Skip to main content

Advertisement

Table 7 Classification results

From: Extraction decision and identification of treatment predictors in Class I malocclusions

  Treatment Predicted group membership Total
Non-extraction Extraction
Original Count Non-extraction 377 20 397
Extraction 67 78 145
% Non-extraction 95.0 5.0 100.0
Extraction 46.2 53.8 100.0
Cross-validateda Count Non-extraction 376 21 397
Extraction 67 78 145
% Non-extraction 94.7 5.3 100.0
Extraction 46.2 53.8 100.0
  1. aCross-validation is done only for those cases in the analysis. In cross-validation, each case is classified by the functions derived from all cases other than that case; 83.9% of original and 83.8% of cross-validated grouped cases were correctly classified. The proportional by chance accuracy rate was computed by squaring and summing the proportion of cases in each group from the table of prior probabilities for groups (0.732 + 0.272 = 0.607). A 25% increase over this would require that our cross-validated accuracy be 75.8% (1.25 × 60.7 % = 75.8%). The cross-validated accuracy rate computed by SPSS was 83.8% which was greater than the proportional by chance accuracy criteria of 75.8%.