Multiple dependent state sampling plans for lot acceptance based on measurement data

This paper proposes a multiple dependent (or deferred) state sampling plan by variables for the inspection of normally distributed quality characteristics. The decision upon the acceptance of the lot is based on the states of the preceding lots (dependent state plan) or on the states of the forthcoming lots (deferred state plan). The lot acceptance probability is derived and the two-point approach to determining the plan parameters is described. The advantages of this new variables plan over conventional sampling plans are discussed. Tables are constructed for the selection of parameters of this plan under the specific values of the producer’s and consumer’s risks, indexed by acceptable quality level and limiting quality level, when the standard deviation is known or unknown.     

Optimal training sample allocation and asymptotic expansions for error rates in discriminant analysis

The sample-based rule obtained from Bayes classification rule by replacing the unknown parameters by ML estimates from a stratified training sample is used for the classification of a random observationX into one ofL populations. The asymptotic expansions in terms of the inverses of the training sample sizes for cross-validation, apparent and plug-in error rates are found. These are used to compare estimation methods of the error rate for a wide range of regular distributions as probability models for considered populations. The optimal training sample allocation minimizing the asymptotic expected error regret is found in the cases of widely applicable, positively skewed distributions (Rayleigh and Maxwell distributions). These probability models for populations are often met in ecology and biology. The results indicate that equal training sample sizes for each populations sometimes are not optimal, even when prior probabilities of populations are equal.     

Estimates of E-capacity and capacity regions for Multiple-access Channel With Random Parameter

The discrete memoryless multiple-access channel with random parameter is investigated. Various situations, when the state of the channel is known or unknown on the encoders and decoder, are considered. Some bounds of E-capacity and capacity regions for average error probability are obtained.     

Extended rough set model based on known same probability dominant valued tolerance relation

Classical rough set theory is based on the conventional indiscernibility relation. It is not suitable for analyzing incomplete information. Some successful extended rough set models based on different non-equivalence relations have been proposed. The data-driven valued tolerance relation is such a non-equivalence relation. However, the calculation method of tolerance degree has some limitations. In this paper, known same probability dominant valued tolerance relation is proposed to solve this problem. On this basis, an extended rough set model based on known same probability dominant valued tolerance relation is presented. Some properties of the new model are analyzed. In order to compare the classification performance of different generalized indiscernibility relations, based on the category utility function in cluster analysis, an incomplete category utility function is proposed, which can measure the classification performance of different generalized indiscernibility relations effectively. Experimental results show that the known same probability dominant valued tolerance relation can get better classification results than other generalized indiscernibility relations.     

An Efficient Algorithm for Bayesian Nearest Neighbours

K-Nearest Neighbours (k-NN) is a popular classification and regression algorithm, yet one of its main limitations is the difficulty in choosing the number of neighbours. We present a Bayesian algorithm to compute the posterior probability distribution for k given a target point within a data-set, efficiently and without the use of Markov Chain Monte Carlo (MCMC) methods or simulation—alongside an exact solution for distributions within the exponential family. The central idea is that data points around our target are generated by the same probability distribution, extending outwards over the appropriate, though unknown, number of neighbours. Once the data is projected onto a distance metric of choice, we can transform the choice of k into a change-point detection problem, for which there is an efficient solution: we recursively compute the probability of the last change-point as we move towards our target, and thus de facto compute the posterior probability distribution over k. Applying this approach to both a classification and a regression UCI data-sets, we compare favourably and, most importantly, by removing the need for simulation, we are able to compute the posterior probability of k exactly and rapidly. As an example, the computational time for the Ripley data-set is a few milliseconds compared to a few hours when using a MCMC approach.

     

On linear classification procedures between two categories with known mean vectors and covariance matrices

Summary This paper is concerned with probabilities (error probabilities), caused by misclassification, of linear classification procedures (linear procedures) between two categories, whose mean vectors and covariance matrices are assumed to be known, while the distribution of each category may well be continuous or discrete. The tightest upper bounds on the largest of two kinds of error probability of each linear procedure and on the expected error probability for any apriori probabilities are obtained. Moreover in some cases of interest, theoptimal linear procedure (in the sense of attaining the infimum out of all the upper bounds) is given.     

Asymptotic distribution of nonparametric estimates of distribution functions under a symmetry condition

We consider geometric concepts connected with infinite-dimensional families of probability measures. We give estimates for a symmetric distribution function both with known and unknown center of symmetry. The estimates considered are asymptotically optimal in the presence of information about the symmetry and in particular, they prove the ordinary empirical distribution function.Translated from Staticheskie Metody, pp. 39–58, 1978.The author thanks Yu. N. Tyurin for interest in the work.     

On a Constrained Optimal Rule for Classification with Unknown Prior Individual Group Membership

We describe a formal approach to constructing the optimal classification rule for classification analysis with unknown prior probabilities ofKmultivariate normal populations membership. This is done by suggesting a balanced design for the classification experiment and by constructing the optimal rule under the balanced design condition. The rule is characterized by a constrained minimization of total risk of misclassification; the constraint of the rule is constructed by a process of equalization among expected utilities ofKpopulation conditional densities. The efficacy of the suggested rule is examined through numerical studies. This indicates that dramatic gains in the accuracy of classification result can be achieved in the case where little is known about the relative population sizes.     

Measurements and infinite-dimensional statistical inverse theory

The most important ingredient of the statistical inverse theory is the indirect and noisy measurement of the unknown. Without the measurement, the formula for the posterior distribution becomes useless. However, inserting the measurement into the posterior distribution is not always simple. In the general setting, the posterior distribution is defined as a regular conditional probability. Hence it is known up to almost all measurements, which is inconvenient when we are given a single measurement. This shortage is covered in the finite-dimensional statistical inverse theory by fixing versions of probability density functions. A usual choice is to consider continuous probability density functions. Unfortunately, infinite-dimensional probability measures lack density functions which prohibits us from using the same method in the general setting. In this work, other possibilities for fixing the posterior distributions are discussed in the Gaussian framework. (© 2008 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Tracking the output of a poorly known markov process

Tracking the output of an unknown Markov process with unknown generator and unknown output function is considered. It is assumed the unknown quantities have a known prior probability distribution. It is shown that the optimal control is a linear feedback in the tracking error plus the conditional expectation of a quantity involving the unknown generator and output function of the Markov process. The results also have application to Bayesian identification of hidden Markov models     

An ensemble method using credal decision trees

Supervised classification learning can be considered as an important tool for decision support. In this paper, we present a method for supervised classification learning, which ensembles decision trees obtained via convex sets of probability distributions (also called credal sets) and uncertainty measures. Our method forces the use of different decision trees and it has mainly the following characteristics: it obtains a good percentage of correct classifications and an improvement in time of processing compared with known classification methods; it not needs to fix the number of decision trees to be used; and it can be parallelized to apply it on very large data sets.     

A method for processing the unreliable expert judgments about parameters of probability distributions

A method for combining two types of judgments about an object analyzed, which are elicited from experts, is considered in the paper. It is assumed that the probability distribution of a random variable is known, but its parameters may be determined by experts. The method is based on the use of the imprecise probability theory and allows us to take into account the quality of expert judgments, heterogeneity and imprecision of information supplied by experts. An approach for computing “cautious” expert beliefs under condition that the experts are unknown is studied. Numerical examples illustrate the proposed method.     

Estimating tail probabilities of heavy tailed distributions with asymptotically zero relative error

Efficient estimation of tail probabilities involving heavy tailed random variables is amongst the most challenging problems in Monte-Carlo simulation. In the last few years, applied probabilists have achieved considerable success in developing efficient algorithms for some such simple but fundamental tail probabilities. Usually, unbiased importance sampling estimators of such tail probabilities are developed and it is proved that these estimators are asymptotically efficient or even possess the desirable bounded relative error property. In this paper, as an illustration, we consider a simple tail probability involving geometric sums of heavy tailed random variables. This is useful in estimating the probability of large delays in M/G/1 queues. In this setting we develop an unbiased estimator whose relative error decreases to zero asymptotically. The key idea is to decompose the probability of interest into a known dominant component and an unknown small component. Simulation then focuses on estimating the latter ‘residual’ probability. Here we show that the existing conditioning methods or importance sampling methods are not effective in estimating the residual probability while an appropriate combination of the two estimates it with bounded relative error. As a further illustration of the proposed ideas, we apply them to develop an estimator for the probability of large delays in stochastic activity networks that has an asymptotically zero relative error.      

Optimal robust insurance with a finite uncertainty set

Decision-makers who usually face model/parameter risk may prefer to act prudently by identifying optimal contracts that are robust to such sources of uncertainty. In this paper, we tackle this issue under a finite uncertainty set that contains a number of probability models that are candidates for the “true”, but unknown model. Various robust optimisation models are proposed, some of which are already known in the literature, and we show that all of them can be efficiently solved via Second Order Conic Programming (SOCP). Numerical experiments are run for various risk preference choices and it is found that for relatively large sample size, the modeler should focus on finding the best possible fit for the unknown probability model in order to achieve the most robust decision. If only small samples are available, then the modeler should consider two robust optimisation models, namely the Weighted Average Model or Weighted Worst-case Model, rather than focusing on statistical tools aiming to estimate the probability model. Amongst those two, the better choice of the robust optimisation model depends on how much interest the modeler puts on the tail risk when defining its objective function. These findings suggest that one should be very careful when robust optimal decisions are sought in the sense that the modeler should first understand the features of its objective function and the size of the available data, and then to decide whether robust optimisation or statistical inferences is the best practical approach.     

Classification Modulo Invariance,With Application to Face Recognition

This article presents techniques for constructing classifiers that combine statistical information from training data with tangent approximations to known transformations; it demonstrates the techniques by applying them to a face recognition task. Our approach is to build Bayes classifiers with approximate class-conditional probability densities for measured data. The high dimension of the measurements in modern classification problems such as speech or image recognition makes inferring probability densities from feasibly sized training datasets difficult. We address the difficulty by imposing severely simplifying assumptions and exploiting a priori information about transformations to which classification should be invariant. For the face recognition task, we used a five-parameter group of such transformations consisting of rotation, shifts, and scalings. On the face recognition task, a classifier based on our techniques has an error rate that is 20% lower than that of the best algorithm in a reference software distribution.     

A conservative estimator for the proportion of false nulls based on Dvoretzky, Kiefer and Wolfowitz inequality

We propose a simple estimator for the weight in a two-component mixture model between a known and an unknown density. We make no parametric assumptions about the unknown component and estimate the weight conservatively, i.e., the estimate is smaller than the true value with high probability. A brief simulation is used to compare the proposal with already available conservative approaches.     

Studies in possibilistic recognition

This paper introduces an algorithm for pattern recognition. The algorithm will classify a measured object as belonging to one of N known classes or none of the classes. The algorithm makes use of fuzzy techniques and possibility is used instead of probability. The algorithm was conceived with the idea of recognizing fast moving objects, but it is shown to be more general. Fuzzy ISODATA's use as a front end to the algorithm is shown. The algorithm is shown to accomplish the objectives of correct classification or no classification. Values that describe possibility distributions are introduced with some of their properties investigated and illustrated. An expected value for a possibility distribution is also investigated. The algorithm actually proves to be adaptable to a wide variety of imprecise recognition problems. Some test results illustrate the use of the technique embodied in the algorithm and indicate its viability.     

混合缺失机制下两总体差异的半经验似然置信区间

假定两个总体x与y均有数据缺失,它们的分布函数分别为F(·)与G_θ(·),其中F(·)未知,G_θ(·)的概率密度函数g_θ(·)形式已知,仅依赖于一些未知的参数,利用Fractional填补法填补缺失值,在一定的条件下证明了缺失数据下两总体差异指标的半经验似然比统计量的渐近分布为x_1~2,由此可构造两总体差异指标的经验似然置信区间.     

The minmax regret gradual covering location problem on a network with incomplete information of demand weights

The gradual covering location problem seeks to establish facilities on a network so as to maximize the total demand covered, allowing partial coverage. We focus on the gradual covering location problem when the demand weights associated with nodes of the network are random variables whose probability distributions are unknown. Using only information on the range of these random variables, this study is aimed at finding the “minmax regret” location that minimizes the worst-case coverage loss. We show that under some conditions, the problem is equivalent to known location problems (e.g. the minmax regret median problem). Polynomial time algorithms are developed for the problem on a general network with linear coverage decay functions.     

Newsvendor problem under complete uncertainty: a case of innovative products

The paper presents a new scenario-based decision rule for the classical version of the newsvendor problem (NP) under complete uncertainty (i.e. uncertainty with unknown probabilities). So far, NP has been analyzed under uncertainty with known probabilities or under uncertainty with partial information (probabilities known incompletely). The novel approach is designed for the sale of new, innovative products, where it is quite complicated to define probabilities or even probability-like quantities, because there are no data available for forecasting the upcoming demand via statistical analysis. The new procedure described in the contribution is based on a hybrid of Hurwicz and Bayes decision rules. It takes into account the decision maker’s attitude towards risk (measured by coefficients of optimism and pessimism) and the dispersion (asymmetry, range, frequency of extremes values) of payoffs connected with particular order quantities. It does not require any information about the probability distribution.