llike a Likert (ordinal), it walks like a Likert (5 levels), it quacks ...
- 3,312
11
votes
Accepted
Can I retain the ordinal nature of a predictor while answering a question about it that is inherently binary?
Binning X will make problems 1 and 2 worse. Comparison of X=1-3 vs. X=4-5 is inherently ill-defined and uninterpretable unless the relationship between X and Y is flat when X=1-3 and when X=4-5. ...
- 96.4k
6
votes
How to find out if there is a relationship between 6 independent variables and 3 dependent variables
"Paid in full", "Behind", and "No pay" are not three separate dependent variables. There is only one dependent variable here, which we can call "paid status". ...
- 19.8k
5
votes
Alternative to mixed-effect ordinal logistic regression for small sample sizes with missing categories
Binning temperature represents a grave statistical error that makes the other issues insignificant and greatly lowers your effective sample size. Use the final temperature as the dependent variable ...
- 96.4k
Top 50 recent answers are included