Comparison group?

Question

I am using the logistic.display function in the epiDisplay package. I have a question about output. With multiple variables, it is easy to interpret the comparison group. However, when using two variables, which one is the comparison group? In my output, is it male or female?

Logistic regression predicting Height : >6 ft vs <=6 ft

                                          OR(95%CI)        P(Wald's test) P(LR-test)
intst: male vs female     1.4 (1.25,1.86)  < 0.001        < 0.001   

Log-likelihood = -7107.9317
No. of observations = 650
AIC value = 124521.6543

It's easier to help you if you include a simple [reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) with sample input and desired output that can be used to test and verify possible solutions. — MrFlick, Feb 10 '20 at 20:48
I just need to know in the output if the reference group is males or females. Is the statement males are 1.4 times more likely to be 6ft taller or females are 1.4 times more likely to be 6 ft taller. — Nick, Feb 10 '20 at 20:53
you might want to ask on https://stats.stackexchange.com/ or https://datascience.stackexchange.com/ . There might be info in the docs for the package, too. — jeffhale, Feb 11 '20 at 02:25

score 1 · Accepted Answer · answered Feb 10 '20 at 21:30

Based on the phrasing, in "A vs B", I would guess B is the reference group, so males have 1.4 times the odds of females to be > 6ft.

To be sure, look in your data and see what is the first factor level for you sex variable---the first factor level will be the reference level. If you haven't set it explicitly, the factor levels will be in alpabetical order. Since "f" comes before "m", this also points to female being the reference group.

Comparison group?

1 Answers1