جستجوی مقالات مرتبط با کلیدواژه "شبیه سازی مونت کارلو" در نشریات گروه "ریاضی"

Hypotheses testing is an effective technique for decision making on the manufacturing process capability. Considering fuzzy quality rather than precise specification limits, we can make more reliable decisions for investigating the manufacturing process capability. In this paper, an applied study on the basis of fuzzy quality using the Yongting’s index is presented. The proposed approach which is used in this applied study is a technique for testing the capability of a normal process in producing products within the preset fuzzy specification limits. The adversity to test process capability indices is complexity in the distribution of its natural estimator, even under the Normal distribution. Also, there is the challenge in testing process capability based on fuzzy quality. The non-parametric approach which is used to test the performance of a product based on fuzzy quality and random sampling techniques which is presented based on the Monte Carlo simulation method and can be generalized for various fuzzy qualities. This study is presented to investigate the quality of paint thickness in the automobile polishing process based on trapezoidal fuzzy quality. The numerical computations are presented to show the performance of the Monte Carlo simulation method for making reliable decisions in testing the Yongting’s index.

In this article, we first investigate some extensions of Kullback-Leibler information and theirproperties. Then, we consider the moment constraints for the maximum distribution of cumulative residualentropy and investigate the relationship between the cumulative residual Kullback-Leibler information(CRKL) and cumulative residual entropy (CRE). We also discuss the methods for estimating the scaleparameter of Rayleigh distribution and provide two estimation methods. In the following we use cumulativeresidual Kullback-Leibler information as a goodness of fit test statistic. Then we compute the criticalvalues and the power of proposed tests and compare the power values with with the power of other tests.Finally, we apply the tests for a real data set.

Introduction  :

 This paper is concerned with using the Maximum Likelihood, Bayes and a new method, E-Bayesian, estimations for computing estimates for the unknown parameter, reliability and hazard rate functions of the Generalized Inverted Exponential distribution. The estimates are derived based on a conjugate prior for the unknown parameter. E-Bayesian estimations are obtained based on three different prior distributions of the hyper parameters. Asymptotic behaviors of E-Bayesian estimations and relations among them have been discussed. The results are computed based on type-II censoring and squared error loss function. Finally, a comparison among the Maximum Likelihood, Bayes and E-Bayesian estimation methods in different sample sizes are made, using the Monte Carlo simulation, which shows that the new method is more efficient than other old methods and is easy to operate.

Suppose the Generalized Inverted Exponential distribution and its unknown parameter, reliability and hazard rate functions. Then the estimates of functions of interest are derived based on type II censored samples of this distribution, using the Monte Carlo simulation. 

Results :

 Results show that the E-Bayesian method is more efficient than other old methods and is easy to operate. Also, the asymptotic behaviors of three E-Bayesian estimations are the same.

In some biological, environmental or ecological studies, there are situations in which obtaining exact measurements of sample units are much harder than ranking them in a set of small size without referring to their precise values. In these situations, ranked set sampling (RSS), proposed by McIntyre (1952), can be regarded as an alternative to the usual simple random sampling (SRS) to draw a more representative sample from the population of interest than what is possible in SRS. To draw a ranked set sample, one first draws n simple random samples, each of size n, from the population of interest and ranks them in an increasing magnitude. The ranking process is done without measuring sample units and therefore it need not to be accurate. One then identifies the ith sample unit from the ith sample for actual quantification (for i=1, …, n). Finally, he repeats this process m times (cycle) if he/she is required to obtain a sample of size mn. Since a ranked set sample contains information from both measured sample units and their corresponding ranks, one intuitively expects that statistical inference based on RSS to be more accurate than what is possible to obtain based on SRS.
This paper is concerned with problem of estimating variance of the normal distribution in RSS. Several methods of estimation of variance of the normal distribution are described and compared via a Monte Carlo simulation study. All simulation studies in this paper have been done using R statistical software version R-3.3.1 In this paper, we consider estimation of the normal variance based on a ranked set sample with single (multiple) cycle(s) and propose different unbiased estimators for each case. Our simulation results indicate that the mean square error (MSE) of each estimator is decreased as the values of n or m increases while the other parameters are kept fixed. It is also found that the estimator based on combining variance estimators of within and between ranking classes has typically better performance than the others. The following results can be obtained based on our simulation study:•If there is a single cycle in RSS, then the proposed estimator in the case of single cycle beats Stokes-modified unbiased estimator.
•In the multiple cycle case in RSS, the estimator based on combining variance estimators of within and between ranking classes is the best one. ./files/site1/files/51/%D9%85%D9%87%D8%AF%D9%88%DB%8C_%D9%85%D9%86%D8%B4_%D8%A7%DB%8C%D8%B1%D8%A7%D9%86%D9%BE%D9%86%D8%A7%D9%87.pdf

Sometimes the extent of the parameter domain changes over the space of the parameter, increases the risk of posterior Bayesian. In this case, the empirical and hierarchical estimates can be a good substitute for bayesian estimation. In this study, when X and Y are two independent exponential distributions with different parameters, were estimated the E-Bayesian and hierarchical Bayesian for the under squared error loss function. This suggested methods, was compared with each other and with the Bayesian estimator using the Monte Carlo simulation and two set data.

In this article we want families beta-G distributions with family Zgrafos-Balakryshnan- G where G is a distribution of power series is a family of distributions using goodness of fit test statistics and risk and exchange rate risk, inverse functions, using monte carlo simulation and two sets actual data comparison and show that beta-G family of distributions model more suitable for distribution of a lifetime.

One of the main goals of studying the time series is estimation of prediction interval based on an observed sample path of the process. In recent years, different semiparametric bootstrap methods have been proposed to find the prediction intervals without any assumption of error distribution. In semiparametric bootstrap methods, a linear process is approximated by an autoregressive process. Then the bootstrap samples are generated by resampling from the residuals. In this paper, first these sieve bootstrap methods are defined and, then, in a simulation study sieve bootstrap prediction intervals are compared with a standard Gaussian prediction interval. Finally, these methods are used to find the prediction intervals for weather data of Isfahan.

Neural networks are among those mathematical models which are used to model non-linear time series with high accuracy. The advantage with these linear times series as opposed to topical ones is that they don’t require restrictive assumptions. The accuracy of neural network based estimators as nonparametric models is of high importance. In that light، we can use bootstrapping to calculate the accuracy of estimators in the time series’ complex nonlinear structures. Though introduced in recent years these methods yield more accurate results in the bias calculation of estimators compared to the other ones. This paper introduces neural network bootstrap، bootstrap autoregressive، moving block bootstrap method and residual bootstrap methods in time series. Then these four algorithms are compared with each other in a simulation study. Finally an example related to Iran’s kerosene price monthly data is worked out.

In the new class of weighted exponential distributions was presented by Gupta and Kundu [1], the skewness parameter has been added to the exponential distribution. Therefore the weighted exponential distribution has the skewness and scale parameters. In this paper, we first study Anderson and Kolmogorov-Smirnov goodness of fit tests for this class with unknown parameters. Then, we apply bootstrap method for estimation of Anderson’s quantile and another method for Kolmogorov-Smirnov. We use the maximum likelihood method for estimation of parameters. Finally, we compare Kolmogorov-Smirnov and Anderson tests in a Monte Carlo simulation study. The results show that the Kolmogorov–Smirnov test has greater power than Anderson test.