Purpose: To estimate the misclassification rate of self-reported visual disabilities in a hospital-based population with known visual impairment. Methods: Subjects (N=570) were recruited among patients aged 50 years and more and classified to three categories of visual impairment level

approach with Lidstone’s Estimate. Our analysis allows the deeper understanding of decision tree classifiers, especially on how to estimate their misclassification rates using our equations. We propose a simple pruning algorithm based on our analysis and prove its superior properties, including its

Abstract. Using a mixture of two normal distributions, we estimate the false positive and false negative errors in the diagnosis of hypertension. Parameters in the mixture are estimated by the expectation-maximization (EM) algorithm. It is shown that both errors depend on cutoff points. Repeated measurements reduce both errors dramatically. The number of repeated measurements is recommended through a simulation study. 1

-one loss (misclassification rate) even when this assumption is violated by a wide margin. The region of quadratic-loss optimality of the Bayesian classifier is in fact a second-order infinitesimal fraction of the region of zero-one optimality. This implies that the Bayesian classifier has a much greater

modeling methods in the literature may not produce a useful balance between the two kinds of misclassification rates, especially when there are few faulty modules. This paper presents a practical classification rule in the context of classification tree models that allows appro-priate emphasis on each type

is at the same time computationally efficient. I then show how to use effect sizes to perform variable selection based on the misclassification rate, which is the data independent expectation of the prediction error. Simulation studies and real data analyses illustrate that the proposed effect size estimation

the misclassification rate (both false positives and negatives) through automatically up-weighting data sources that are most informative, while down-weighting less informative and biased sources. Extensive studies indicate that NBEL is significantly more robust than the classic naïve Bayes to unreliable, error

Abstract—A greedy technique is proposed to construct parsimonious kernel classifiers using the orthogonal forward selection method and boosting based on Fisher ratio for class separability measure. Unlike most kernel classification methods, which restrict kernel means to the training input data and use a fixed common variance for all the kernel terms, the proposed technique can tune both the mean vector and diagonal covariance matrix of individual kernel by incrementally maximizing Fisher ratio for class separability measure. An efficient weighted optimization method is developed based on boosting to append kernels one by one in an orthogonal forward selection procedure. Experimental results obtained using this construction technique demonstrate that it offers a viable alternative to the existing state-of-the-art kernel modeling methods for constructing sparse Gaussian radial basis function network classifiers that generalize well. Index Terms—Boosting, classification, Fisher ratio of class separability, forward selection, kernel classifier, orthogonal least square, radial basis function network. I.

), 20 % had>400 copies/mL. For children with WHO stage 1/2 HIV, misclassification as failure (met CD4 failure criteria, but VL undetectable) was 64 % for WHO 2006

This study compares the classification accuracy of linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), logistic regression (LR), and classification and regression trees (CART) under a variety of data conditions. Past research has generally found comparable performance of LDA and LR, with relatively less research on QDA and virtually none on CART. This study uses Monte Carlo simulations to assess the cross-validated predictive accuracy of these methods, while manipulating such factors as pre-dictor distribution, sample size, covariance matrix inequality, group separation, and group size ratio. The results indicate that QDA performs as well as or better than the other alternatives in virtually all conditions. Suggestions for practitioners are provided.