Actual Error Rates in Classification of the T-Distributed Random Field Observation Based on Plug-in Linear Discriminant Function

In current paper a problem of classification of T-distributed random field observation into one of two populations specified by common scaling function is considered. The ML and LS estimators of themean parameters are plugged into the linear discriminant function. The closed form expressions for the Bayes error rate and the actual error rate associated with the aforementioned discriminant functions are derived. This is the extension of one for the Gaussian case. The actual error rates are used to evaluate and compare the performance of the plug-in discriminant function by means of Monte Carlo study.

[1]  Paul D. McNicholas,et al.  Model-based classification via mixtures of multivariate t-distributions , 2011, Comput. Stat. Data Anal..

[2]  K. Dučinskas,et al.  Approximation of the expected error rate in classification of the Gaussian random field observations , 2009 .

[3]  Paul Switzer,et al.  Extensions of linear discriminant analysis for statistical classification of remotely sensed satellite imagery , 1980 .

[4]  Nobumichi Shutoh.  An asymptotic expansion for the distribution of the linear discriminant function based on monotone missing data , 2012 .

[5]  K. Dučinskas,et al.  Multiclass classification of the scalar Gaussian random field observation with known spatial correlation function , 2015 .

[6]  Geoffrey J. McLachlan,et al.  Discrimination with autocorrelated observations , 1985, Pattern Recognit..

[7]  Michelle A. Steane,et al.  Model-Based Classification via Mixtures of Multivariate t-Factor Analyzers , 2012, Commun. Stat. Simul. Comput..

[8]  Weili Wu,et al.  Spatial contextual classification and prediction models for mining geospatial data , 2002, IEEE Trans. Multim..

[9]  Variable selection and error rate estimation in discriminant analysis , 1997 .

[10]  Dale L. Zimmerman,et al.  Optimal network design for spatial prediction, covariance parameter estimation, and empirical prediction , 2006 .

[11]  Noel A Cressie,et al.  Statistics for Spatial Data. , 1992 .

[12]  K. Dučinskas,et al.  Linear Discriminant Analysis of Multivariate Spatial–Temporal Regressions , 2005 .

[13]  Noel A. C. Cressie,et al.  Statistics for Spatial Data: Cressie/Statistics , 1993 .

[14]  K. Zografos,et al.  Errors of misclassification in discrimination of dimensional coherent elliptic random field observations , 2011 .

[15]  Kanti V. Mardia,et al.  Spatial discrimination and classification maps , 1984 .

[16]  Zhengyuan Zhu,et al.  Spatial sampling design under the infill asymptotic framework , 2006 .

[17]  Samuel Kotz,et al.  Estimation Methods for the Multivariate t Distribution , 2008 .

[18]  Henning Omre,et al.  T-distributed Random Fields : A Parametric Model for Heavy-tailed Random Fields , 2006 .

[19]  Peter J. Diggle,et al.  An Introduction to Model-Based Geostatistics , 2003 .

[20]  Kestutis Ducinskas,et al.  Comparison of ML and OLS Estimators in Discriminant Analysis of Spatially Correlated Observations , 2002, Informatica.

[21]  Leonidas Sakalauskas,et al.  Locally Homogeneous and Isotropic Gaussian Fields in Kriging , 2013, Informatica.

[22]  K. Mardia,et al.  Maximum likelihood estimation of models for residual covariance in spatial regression , 1984 .

[23]  Kestutis Ducinskas,et al.  Expected Bayes Error Rate in Supervised Classification of Spatial Gaussian Data , 2011, Informatica.

[24]  Brajendra C. Sutradhar,et al.  Estimation of the parameters of a regression model with a multivariate t error variable , 1986 .

[25]  Bani K. Mallick,et al.  A note on Bayesian spatial prediction using the elliptical distribution , 2003 .

[26]  M. Okamoto.  An Asymptotic Expansion for the Distribution of the Linear Discriminant Function , 1963 .