confidence interval interpretation (diagnostic tests)

#1
If the 95% confidence interval for a relative risk (RR) or an odds ratio (OR) crosses 1, then this is taken as no evidence of an effect = NO STATISTICAL SIGNIFICANCE. DOES IT APPLY TO CONFIDENCE INTERVALS FOR DIAGNOSTIC VALUES (Se, Sp and accuracy)?
Exemple: Se=0.89 CI95% 0.78 -1.07
 

Dragan

Super Moderator
#2
If the 95% confidence interval for a relative risk (RR) or an odds ratio (OR) crosses 1, then this is taken as no evidence of an effect = NO STATISTICAL SIGNIFICANCE. DOES IT APPLY TO CONFIDENCE INTERVALS FOR DIAGNOSTIC VALUES (Se, Sp and accuracy)?
Exemple: Se=0.89 CI95% 0.78 -1.07
In general, it may or may not. It depends on what a particular parameter is specified to be under a null hypothesis, e.g. it could be 1 or some other value.