2
$\begingroup$

I have have a dataset of about 500k subjects, each subject have 2 measures of the same thing:

measures A: in which 0 is the worst case and 1 is the best case.

measures B: in witch ordinal variable with values 0,1,2,3 in which 0 is the worst case and 4 is the best case.

I want check if the two measures are consistent witch each other, is there statistical procedure to do it?

Edit: by consistent I mean that people that are in the best case in the measure A tend to have higher values in the measure B, And people in the worst case in the measure A tend to have lower values in the measure B.

Improve this question
$\endgroup$
2
  • $\begingroup$ What do you mean by "consistent". $\endgroup$
    – Galen
    Commented Mar 24 at 14:27
  • $\begingroup$ @Galen, thanks for the answer I hope it is more clear now. $\endgroup$
    – data student
    Commented Mar 24 at 14:34

1 Answer 1

Reset to default
2
$\begingroup$

Probably you want some measure of correlation, this is what your definition of consistency measures. For comparing the most relevant alternatives, see How to choose between Pearson and Spearman correlation?

Improve this answer
$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.