Discriminant Analysis When the Initial Samples Are Misclassified

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning kernel logistic regression in the presence of class label noise (2014, background): “Part of the reason for this may be that uniform/symmetric label noise is relatively harmless [21,22,12,27].”
Multi-class classification in the presence of labelling errors (2011, background): “Often, such assumption does not hold, though (see [2, 3, 4, 5] for examples).”
Statistical fraud detection: A review (2002, background): “Some work has addressed misclassification of training samples (e.g., Lachenbruch, 1966, 1974; Chhikara and McKeon, 1984), but not in the context of fraud detection as far as we are aware.”
Linear discriminant analysis with misallocation in training samples (1984, methodology): “Assuming that training samples are randomly misallocated, Lachenbruch (1966) and McLachlan (1972) studied R 1 and R2 for their expected values and variances.”
Discriminant Analysis When the Initial Samples are Misclassified II: Non-Random Misclassification Models (1974, background): “INTR~DUOTI~N Lachenbruch (1966) studied the effects of mis- classification of the initial samples on the performance of the linear discriminant function (LDF).”
Supervised machine learning: A brief primer (2020, background): “Label noise has been shown to lead to inaccurate predictor selection and rankings (Frénay et al., 2014; Gerlach & Stamey, 2007; Shanab et al., 2012) and to decrease prediction performance (Lachenbruch, 1966; Nettleton et al., 2010; Wilson & Martinez, 2000).”