Skip to main content

Table 5 Ensemble outlier detection results for the TNBC dataset (mean values for the number of variables selected, MSE and misclassifications for the random strategies are presented)

From: Ensemble outlier detection and gene selection in triple-negative breast cancer data

  TNBC original data Random patients Random variables
  LOGIT-EN SPLS-DA SGPLS LOGIT-EN
Variables selected 107 2945 551 82 65
MSE 0.020 0.025 0.084 0.032 0.035
Misclassifications 16 29 23 35 41
Parameter (α) 0.9 0.8 0.7 0.7 0.7
Parameter (L) - 4 4 - -
Resampling number - 100 100
Influential observations 24 40 37
Suspect (influential) observations 2 6 6