3.6 GEE Models

Correlated observations can be handled using GEE

 rm_uvsum(response = 'size_change',
 covs=c('time','ctdna_status'),
 gee=TRUE,
 id='id', corstr="exchangeable",
 family=gaussian("identity"),
 data=ctDNA,showN=TRUE)

	Estimate(95%CI)	p-value	Global p-value	N
time	-0.12 (-0.44, 0.19)	0.44		262
ctdna status			<0.001	262
Clearance	Reference			134
No clearance, decrease from baseline	61.29 (37.38, 85.20)	<0.001		42
No clearance, increase from baseline	82.52 (64.67, 100.37)	<0.001		86