Updating a discriminant function in basis of unclassified data

The problem of updating a discriminant function on the basis of data of unknown origin is studied. There are observations of known origin from each of the underlying populations, and subsequently there is available a limited number of unclassified observations assumed to have been drawn from a mixture of the underlying populations. A sample discriminant function can be formed initially from the classified data. The question of whether the subsequent updating of this discriminant function on the basis of the unclassified data produces a reduction in the error rate of sufficient magnitude to warrant the computational effort is considered by carrying out a series of Monte Carlo experiments. The simulation results are contrasted with available asymptotic results.

[1]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[2]  M. E. Muller,et al.  A Note on the Generation of Random Normal Deviates , 1958 .

[3]  H. O. Hartley,et al.  Classification and Estimation in Analysis of Variance Problems , 1968 .

[4]  N. E. Day.  Estimating the components of a mixture of normal distributions , 1969 .

[5]  S. John,et al.  On Identifying the Population of Origin of Each Observation in a Mixture of Observations from Two Normal Populations , 1970 .

[6]  A. Scott,et al.  Clustering methods based on likelihood ratio criteria. , 1971 .

[7]  D. Hosmer.  A Comparison of Iterative Maximum Likelihood Estimates of the Parameters of a Mixture of Two Normal Distributions Under Three Different Types of Sample , 1973 .

[8]  G. McLachlan.  Iterative Reclassification Procedure for Constructing An Asymptotically Optimal Rule of Allocation in Discriminant-Analysis , 1975 .

[9]  F. Marriott.  389: Separating Mixtures of Normal Distributions , 1975 .

[10]  D. M. Titterington,et al.  Updating a Diagnostic System using Unconfirmed Cases , 1976 .

[11]  Patrick L. Odell,et al.  Concerning several methods for estimating crop acreages using remote sensing data , 1976 .

[12]  P. Odell.  Current and past roles of the statistician in space applications , 1976 .

[13]  S. Sclove.  Population mixture models and clustering algorithms , 1977 .

[14]  G. McLachlan.  Estimating the Linear Discriminant Function from Initial Samples Containing a Small Number of Unclassified Observations , 1977 .

[15]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[16]  Terence J. O'Neill.  Normal Discrimination with Unclassified Observations , 1978 .

[17]  D. Titterington,et al.  Estimation Problems with Data from a Mixture , 1978 .

[18]  G. McLachlan,et al.  The efficiency of a linear discriminant function based on unclassified initial samples , 1978 .

[19]  Roderick J. A. Little,et al.  Consistent Regression Methods for Discriminant Analysis with Incomplete Data , 1978 .

[20]  Peter Bryant,et al.  Asymptotic behaviour of classification maximum likelihood estimates , 1978 .

[21]  A. D. Gordon.  A measure of the agreement between rankings , 1979 .

[22]  P. Switzer.  Extensions of linear discriminant analysis for statistical classification of remotely sensed satellite imagery. Technical report No. 30 , 1979 .

[23]  G. McLachlan,et al.  Small sample results for a linear discriminant function estimated from a mixture of normal populations , 1979 .

[24]  Geoffrey J. McLachlan,et al.  A case study of two clustering methods based on maximum likelihood , 1979 .

[25]  J. Anderson.  Multivariate logistic compounds , 1979 .

[26]  Geoffrey J. McLachlan,et al.  A Comparison of the Mixture and Classification Approaches to Cluster-Analysis , 1980 .

[27]  Geoffrey J. McLachlan,et al.  Some Efficiency Results for the Estimation of the Mixing Proportion in a Mixture of 2 Normal-Distributions , 1981 .