Should i use McNemar's for a matched-pair study?

#1
Hello,

I have an age & sex matched-group of patients.

Control group and study group both had the same operations. Control group had no intraoperative fracture complication. Study group had intra-operative fracture complication. Study group also has two subgroups (two different surgical approaches).

All patients had preoperative and postoperative outcome measurement (out of 100 points).

Should i use Mc Nemar's for control - study group, and also subgroup comparison for clinical outcome measurements?

Thank you for your interest.
 

Karabiner

TS Contributor
#5
There is no use for McNemar's test here. McNemar's is for
binary response variables, but you have a 0-100 score here.

Moreover, a matched pairs analysis would be unusua. You
could use a mixed ANOVA with time of measurement
as repeated measures factor and group as between-subjects factor.

With kind regards

Karabiner
 
#6
There is no use for McNemar's test here. McNemar's is for
binary response variables, but you have a 0-100 score here.

Moreover, a matched pairs analysis would be unusua. You
could use a mixed ANOVA with time of measurement
as repeated measures factor and group as between-subjects factor.

With kind regards

Karabiner
Thank you. I hope i can deal with that suggestion.
Do you mind suggesting some reading about it?
 

hlsmith

Omega Contributor
#7
What are the average scores? If the aren't around 50 or have quite a bit of dispersion, linear regression approaches can have problems. This is due to value being contained within 0 and 100.
 

hlsmith

Omega Contributor
#9
What is the standard deviation of these values, the issue would be that say + 2(std) may be something like 30, which would not be possible if the top value has to be contained within 100.

Are the scores a percentage, if so you may want to investigate beta regression.