ESTIMATING A DISTRIBUTION FUNCTION WITH TRUNCATED DATA

ＥＳＴＩＭＡＴＩＮＧＡＤＩＳＴＲＩＢＵＴＩＯＮＦＵＮＣＴＩＯＮＷＩＴＨＴＲＵＮＣＡＴＥＤＤＡＴＡＨＥＳＨＵＹＵＡＮ（何书元）（ＤｅｐａｒｔｍｅｎｔｏｆＰｒｏｂａｂｉｌｉｔｙａｎｄＳｔａｔｉｓｔｉｃｓ，ＰｅｋｉｎｇＵｎｉｖｅｒｓｉｔｙＢｅｉｊｉｎｇ１０...     

Inference for a truncated positive normal distribution

The main object of this paper is to study an extension of the half normal distribution defined by adding a positive truncation to it. The new model is more flexible than the half-normal distribution and contains the half normal distribution as a special case. Properties of this distribution, such as moments, hazard function and entropy are studied and parameters estimation is dealt with by using moments and maximum likelihood. A real data application indicates good fit performance of the new model when compared to other competitors in literatures.     

Some results on the multivariate truncated normal distribution

This note formalizes some analytical results on the n-dimensional multivariate truncated normal distribution where truncation is one-sided and at an arbitrary point. Results on linear transformations, marginal and conditional distributions, and independence are provided. Also, results on log-concavity, A-unimodality and the MTP₂ property are derived.     

Maximum-likelihood estimation of the parameters of a multivariate normal distribution

This paper provides an exposition of alternative approaches for obtaining maximum- likelihood estimators (MLE) for the parameters of a multivariate normal distribution under different assumptions about the parameters. A central focus is on two general techniques, namely, matrix differentiation and matrix transformations. These are systematically applied to derive the MLE of the means under a rank constraint and of the covariances when there are missing observations. Derivations using induction and inequalities are also included to illustrate alternative methods. Other examples, such as a connection with an econometric model, are included. Although the paper is primarily expository, some of the proofs are new.     

The singly truncated normal distribution: A non-steep exponential family

This paper is concerned with the maximum likelihood estimation problem for the singly truncated normal family of distributions. Necessary and suficient conditions, in terms of the coefficient of variation, are provided in order to obtain a solution to the likelihood equations. Furthermore, the maximum likelihood estimator is obtained as a limit case when the likelihood equation has no solution.     

基于分组数据的Weibull分布的参数估计

介绍了一种对基于分组数据的Weibull分布进行参数估计的方法．所得估计具有良好的收敛性，同时模拟结果也表明这种方法的可行性．     

A Wiener process model with truncated normal distribution for reliability analysis

The use of degradation model to perform the reliability analysis has drawn much attention due to the fact that the performance of numerous highly reliable systems degrades over time. To describe the unit-to-unit variability for a population of systems, the random effect has been incorporated into the degradation model that plays an important part in assessing the reliability of deteriorating systems. In the existing literature, the normal distribution is commonly adopted to represent the random effect, but the assumption can be unsuitable for some practical applications, such as the degradation process of train wheels. In this paper, we present a degradation modeling and reliability estimation approach by using truncated normal distribution to characterize the unit-to-unit variability. A Wiener process with truncated normal distribution is firstly applied to model the degradation process of the deteriorating system, and the analytical expressions of probability density function and reliability function are derived. Expectation maximization algorithm is then used to estimate the model parameters. The effectiveness and feasibility of the presented approach are illustrated through a numerical example and practical case studies for laser devices and train wheels. The results indicate that the presented approach can obtain better reliability estimation results by considering the truncated normal distribution when the unit-to-unit variability has significant difference.     

A truncated Cauchy distribution

A truncated version of the Cauchy distribution is introduced. Unlike the Cauchy distribution, this possesses finite moments of all orders and could therefore be a better model for certain practical situations. One such situation in finance is discussed. Explicit expressions for the moments of the truncated distribution are also derived.     

Estimating parameters of a k-factor GIGARCH process

Some crucial time series of market data, such as electricity spot prices, exhibit long-memory, in the sense of slowly-decaying correlations combined with heteroskedasticity. To be able to modelize such a behaviour, we consider in this Note the k-factor GIGARCH process and we propose two methods to address the related parameter estimation problem. For each method, we develop the asymptotic theory for the estimation. To cite this article: A.K. Diongue, D. Guégan, C. R. Acad. Sci. Paris, Ser. I 339 (2004).     

Identification of parameters and the distribution of the minimum of the tri-variate normal

In this note, for tri-variate normal distributions, we consider the problem of the identification of parameters when only the distribution of the minimum is known.     

Estimating the parameters of fatigue curve of a composite material

By using the method of maximum likelihood, the parameters of two versions of a mathematical model for fatigue damage accumulation in a laminate are estimated. The models, which are founded on the Markov chain theory, are very simple: they do not take into account the specific structural features of a composite and therefore cannot provide numerical coincidence with experimental fatigue test data, but they can be used for a nonlinear regression analysis of fatigue curves. A simple method is offered for approximately estimating model parameters, some of which characterize the distribution of the local static strength. By using such models, we can predict the relative changes in fatigue curves from known relative variations in the parameters of static strength and also predict the distribution function of fatigue life in program fatigue tests.Translated from Mekhanika Kompozitnykh Materialov, Vol. 41, No. 1, pp. 109–120, January–February, 2005.     

Estimation in truncated Poisson distribution

Bayes’ estimator of truncated Poisson distribution (TPD) has been obtained by using gamma prior. Furthermore, recurrence relations for the estimator of the parameter are obtained. R-software has been used for comparing the estimates with the corresponding maximum likelihood estimator (MLE).     

Estimating the parameters of Weibull distribution and the acceleration factor from hybrid partially accelerated life test

This article considers the estimation of parameters of Weibull distribution based on hybrid censored data. The parameters are estimated by the maximum likelihood method under step-stress partially accelerated test model. The maximum likelihood estimates (MLEs) of the unknown parameters are obtained by Newton–Raphson algorithm. Also, the approximate Fisher information matrix is obtained for constructing asymptotic confidence bounds for the model parameters. The biases and mean square errors of the maximum likelihood estimators are computed to assess their performances through a Monte Carlo simulation study.