Table 2.

Logistic regression analysis with random effects

Random effects
Groups name	Variance	Standard deviation
Clinical site (intercept)	0.1371	0.3703
Number of observations, 2880; groups: site, 25
Fixed effects
	Estimate	Standard error	Z value	Pr (>|z|)
(Intercept)	− 2.734	0.16884	− 16.192	< 2e–16***
Pre-test probability	3.04813	0.19998	15.243	< 2e–16***
Method (original D+F or updated D+F 2011)	0.43833*	0.09312	4.707	2.51e–06***
Correlation of fixed effects
	(Intercept)	Pre-test probability
Pre-test probability	− 0.818
Method (original D+F or updated D+F 2011)	− 0.566	0.392

We performed a logistic regression analysis with the outcome (prevalence; CAD or no CAD) as dependent and the respective pre-test probability and the method of computation as predictors using the stacked data set (method original D+F versus updated D+F 2011). In order to take care of the variability between sites, we applied a random intercept for site. There is a significant effect of the method with a coefficient equal to 0.44, corresponding to an odds ratio of 1.55 (95% CI 1.29, 1.86). Significance codes: 0 = ‘***’, 0.001 = ‘**’, 0.01 = ‘*’, 0.05 = ‘.’ 0.1 = ‘ ’ 1; *Statistical significance