Efficiency of discriminant analysis when initial samples are classified stochastically
Pattern RecognitionPublished 1 January 1990
T. Krishnan, Subhas C. Nandy
Citations14
SJR quartileQ1
SJR score2.06
SNIP2.67
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The Efron efficiency of this procedure compared to the situation where the initial classification is done deterministically and correctly is studied, which concludes that stochastic supervision contains a great deal of information on the discriminant function.
Abstract
We consider the problem of discriminant analysis of two multivariate normal populations having a common dispersion matrix, where the initial samples are classified stochastically. We assume a beta model for this classification variable and assume it to be independent of the feature vector X, given the group. We study the Efron efficiency of this procedure compared to the situation where the initial classification is done deterministically and correctly. We present tables and charts of this efficiency and conclude that stochastic supervision contains a great deal of information on the discriminant function.
Keywords
Computer ScienceMathematics
Journal of the Royal Statistical Society Series B (Statistical Methodology)Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm
49,657 Citations1977A. P. Dempster, N. M. Laird +1 more
Digital Access to Scholarship at Harvard (DASH) (Harvard University)Maximum Likelihood from Incomplete Data via the EM Algorithm
4,523 Citations1977Dempster, Arthur P., Laird, Nan M. +1 more
Journal of the American Statistical AssociationThe Efficiency of Logistic Regression Compared to Normal Discriminant Analysis
541 Citations1975Bradley Efron
This article computes the asymptotic relative efficiency of the two procedures used to estimate Fisher's discriminant by maximum likelihood and assign x on the basis of the estimated discriminant, a method known as the normal discrimination procedure.
Journal of the American Statistical AssociationNormal Discrimination with Unclassified Observations
144 Citations1978Terence J. O’Neill
Journal of the American Statistical AssociationThe Efficiency of Logistic Regression Compared to Normal Discriminant Analysis
110 Citations1975Bradley Efron
TechnometricsDiscriminant Analysis When the Initial Samples are Misclassified II: Non-Random Misclassification Models
50 Citations1974Peter A. Lachenbruch
Sampling studies show that the actual error rates of the rules from samples with initial misclassification are only slightly affected; the apparent error rates, obtained by resubstituting the observations into the calculated discriminant function, are drastically affected, and cannot be used.
Journal of the American Statistical AssociationNormal Discrimination with Unclassified Observations
42 Citations1978Terence J. O’Neill
Journal of the American Statistical AssociationLinear Discriminant Analysis with Misallocation in Training Samples
42 Citations1984Raj S. Chhikara, Jim McKeon
BiometrikaStatistical diagnosis when basic cases are not classified with certainty
41 Citations1976J. Aitchison, Colin B. Begg
The theory provides a generalization of current statistical diagnostic techniques and its relationship to these is discussed and a central part of the analysis is concerned with the reduction of such assessments to simpler, more interpretable forms.
Pattern RecognitionEfficiency of learning with imperfect supervision
15 Citations1988T. Krishnan
Efron's Asymptotic Relative Efficiency is derived of the discriminant function estimated under this model, relative to the case when classification is perfect, and it is shown that training samples are useful even if prone to a certain amount of misclassification.
Journal of the American Statistical AssociationLinear Discriminant Analysis with Misallocation in Training Samples
14 Citations1984Raj S. Chhikara, Jim McKeon
TechnometricsDiscriminant Analysis When the Initial Samples Are Misclassified II: Non-Random Misclassification Models
13 Citations1974Peter A. Lachenbruch
Pattern RecognitionDiscriminant analysis with a stochastic supervisor
10 Citations1987T. Krishnan, Subhas C. Nandy
The EM algorithm for maximum likelihood estimation of the parameters for linear discriminant analysis for two p -variate normal distributions with a common covariance matrix is derived.
Pattern RecognitionPattern recognition with an imperfect supervisor
9 Citations1989U.A. Katre, T. Krishnan
The likelihood equations for this case are derived and some ways of solving them to estimate parameters are discussed and results of computations with various choices of initial values of parameters in iterative procedures of estimation are reported.
Pattern RecognitionAn alternative stochastic supervisor in discriminant analysis
9 Citations1989D. M. Titterington
A model for a stochastic supervisor that is an alternative to the model proposed, for the 2-group case, by Krishnan and Nandy and results in a simple EM algorithm for parameter estimation.