Journal of Statistical Research of Iran
http://jsri.srtc.ac.ir
Journal of Statistical Research of Iran JSRI - Journal articles for year 2008, Volume 4, Number 2Yektaweb Collection - http://www.yektaweb.comen2008/3/11Ordering of Order Statistics Using Variance Majorization
http://jsri.srtc.ac.ir/browse.php?a_id=175&sid=1&slc_lang=en
<p><span style="line-height: 1.6em;"> In this paper, we study stochastic comparisons of order statistics of independent random variables with proportional hazard rates, using the notion of variance majorization.</span></p>
<p></p>
Baha-Eldin KhalediNumber of Minimal Path Sets in a Consecutive-k-out-of-n: F System
http://jsri.srtc.ac.ir/browse.php?a_id=176&sid=1&slc_lang=en
<p><span style="line-height: 1.6em;">In this paper the combinatorial problem of determining the number of minimal path sets of a consecutive-</span><em style="line-height: 1.6em;">k</em><span style="line-height: 1.6em;">-out-of-</span><em style="line-height: 1.6em;">n</em><span style="line-height: 1.6em;">: F system is considered. For the cases where </span><em style="line-height: 1.6em;">k</em><span style="line-height: 1.6em;"> = 2, 3 the explicit formulae are given and for </span><em style="line-height: 1.6em;">k</em><span style="line-height: 1.6em;"> ≥ 4 a recursive relation is obtained. Direct computation for determining the number of minimal path sets of a consecutive-</span><em style="line-height: 1.6em;">k</em><span style="line-height: 1.6em;">-out-of-</span><em style="line-height: 1.6em;">n</em><span style="line-height: 1.6em;">: F system for </span><em style="line-height: 1.6em;">k</em><span style="line-height: 1.6em;"> ≥ 4 remains a difficult task.</span></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
Mohammad Khanjari SadeghEffect of Measurement Errors on a Class of Estimators of Population Mean Using Auxiliary Information in Sample Surveys
http://jsri.srtc.ac.ir/browse.php?a_id=174&sid=1&slc_lang=en
<p><span style="line-height: 1.6em;"> We consider the problem of estimation the population mean of the study variate </span><em style="line-height: 1.6em;">Y</em><span style="line-height: 1.6em;"> in presence of measurement errors when information on an auxiliary character </span><em style="line-height: 1.6em;">X</em><span style="line-height: 1.6em;"> is known. A class of estimators for population means using information on an auxiliary variate </span><em style="line-height: 1.6em;">X</em><span style="line-height: 1.6em;"> is defined. Expressions for its asymptotic bias and mean square error are obtained. Optimum conditions are obtained for which the mean square errors of the proposed class of estimators are minimum.</span></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p> </p>
<p></p>
<p></p>
Housila P.SinghSome Results Based on Entropy Properties of Progressive Type-II Censored Data
http://jsri.srtc.ac.ir/browse.php?a_id=171&sid=1&slc_lang=en
<p><span style="line-height: 1.6em;">In many life-testing and reliability studies, the experimenter might not always obtain complete information on failure times for all experimental units. One of the most common censoring schemes is progressive type-II censoring. The aim of this paper is characterizing the parent distributions based on Shannon entropy of progressive type-II censored order statistics. It is shown that the equality of the Shannon information in progressive type-II censored order statistics can determine the parent distribution uniquely. We establish some characterization through the difference of Shannon entropy of the parent distribution and respective progressive type-II censored order statistics. We also prove that the dispersive ordering of the parent distributions implies the entropy ordering of their respective progressive type-II censored order statistics.</span></p>
<p></p>
<p></p>
<p> </p>
Jafar AhmadiBayesian Estimation of the Multiple Change Points in Gamma Process Using X-bar chart
http://jsri.srtc.ac.ir/browse.php?a_id=172&sid=1&slc_lang=en
<p><span style="line-height: 1.6em;">The process personnel always seek the opportunity to improve the processes. One of the essential steps for process improvement is to quickly recognize the starting time or the change point of a process disturbance. Different from the traditional normally distributed assumption for a process, this study considers a process which follows a gamma process. In addition, we consider the possibility of the existence of more than one change point. The proposed approach combines the commonly used </span>X-bar<span style="line-height: 1.6em;"> control chart with the Bayesian estimation technique using reversible jump Markov chain Monte Carlo method (RJMCMC) to obtain Bayes estimates. The efficiency of our proposed method is evaluated through a series of simulations. The results show that in many cases if there exist more than one change point, our proposed method is able to estimate the true model. Consequently, if there exist more than one change point in the process we have some chance to estimate the true model which will be helpful to determine and remove the root causes introduced into the process. This method is more flexible than the case we assumed that there is just one change point in the process. </span></p>
<p></p>
<p></p>
Esmail Dehghan Monfared“Equivalent Linear Composition” as an Efficient Stratification Factor in Multipurpose Surveys
http://jsri.srtc.ac.ir/browse.php?a_id=177&sid=1&slc_lang=en
<p><span style="line-height: 1.6em;">Horticulture survey is a multi-purpose survey which is conducted ad hoc by Statistical Center of Iran (SCI). Availability of survey variables in the sampling frame suggests a multivariate stratification in each province based on its desired variables for acquiring a higher efficiency. There are several ways to stratify the sampling frame considering all stratification variables, such as using sum of observation on all variables, clustering, using first principal component, and specially an almost new method which uses multiple-frame techniques. We introduce, </span><em style="line-height: 1.6em;">the equivalent linear composition factor</em><span style="line-height: 1.6em;">, and illustrate how it works more efficiently then the other methods in this particular survey.</span></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p> </p>
<p></p>
<p></p>
<p></p>
Arman Bidarbakht-niaPredicting Population for Male of Rural Area in Bangladesh
http://jsri.srtc.ac.ir/browse.php?a_id=173&sid=1&slc_lang=en
<p><span style="line-height: 1.6em;"> In this paper the population for male of rural area in Bangladesh is predicted by using the geometric growth rate method. The predictions are computed in a three-step procedure. In the first step, the prediction are computed using an exponentail model estimated by Quasi-Newton method for the years 1974, 1981, 1991, and 2001 using the package STATISTICA. Using the cross-validation predictive power (CVPP) criterion and coefficient of determination, the shrinkage coefficient </span><span style="line-height: 1.6em;">$lambada$</span><span style="line-height: 1.6em;"> </span><span style="line-height: 1.6em;"> is constructed. The shrinkage coefficient determines the adequacy of the first step prediction. In the second step, these predicted values are used to estimate the growth rate for different age groups by using the geometric growth arte method. In the final step, considering the population for male of rural area in Bangladesh for the census year 2001 as the base population and using the estimated geometric growth rate of the second step estimation, the predictions for the male population of rural area of Bangladesh are estimated for the years 2002 through 2031 by applying geometric growth rate method.</span></p>
<p></p>
<p></p>
<p></p>
<p></p>
<p></p>
Rafiqul Islam