Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
14
2
2018
3
1
Prediction of Times to Failure of Censored Units in Progressive Hybrid Censored Samples for the Proportional Hazards Family
131
155
EN
Samaneh
Ameli
s.ameli@birjand.ac.ir
Majid
Rezaie
mjrezaei@birjand.ac.ir
Jafar
Ahmadi
ahmadi-j@um.ac.ir
10.29252/jsri.14.2.131
In this paper, the problem of predicting times to failure of units censored in multiple stages of progressively hybrid censoring for the proportional hazards family is considered. We discuss different classical predictors. The best unbiased predictor ($BUP$), the maximum likelihood predictor ($MLP$) and conditional median predictor ($CMP$) are all derived. As an example, the obtained results are computed for exponential distribution. A numerical example is presented to illustrate the prediction methods discussed here. Using simulation studies, the predictors are compared in terms of bias and mean squared prediction error ($MSPE$).
Best unbiased predictor, conditional median predictor, maximum likelihood predictor, mean square prediction error, Monte-Carlo simulation, point predictor, progressive hybrid censoring.
http://jsri.srtc.ac.ir/article-1-269-en.html
http://jsri.srtc.ac.ir/article-1-269-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
14
2
2018
3
1
Parameter Estimation in Spatial Generalized Linear Mixed Models with Skew Gaussian Random Effects using Laplace Approximation
157
169
EN
Seyed Reza
Hosseini Shojaei
shojaee87@birjand.ac.ir
Yadollah
Waghei
ywaghei@birjand.ac.ir
Mohsen
Mohammadzadeh
mohsen_ m@modares.ac.ir J. Statist.
10.29252/jsri.14.2.157
Spatial generalized linear mixed models are used commonly for modelling non-Gaussian discrete spatial responses. We present an algorithm for parameter estimation of the models using Laplace approximation of likelihood function. In these models, the spatial correlation structure of data is carried out by random effects or latent variables. In most spatial analysis, it is assumed that random effects have Gaussian distribution, but the assumption is questionable. This assumption is replaced in the present work, using a skew Gaussian distribution for the latent variables, which is more flexible and includes Gaussian distribution. We examine the proposed method using a real discrete data set.
Laplace approximation, multivariate skew Gaussian, random effects, SGLM, spatial data.
http://jsri.srtc.ac.ir/article-1-273-en.html
http://jsri.srtc.ac.ir/article-1-273-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
14
2
2018
3
1
Rayleigh Confidence Regions based on Record Data
171
188
EN
Mousa
Abdi
me.abdi@bam.ac.ir
Akbar
Asgharzadeh
a.asgharzadeh@umz.ac.ir
10.29252/jsri.14.2.171
This paper presents exact joint confidence regions for the parameters of the Rayleigh distribution based on record data. By providing some appropriate pivotal quantities, we construct several joint confidence regions for the Rayleigh parameters. These joint confidence regions are useful for constructing confidence regions for functions of the unknown parameters. Applications of the joint confidence regions using two environmental data sets are presented for illustrative purposes. Finally, a simulation study is conducted to study the performance of the proposed joint confidence regions.
Joint confidence region, pivotal quantity, Rayleigh distribution, records
http://jsri.srtc.ac.ir/article-1-268-en.html
http://jsri.srtc.ac.ir/article-1-268-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
14
2
2018
3
1
Inference for the Type-II Generalized Logistic Distribution with Progressive Hybrid Censoring
189
217
EN
Mina
Azizpour
and Akbar Asgharzadeh
minaazizpoor@gmail.com
Akbar
Asgharzadeh
a.asgharzadeh@umz.ac.ir
10.29252/jsri.14.2.189
This article presents the analysis of the Type-II hybrid progressively censored data when the lifetime distributions of the items follow Type-II generalized logistic distribution. Maximum likelihood estimators (MLEs) are investigated for estimating the location and scale parameters. It is observed that the MLEs can not be obtained in explicit forms. We provide the approximate maximum likelihood estimators (AMLEs) by appropriately approximating the likelihood equations. Asymptotic confidence intervals based on MLEs and AMLEs and one bootstrap confidence interval are proposed.
Estimation of the shape parameter is also discussed. Monte Carlo simulations are performed to compare the performances of the different methods and two real data sets have been analyzed for illustrative purposes.
Maximum likelihood estimation, progressively Type-II hybrid censoring, Type-II generalized logistic distribution.
http://jsri.srtc.ac.ir/article-1-270-en.html
http://jsri.srtc.ac.ir/article-1-270-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
14
2
2018
3
1
A Perturbed Half-normal Distribution and Its Applications
219
246
EN
Eisa
Mahmoudi
mahmoudi@yazd.ac.ir
Reihaneh
Lalehzari
rlalehzari@gmail.com
Rahmat Sadat
Meshkat
r.meshkat@gmail.com
10.29252/jsri.14.2.219
In this paper, a new generalization of the half-normal distribution which is called the perturbed half-normal distribution is introduced. The new distribution belongs to a family of distributions which includes the half-normal distribution along with an extra parameter to regulate skewness. The probability density function (pdf) is derived and some various properties of the new distribution are obtained. The derived properties include the cumulative distribution function (cdf), the $r$th moment, moment generating function, characteristic function, mean deviation about the mean and estimation of the parameters using the method of moments and maximum likelihood. Finally, the flexibility and potentiality of the new distribution is illustratedin an application to two real data sets.
Error function, half-normal distribution, hypergeometric function, skewness, moment generating function.
http://jsri.srtc.ac.ir/article-1-272-en.html
http://jsri.srtc.ac.ir/article-1-272-en.pdf
Statistical Research and Training Center - Statistical Centre of Iran
Journal of Statistical Research of Iran JSRI
1735-1294
14
2
2018
3
1
â€‹Rank based Least-squares Independent Component Analysis
247
266
EN
Jafar
Rahmani Shamsi
jrahmanishamsi@yahoo.com
Ali
Dolati
adolati@yazd.ac.ir
10.29252/jsri.14.2.247
In this paper, we propose a nonparametric rank-based alternative to the least-squares independent component analysis algorithm developed. The basic idea is to estimate the squared-loss mutual information, which used as the objective function of the algorithm, based on its copula density version. Therefore, no marginal densities have to be estimated. We provide empirical evaluation of the proposed algorithm through simulation and real data analysis. Since the proposed algorithm uses rank values rather than the actual values of the observations, it is extremely robust to the outliers and suffers less from the presence of noise than the other algorithms.
Copula, independent component analysis, squared-loss mutual information.
http://jsri.srtc.ac.ir/article-1-271-en.html
http://jsri.srtc.ac.ir/article-1-271-en.pdf