Debasis Kundu

Generalized Exponential Distributions

Summary The three-parameter gamma and three-parameter Weibull distributions are commonly used for analysing any lifetime data or skewed data. Both distributions have several desirable properties, and nice physical interpretations. Because of the scale and shape parameters, both have quite a bit of flexibility for analysing different types of lifetime data. They have increasing as well as decreasing hazard rate depending on the shape parameter. Unfortunately both distributions also have certain drawbacks. This paper considers a three-parameter distribution which is a particular case of the exponentiated Weibull distribution originally proposed by Mudholkar, Srivastava & Freimer (1995) when the location parameter is not present. The study examines different properties of this model and observes that this family has some interesting features which are quite similar to those of the gamma family and the Weibull family, and certain distinct properties also. It appears this model can be used as an alternative to the gamma model or the Weibull model in many situations. One dataset is provided where the three-parameter generalized exponential distribution fits better than the three-parameter Weibull distribution or the three-parameter gamma distribution.

Exponentiated Exponential Family: An Alternative to Gamma and Weibull Distributions

Summary In this article we study some properties of a new family of distributions, namely Exponentiated Exponentialdistribution, discussed in Gupta, Gupta, and Gupta (1998). The Exponentiated Exponential family has two parameters (scale and shape) similar to a Weibull or a gamma family. It is observed that many properties of this new family are quite similar to those of a Weibull or a gamma family, therefore this distribution can be used as a possible alternative to a Weibull or a gamma distribution. We present two reall ife data sets, where it is observed that in one data set exponentiated exponential distribution has a better fit compared to Weibull or gamma distribution and in the other data set Weibull has a better fit than exponentiated exponential or gamma distribution. Some numerical experiments are performed to see how the maximum likelihood estimators and their asymptotic results work for finite sample sizes.

Generalized exponential distribution: different method of estimations

Recently a new distribution, named as generalized exponential distribution has been introduced and studied quite extensively by the authors. Generalized exponential distribution can be used as an alternative to gamma or Weibull distribution in many situations. In a companion paper, the authors considered the maximum likelihood estimation of the different parameters of a generalized exponential distribution and discussed some of the testing of hypothesis problems. In this paper we mainly consider five other estimation procedures and compare their performances through numerical simulations.

Generalized Rayleigh distribution

Recently, Surles and Padgett (Lifetime Data Anal., 187-200, 7, 2001) introduced two-parameter Burr Type X distribution, which can also be described as generalized Rayleigh distribution. It is observed that this particular skewed distribution can be used quite effectively in analyzing lifetime data. Different estimation procedures have been used to estimate the unknown parameter(s) and their performances are compared using Monte Carlo simulations.

Exact likelihood inference based on Type-I and Type-II hybrid censored samples from the exponential distribution

Chen and Bhattacharyya (1988,Comm. Statist. Theory Methods,17, 1857–1870) derived the exact distribution of the maximum likelihood estimator of the mean of an exponential distribution and an exact lower confidence bound for the mean based on a hybrid censored sample. In this paper, an alternative simple form for the distribution is obtained and is shown to be equivalent to that of Chen and Bhattacharyya (1988). Noting that this scheme, which would guarantee the experiment to terminate by a fixed timeT, may result in few failures, we propose a new hybrid censoring scheme which guarantees at least a fixed number of failures in a life testing experiment. The exact distribution of the MLE as well as an exact lower confidence bound for the mean is also obtained for this case. Finally, three examples are presented to illustrate all the results developed here.

Estimation of P[Y<X] for Weibull distributions

This paper deals with the estimation of R=P[Y<X] when X, and Y are two independent Weibull distributions with different scale parameters, but having the same shape parameter. The maximum likelihood estimator, and the approximate maximum likelihood estimator of R are proposed. We obtain the asymptotic distribution of the maximum likelihood estimator of R. Based on the asymptotic distribution, the confidence interval of R can be obtained. We also propose two bootstrap confidence intervals. We consider the Bayesian estimate of R, and propose the corresponding credible interval for R. Monte Carlo simulations are performed to compare the different proposed methods. Analysis of a real data set has also been presented for illustrative purposes.

Analysis of Type-II progressively hybrid censored data

The mixture of Type-I and Type-II censoring schemes, called the hybrid censoring scheme, is quite common in life-testing or reliability experiments. Recently, Type-II progressive censoring scheme has become quite popular for analyzing highly reliable data. One drawback of the Type-II progressive censoring scheme is that the length of the experiment can be quite large. In this paper, we introduce a Type-II progressively hybrid censoring scheme, where the experiment terminates at a pre-specified time. For this censoring scheme, we analyze the data under the assumptions that the lifetimes of the different items are independent and exponentially distributed random variables with parameter @l. We obtain the maximum-likelihood estimator of the unknown parameter in an exact form. Asymptotic confidence intervals based on @l@^, ln@l@^, confidence interval based on likelihood ratio test and two bootstrap confidence intervals are also proposed. Bayes estimate and credible interval of the unknown parameter are obtained under the assumption of gamma prior of the unknown parameter. Different methods have been compared using Monte Carlo simulations. One real data set has been analyzed for illustrative purposes.

Bayesian Inference and Life Testing Plan for the Weibull Distribution in Presence of Progressive Censoring

This article deals with the Bayesian inference of unknown parameters of the progressively censored Weibull distribution. It is well known that for a Weibull distribution, while computing the Bayes estimates, the continuous conjugate joint prior distribution of the shape and scale parameters does not exist. In this article it is assumed that the shape parameter has a log-concave prior density function, and for the given shape parameter, the scale parameter has a conjugate prior distribution. As expected, when the shape parameter is unknown, the closed-form expressions of the Bayes estimators cannot be obtained. We use Lindleys approximation to compute the Bayes estimates and the Gibbs sampling procedure to calculate the credible intervals. For given priors, we also provide a methodology to compare two different censoring schemes and thus find the optimal Bayesian censoring scheme. Monte Carlo simulations are performed to observe the behavior of the proposed methods, and a data analysis is onducted for illustrative purposes.

Discriminating between Weibull and generalized exponential distributions

Recently the two-parameter generalized exponential (GE) distribution was introduced by the authors. It is observed that a GE distribution can be considered for situations where a skewed distribution for a non-negative random variable is needed. The ratio of the maximized likelihoods (RML) is used in discriminating between Weibull and GE distributions. Asymptotic distributions of the logarithm of the RML under null hypotheses are obtained and they are used to determine the minimum sample size required in discriminating between two overlapping families of distributions for a user specified probability of correct selection and tolerance limit.

Modified moment estimation for the two-parameter Birnbaum--Saunders distribution

The maximum likelihood estimators and a modification of the moment estimators of a two-parameter Birnbaum-Saunders distribution are discussed. A simple bias-reduction method is proposed to reduce the bias of the maximum likelihood estimators and the modified moment estimators. The jackknife technique is also used to reduce the bias of these estimators. Monte Carlo simulation is used to compare the performance of all these estimators. The probability coverages of confidence intervals based on inferential quantities associated with all these estimators are evaluated using Monte Carlo simulations for small, moderate and large sample sizes. Two illustrative examples and some concluding remarks are finally presented.