مجله علوم آماری
سال نهم شماره 2 (پیاپی 18، پاییز و زمستان 1394)

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.

Process capability indices are widely used in various industries as a statistical measure to assess how well a process meets a predetermined level of production tolerance. In this paper، we propose new confidence intervals for the ratio and difference of two Cpmk indices، based on the asymptotic and parametric bootstrap approaches. We compare the performance of our proposed methods with generalized confidence intervals in term of coverage probability and average length via a simulation study. Our simulation results show the merits of our proposed methods.

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.

Distribution of extreme values of a data set is especially used in natural phenomena including flow discharge، wind speeds، precipitation and it is also used in many other applied sciences such as reliability studies and analysis of environmental extreme events. So if one can model the extremal behavior، then the manner of their future behavior can be predicted. This article is devoted to study extreme wind speeds in Zahedan city using maximal generalized extreme value distribution. In this article، we apply four methods to estimate distribution parameters including maximum likelihood estimation، probability weighted moments، elemental percentile and quantile least squares then compare estimates by average scaled absolute error criterion. We also obtain quantiles estimation and confidence intervals. As a part of result، return period of maximum wind speeds are computed.

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.

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.

In this paper، we study the applicability of probabilistic solutions for the alignment of tertiary structure of proteins and discuss its difference with the deterministic algorithms. For this purpose، we introduce two Bayesian models and address a solution to add amino acid sequence and type (primary structure) to protein alignment. Furthermore، we will study the parameter estimation with Markov Chain Monte Carlo sampling from the posterior distribution. Finally، in order to see the effectiveness of these methods in the protein alignment، we have compared the parameter estimations in a real data set.