Measuring agreement between healthcare survey instruments using mutual information

Table 6 Agreement/disagreement between two instruments using three measures

Data set	Measure
Data set	Odds ratio	Cohen’s kappa	Local mutual information
(Table 2 in Shulman et al. 1986) Clock exam and MMSE^a	15.6	0.493	Agreement (0.422 in I _agreement, -0.212 in I _disagreement)
(Figure 1 in Russell et al. 2012) BDI^b + CDRS_R^c and ICD-10^d	∞**	0.693	Agreement (0.18 in I _agreement, -0.03 in I _disagreement)
(Figure 1 in Russell et al. 2012) CDRS_R and ICD-10	0.311*	-0.015*	Inconclusive ( -0.018 in I _agreement, 0.024 in I _disagreement)
(Table 4 in Seago 2002) Score scheme comparison	4	0.265	Agreement ( 0.152 in I _agreement, -0.107 in I _disagreement)

(Note: * insignificant at confidence level = 95 %, ** Infinity since one of the cells contains 0, ^aMini mental state examination, ^bBeck Depression Inventory, ^cChildren’s Depression Rating Scale-Revised, ^dInternational Classification Disease – 10 clinical interview)

ISSN: 1472-6947