How evaluate the agreement of: real diagnosis (1-true,0-false) and diagnosis prognosis (1-true,0-false) /JMP 10/

[#1]

I have three var:

ID patients

D (real Diagnosis): 1-true, 0-false

and

P (Prognosis of diagnosis): 1-true, 0-false.

How evaluate D and P agreement?

I know about cohen's kappa ("Analyze > Quality and Process > Variability / Attribute Gauge Chart").

Do I correctly organized data?

Gr  Y1 Y2

1   0    D

2   1    D

3   1    D

4   0    D

5   0    D

6   1    P

7   0    P

8   1    P

9   1    P

10  1   P

[#2 · Accepted solution]

Your three variables should be your three columns: ID, Diagnosis, Prognosis.

In the diagnosis and prognosis column you would have your 1/0 or true/false, value for each subject.

ID     Diagnosis     Prognosis

1          True          False

2          Ture          True

etc....

Then you can start with fit y-by-x to compare the diagnosis to the prognosis (both columns should be categorical so that you get a mosaic plot and a cross-tabs table). From there look at the JMP documentation on fit y-by-x for agreement statistics.  You may also wish to google "FDA guidance on reporting diagnostic tests" for further insight to the types of analyses you might want to run with regard to diagnostic tests.

[#3]

Oh, it turns out y-by-x has "Agreement statistics"! But that is not cross-tabulation analysis, is not it? Thanks, Karen! P.S. "FDA guidance..." Oh, it's interesting!