Skip to main content

Table 2 Reported measures of agreement: analytic framework

From: Validation of a case definition to define chronic dialysis using outpatient administrative data

  

Registry definition (Reference Standard)

 
  

+

-

Total

Administrative record

+

a

b

a+b

 

-

c

d

c+d

 

Total

a+c

b+d

N

  1. Abbreviations: a: true positives; b: false positives; c: false negatives; d: true negatives; N: total validation sample
  2. Positive agreement = 2a/[2a+b+c]
  3. The measure of agreement in positive cases; the number of true positives divided by all of the positives defined by both data sources. Positive agreement will show imbalance in the agreement between positive and negative responses.
  4. Sensitivity = a/(a+c)
  5. The proportion of those on dialysis according to the administrative data among those positive cases identified in reference standard. The ability of administrative data to correctly identify individuals on dialysis according to the reference standard
  6. Positive Predictive Value (PPV) = a/(a+b)
  7. The proportion of those on dialysis according to the reference standard among those positive cases identified in the administrative data
  8. Kappa = [(a+d)/N - ((a+b)(a+c) + (c+d)(b+d))/N2]/[1-((a+b)(a+c)+(c+d)(b+d))/N2]
  9. The agreement between the administrative data and reference standard above what is expected by chance
Back to article page