Diff for "FAQ/criteria" - CBU statistics Wiki
location: Diff for "FAQ/criteria"
Differences between revisions 7 and 8
Revision 7 as of 2006-07-25 15:04:50
Size: 1116
Editor: pc0082
Comment:
Revision 8 as of 2006-07-25 15:08:51
Size: 1222
Editor: pc0082
Comment:
Deletions are marked like this. Additions are marked like this.
Line 1: Line 1:
Describe FAQ/criteria here.
For 2 x 2 tables there are four terms used to summarise the classification table
of observed and predicted group membership outputted by discriminant procedures
such as binary logistic regression.
For 2 x 2 tables there are four terms used to summarise the classification table of observed and predicted group membership outputted by discriminant procedures such as binary logistic regression.
Line 6: Line 3:
Let’s call the two groups positive (+) and negative (-) then Let’s call the two groups positive (+) and negative (-) with classification table given below.
Line 8: Line 5:
The following four quantities are often quoted and asked for by journals as a means of evaluating the sharpness of the model fit in the two group case.
Line 14: Line 10:

The following four quantities are often quoted and asked for by journals as a means of evaluating the sharpness of the model fit in the two group case.
Line 15: Line 13:
Sensitivity = a/(a+c)= proportion of those who are really +
who test +
 * Sensitivity = a/(a+c)= proportion of those who are really + who are predicted to be +
Line 18: Line 15:
Specificity = d/(b+d) = proportion of those who are really -
who test -
 * Specificity = d/(b+d) = proportion of those who are really - who are predicted to be -
Line 21: Line 17:
PPV = a/(a+b) = proportion of those who tested + who really are +  * Positive Predictive Value (PPV) = a/(a+b) = proportion of those predicted as + who really are +
Line 23: Line 19:
NPV = d/(c+d) = proportion of those who tested - who really are -  * Negative Predictive Value (NPV) = d/(c+d) = proportion of those predicted as - who really are -

For 2 x 2 tables there are four terms used to summarise the classification table of observed and predicted group membership outputted by discriminant procedures such as binary logistic regression.

Let’s call the two groups positive (+) and negative (-) with classification table given below.

True

+

-

Pred

+

a

b

-

c

d

The following four quantities are often quoted and asked for by journals as a means of evaluating the sharpness of the model fit in the two group case.

  • Sensitivity = a/(a+c)= proportion of those who are really + who are predicted to be +
  • Specificity = d/(b+d) = proportion of those who are really - who are predicted to be -
  • Positive Predictive Value (PPV) = a/(a+b) = proportion of those predicted as + who really are +
  • Negative Predictive Value (NPV) = d/(c+d) = proportion of those predicted as - who really are -

None: FAQ/criteria (last edited 2015-02-02 14:34:05 by PeterWatson)