I'm performing a diagnostic method comparison study in which I have 2 groups; one assessed using the experimental method, and one assessed using the standard method. These groups are matched, with 3 standard per experiment.
Continous variables measured are not normally distributed, and data is matched, thus I'm opting for the Wilcoxon matched-pair signed-rank test to compare variables between the groups.
Now, in Stata every command for comparison of groups (ttest, ranksum...) allows the by(group) option, but not -signrank- !
For example: ranksum age, by(cohort)
if I want to compare the age distribution between the groups (defined by var cohort). But -ranksum- is for unmatched data!
Thus, my question is how to, similarly to ranksum, perform -signrank- with a by(groupvar) option? -signrank- doesn't allow this by default.
Is there a user-written command for this?
I've seen the -reshape- command being used, but I'm not used to that and I don't really know how to use it.
Hello Rasmus. I suggest that you post your question to the Statalist forum (see the link below). And when you do, please pay attention to the advice in the FAQ about using -dataex- (and CODE tags) to generate a small sample dataset. Having the data usually makes things much clearer to people, and that makes it much more likely someone will be able to help you. HTH.
- https://www.statalist.org/forums/forum/general-stata-discussion/general
- https://www.statalist.org/forums/help
Probably you should see how you have entered the data in STATA. The data needs to be entered in 'wide' format.
Given that your data is in long format (i.e., cohort data has been entered consecutively and not paired side by side) with id's in corresponding order (i.e., id1 in cohort1 matches id1 in cohort2) I would follow Inaamul Haq's remark and
sort cohort
reshape wide X, i(id) j(cohort)
Then you could test the equality of matched pairs using
signrank X1 = X2
Also, have a look at here:
https://www.statalist.org/forums/forum/general-stata-discussion/general/1344903-running-signrank-with-by-groupvar-option
FYI, Rasmus Walter Green did post this question to Statalist. Those who wish to follow that discussion can do so here:
- https://www.statalist.org/forums/forum/general-stata-discussion/general/1483215-wilcoxon-matched-pair-sign-rank-test-signrank-with-a-grouping-variable-by-groupvar
Hi, You can search the following test on the internet:
sign test in stata
or
run command signrank depvarforgroup1= depvarforgroup2
- Badges
- Science topic