|
|
|
 |
Search published articles |
 |
|
Showing 237 results for Type of Study: Research
Nasrin Moradi, Abdolreza Sayyareh, Hanieh Panahi,
Volume 8, Issue 1 (9-2014)
Abstract
In this article, the parameters of the Exponentiated Burr type III distribution have been estimated based on type II censored data using maximum likelihood method with EM algorithm and Bayesian approach under Gamma prior distributions against the squared error, linex and entropy loss functions. Importance sampling technique and Lindley's approximation method have been applied to evaluate these Bayes estimates. The results are checked by simulation study and analyzing real data of acute myelogeneous disease. The Bayes estimates are, generally, better than the MLEs and all estimates improve by increasing sample size.
Aref Khanjari Idenak, Mohammadreza Zadkarami, Alireza Daneshkhah,
Volume 8, Issue 2 (3-2015)
Abstract
In this paper a new compounding distribution with increasing, decreasing, bathtub shaped and unimodal hazard rate function is proposed. The new four-parameters distribution is a generalization of the complementary exponential power distribution. The raw-moments, density function of the order statistics, survival function, hazard rate function, quantiles, mean residual lifetime and reliability function are presented. The estimation of the new distribution in a special case Poisson complementary exponential power distribution is studied by the method of maximum likelihood and EM algorithm. Expression for asymptotic distribution for the maximum likelihood estimation of the parameters of the PCEP distribution are obtained and for determining the precision of the variance and covariance of the estimations, a simulation is used, Then experimental results are illustrated based on the real data set.
Ali Doostmoradi, Mohammadreza Zadkarami, Mohammadreza Akhoond, Aref Khanjari Idenak,
Volume 8, Issue 2 (3-2015)
Abstract
In this paper a new distribution function based on Weibull distribution is introduced. Then the characteristics of this new distribution are considered and a real data set is used to compare this distribution with some of the generalized Weibull distributions.
Kamran Ghoreishi,
Volume 8, Issue 2 (3-2015)
Abstract
In the Bayesian analysis of contingency tables, analysts commonly use special prior distributions for the parameters of log-linear models or the cell probabilities. But, in practice, sometimes there is some interpretive information which is rather on (generalized) odds ratios. So, it seems one will need a powerful approach so that he can model his prior believe on (generalized) odds ratios. Here, we refer to these priors as structural priors. In this paper we first introduce the general pattern of the structural priors. Then, since these priors have vast application in clinical trials and especially in the analysis of 2 x 2 complete and incomplete contingency tables, we obtain the corresponding structural priors, separately, under three conditions.
Zahra Yazari, Sayed Mohammad Reza Alavi,
Volume 8, Issue 2 (3-2015)
Abstract
The randomized response technique is a procedure for collecting the information on sensitive characteristics without exposing the identity of the respondent. Optional randomized response models are based on the basic premise that a question may be sensitive for one respondent but may not be sensitive for another. In this paper a three stage optional randomized response model is proposed and its properties are discussed using simulation with R package. The mean and sensitivity level of household's income of students of Shahid Chamran University are estimated using this model.
Ehsan Zamanzade,
Volume 8, Issue 2 (3-2015)
Abstract
In this paper, an improved mean estimator for unbalanced ranked set samples is proposed. The estimator is obtained by using the fact that distribution function of order statistics are stochastically ordered. Also, it is showed that this estimator is convergent and has better performance than its empirical counterpart in unbalanced ranked set samples.
Akbar Asgharzadeh, Mina Azizpour, Reza Valiollahi,
Volume 9, Issue 1 (9-2015)
Abstract
One of the drawbacks of the type II progressive censoring scheme is that the length of the experiment can be very large. Because of that, recently a new censoring scheme named as the type II progressively hybrid censored scheme has received considerable interest among the statisticians. In this paper, the statistical inference for the half-logistic distribution is discussed based on the progressively type II hybrid censored samples. The maximum likelihood estimator, the approximate maximum likelihood estimator and the Bayes estimator of parameter using Lindley approximation and MCMC method are obtained. Asymptotic confidence intervals, Bootstrap confidence intervals and Bayesian credible intervals are obtained. Different point and interval estimators are compared using Monte Carlo simulation. A real data set is presented for illustrative purposes.
Fatemeh Safaei, Jafar Ahmadi,
Volume 9, Issue 1 (9-2015)
Abstract
Consider a repairable system where two types of failures occur with different rate functions. The choice of minimal repair or replacement depends on the types of failures. The length of replacement cycle becomes optimal in terms of the cost function and the concept of discounted cost. In this paper, for two repairable systems the optimal replacement cycles are compared based on failure rate functions and probability of minimal repairs. Based on our results, one can make a decision for the period of replacement times. In order to illustrate the obtained results, numerical examples and simulation study are given.
Saba Aghadoust, Kamel Abdollahnezhad, Farhad Yaghmaei, Ali Akbar Jafari,
Volume 9, Issue 1 (9-2015)
Abstract
The log-normal distribution is used to describe the positive data that has skewed distribution with small mean and large variance. This distribution has application in many sciences for example medicine, economics, biology and alimentary science, etc. Comparison of means of several log-normal populations always has been in focus of researchers, but their test statistics are not easy to derive or extremely complicated for this comparisons. In this paper, the size and power of different testing methods including F-test, likelihood ratio test, generalized p-value approach and computational approach test are compared in a simulation study.
Bahareh Afhami, Mohsen Madadi, Mohsen Rezapour,
Volume 9, Issue 1 (9-2015)
Abstract
In this paper, first the Shannon entropy of k-record values is derived from the generalized Pareto distribution and propose goodness-of-fit tests based on this entropy. Finally, real data and a simulation study are used for analyzing the performance of this statistic.
Shahram Yaghoubzadeh, Ali Shadrokh, Masoud Yarmohammadi,
Volume 9, Issue 1 (9-2015)
Abstract
In this paper, we introduce a new five-parameters distribution with increasing, decreasing, bathtub-shaped failure rate, called as the Beta Weibull-Geometric (BWG) distribution. Using the Sterling Polynomials, the probability density function and several properties of the new distribution such as its reliability and failure rate functions, quantiles and moments, Renyi and Shannon entropies, moments of order statistics, mean residual life, reversed mean residual life are obtained. The maximum likelihood estimation procedure is presented in this paper. Also, we compare the results of fitting this distribution to some of their sub-models, using to a real data set. It is also shown that the BWG distribution fits better to this data set.
Ghobad Barmalzan, Abedin Haidari, Khaled Masomifard,
Volume 9, Issue 2 (2-2016)
Abstract
In this paper, series and parallel systems, when the lifetimes of their components following the scale model are studied and different stochastic orderings between them are discussed. Moreover, we apply these results to the series and parallel systems consisting of exponentiated Weibull or generalized gamma components. The presented results in this paper complete and extend some known results in the literature.
Sayed Mohammad Reza Alavi, Mahboobeh Tajadini,
Volume 9, Issue 2 (2-2016)
Abstract
In survey sampling, the respondents often do not state the actual response to the sensitive questions. Randomized response techniques have been designed to protect the privacy of responses. This paper focused on the randomized response technique for qualitative variables based on Simmons method. Using idea of repeating answer, the new repeated randomized response technique is introduced. Its efficiency is compared with the Simmons technique. Proportion of student cheating in Shahid Chamran University is estimated using the proposed technique.
Ali Aghamohammadi, Sakineh Mohammadi,
Volume 9, Issue 2 (2-2016)
Abstract
In many medical studies, in order to describe the course of illness and treatment effects, longitudinal studies are used. In longitudinal studies, responses are measured frequently over time, but sometimes these responses are discrete and with two-state. Recently Binary quantile regression methods to analyze this kind of data have been taken into consideration. In this paper, quantile regression model with Lasso and adaptive Lasso penalty for longitudinal data with dichotomous responses is provided. Since in both methods posteriori distributions of the parameters are not in explicit form, thus the full conditional posteriori distributions of parameters are calculated and the Gibbs sampling algorithm is used to deduction. To compare the performance of the proposed methods with the conventional methods, a simulation study was conducted and at the end, applications to a real data set are illustrated.
Hamid Lorestani, Abdolreza Sayyareh,
Volume 9, Issue 2 (2-2016)
Abstract
Most of natural phenomena are modeled with univariate and multivariate normal distributions and their derivatives. Folded normal variables are defined as the absolute of normal random variables. So far, univariate and bivariate normal distributions, their characteristics and usages have been studied too. Distribution of the maximum of dependent random variables which have elliptically contoured distribution, has been considered by others. In this paper, distribution of the maximum of dependent random variables with bivariate folded standard normal distribution, which their joint distribution is not of the elliptically contoured family, is calculated. Also, the mean, variance and moment generating function of this distribution are investigated.
Fatemeh Hooti, Jafar Ahmadi,
Volume 10, Issue 1 (8-2016)
Abstract
In this paper, the quantile function is recalled and some reliability measures are rewritten in terms of quantile function. Next, quantile based dynamic cumulative residual entropy is obtained and some of its properties are presented. Then, some characterization results of uniform, exponential and Pareto distributions based on quantile based dynamic cumulative entropy are provided. A simple estimator is also proposed and its performance is studied for exponential distribution. Finally discussion and results are presented.
Hamid Reza Nilisani, Mohamma Amini, Abolghasem Bozorgnia,
Volume 10, Issue 1 (8-2016)
Abstract
An important inequality for distribution of maximum independent random variables is Levy inequality. In this paper, a version of this inequality for weakly negative dependent random variables will be provided. The strong law for dependent random variables has been studied by different authors. In this research, also, the weighted complete convergence for arrays of rowwise negatively dependent random variables that are stochastically bounded will be obtained. complete convergence and strong law for such random variables will result.
Shiva Akhtarian, Tahere Yaghoobi,
Volume 10, Issue 1 (8-2016)
Abstract
Given the widespread usage of software systems in all aspects of modern life, the need to produce almost error free and high quality software has become more and more important. Software reliability is considered as an important approach to software quality assessment. Software reliability modeling based on non- homogeneous Poisson process is a quite successful method in software reliability engineering. In this paper, we first study the general growth model of software reliability, and then we extend the general model by considering two types of simple and complex errors, dependency between complex errors and time delay between detecting and removing complex errors. Estimating the model parameters has been done by using two failure data sets of real software projects through MATLAB software. We compare the proposed model with two existing models using various criteria. The results show that the proposed model better fits the data, providing more accurate information about the software quality.
Hamed Mohamadghasemi, Ehsan Zamanzade, Mohammad Mohammadi,
Volume 10, Issue 1 (8-2016)
Abstract
Judgment post stratification is a sampling strategy which uses ranking information to give more efficient statistical inference than simple random sampling. In this paper, we introduce a new mean estimator for judgment post stratification. The estimator is obtained by using ordering observations in post strata. Our simulation results indicate that the new estimator performs better than its leading competitors in the literature.
Abouzar Bazyari,
Volume 10, Issue 1 (8-2016)
Abstract
Hypothesis testing the homogeneity of means of k univariate normal populations against the hypothesis of one sided ordered means with unknown and equal variances is considered. A new completely method to find the uniformly most powerful test at significance level α is presented based on the multivariate t distribution. Since for more than two populations finding the null distribution of test statistic is not easy, the power of test is computed and then the critical values of test statistic for different significance levels obtained. This testing method is used for real examples. Also testing homogeneity of k mean vectors against two sided ordered mean vectors of multivariate normal populations is considered. Using Monte Carlo simulation the values of classical power of test for two bivariate and trivariate normal distributions at different significance levels are compared.
|
|
