|
|
|
 |
Search published articles |
 |
|
Mojtaba Khazaei,
Volume 2, Issue 1 (8-2008)
Abstract
One of the models that can be used to study the relationship between Boolean random sets and explanatory variables is growth regression model which is defined by generalization of Boolean model and permitting its grains distribution to be dependent on the values of explanatory variables. This model can be used in the study of behavior of Boolean random sets when their coverage regions variation is associated with the variation of grains size. In this paper we make possible the identification and fitting suitable growth model using available information in Boolean model realizations and values of explanatory variables. Also, a suitable method for fitting growth regression model is presented and properties of its obtained estimators are studied by a simulation study.
Nabaz Esmaeilzadeh, Hooshang Talebi,
Volume 2, Issue 2 (2-2009)
Abstract
So far, the Plackett-Burman (PB) designs have been considered as saturated non-regular fractional factorial designs for screening purposes. Since introduction of the hidden projection of PB's by Wang and Wu (1995), the estimation capability of such projections onto a subset of factors has been investigated by many researchers. In this paper, by considering the search and estimation capability of a design, we introduce the post-stage search designs, using sparsity principle of factorial effects. That is, by the post-stage property of a design, we mean the capability of such a design in searching and estimating possible nonzero 3-factorial interactions along with estimation of the general mean, main effects and active 2-factor interaction effects, identified in the pre-stage. We show that a 12-runs PB projections onto 4 and 5 factors are post-stage search designs.
Hamidreza Mostafaei, Maryam Safaei,
Volume 3, Issue 2 (3-2010)
Abstract
In 2002 the enforcement on policy unification of exchange rate caused dramatic decrease in the nominal price of Iran's Rial against U.S.dollar per on unit.For this reason due to the existence of unexpected and large change we cannot use the linear time series models for surveying the fluctuations of the rate of Iran's Rial change against U.S. dollar per on unit. In this paper we compare Self-Exciting threshold autoregressive and Markov switching autoregressive model. then it will be show that only the Markov switching autoregressive model being able to show the behaviors of Iran's exchange rate.
Nasrollah Iranpanah,
Volume 3, Issue 2 (3-2010)
Abstract
Abstract: In many environmental studies, the collected data are usually spatially dependent. Determination of the spatial correlation structure of the data and prediction are two important problem in statistical analysis of spatial data. To do so, often, a parametric variogram model is fitted to the empirical variogram of the data by estimating the unknown parameters of the mentioned variogram. Since there are no closed formulas for the variogram parameters estimator, they are usually computed numerically. Therefore, the precision measures of the variogram parameters estimator and spatial prediction can be calculated using bootstrap methods. Lahiri (2003) proposed the moving block bootstrap method for spatial data, in which observations are divided into several moving blocks and resampling is done from them. Since, in this method, the presence of boundary observations in the resampling blocks have less selection chance than the other observations, therefore, the estimator of the precision measures would be biased. In this paper, revising the moving block bootstrap method, the separate block bootstrap method was presented for estimating the precision measures of the variogram parameters estimator and spatial prediction. Then its usage was illustrated in an applied example.
Mohammadvali Ahmadi, Majid Sarmad,
Volume 3, Issue 2 (3-2010)
Abstract
Because of importance and popularity of the Normal distribution, the samples based on this distribution has been considered and the outliers are identified using cut-off values which are dependent on the sample size. A decision problem has been structured to obtain the optimal cut-off value. The problem is solved by a simulation study with a minimax rule.
Ghadi Mahdavi, Zahra Majedi,
Volume 4, Issue 1 (9-2010)
Abstract
The GARCH(1,1) and GARCH(1,1)-t models lead to highly volatile quantile forecasts, while historical simulation, Variance–Covariance, adaptive generalized Pareto distribution and non-adaptive generalized Pareto distribution models provide more stable quantile forecasts. In general, GARCH(1,1)-t, generalized Pareto distribution models and historical simulation are preferable for most quantiles.
Mehrdad Niaparast, Sahar Mehr-Mansour,
Volume 4, Issue 1 (9-2010)
Abstract
The main part of optimal designs in the mixed effects models concentrates on linear models and binary models. Recently, Poisson models with random effects have been considered by some researchers. In this paper, an especial case of the mixed effects Poisson model, namely Poisson regression with random intercept is considered. Experimental design variations are obtained in terms of the random effect variance and indicated that the variations depend on the variance parameter. Using D-efficiency criterion, the impression of random effect on the experimental setting points is studied. These points are compared with the optimal experimental setting points in the corresponding model without random effect. We indicate that the D-efficiency depends on the variance of random effect.
Atefeh Farokhy, Mousa Golalizadeh,
Volume 4, Issue 1 (9-2010)
Abstract
The multilevel models are used in applied sciences including social sciences, sociology, medicine, economic for analysing correlated data. There are various approaches to estimate the model parameters when the responses are normally distributed. To implement the Bayesian approach, a generalized version of the Markov Chain Monte Carlo algorithm, which has a simple structure and removes the correlations among the simulated samples for the fixed parameters and the errors in higher levels, is used in this article. Because the dimension of the covariance matrix for the new error vector is increased, based upon the Cholesky decomposition of the covariance matrix, two methods are proposed to speed the convergence of this approach. Then, the performances of these methods are evaluated in a simulation study and real life data.
Haleh Nekoee, Hooshang Talebi,
Volume 4, Issue 2 (3-2011)
Abstract
Two designs, with N runs and k factors all with two levels are said to be isomorphic or equivalent if one is obtained from another by permuting rows, columns or/and changing the levels of one or more factors. When N and k increase the matter of isomorphic recognition of two designs will be complicated. Therefore it is essential to apply needed conditions which are able to recognize and separate non-isomorphic designs. It should be done in the least possible time. Majority of needed existed conditions in the literature review can’t meet the two objectives, maximum separation in minimum span, at the same time. In this paper, a new method has been used to present non-equivalent. This new method has been designed abased on choice and comparisons of one or some rows of design matrix. This new method hopefully has higher ability to recognize non-equivalence. Besides, the new method has lower calculation and therefore is able to determine non-equivalence of two designs.
Ahad Malekzadeh, Mina Tohidi,
Volume 4, Issue 2 (3-2011)
Abstract
Coefficient of determination is an important criterion in different applications. The problem of point estimation of this parameter has been considered by many researchers. In this paper, the class of linear estimators of R^2 was considered. Then, two new estimators were proposed, which have lower risks than other usual estimator, such as the sample coefficient of determination and its adjusted form. Also on the basis of some simulations, we show that the Jacknife estimator is an efficient estimator with lower risk, when the number of observations is small.
Maryam Safaei,
Volume 5, Issue 1 (9-2011)
Abstract
This paper offers a method of the estimation of the transition probability for the behaviors of financial time series by Markov Switching Autoregressive model. Using this model, the behaviors of fluctuations of exchange rate form two regimes low and high changes rate are considered. Results of prediction show that the persistence probability of regimes will be decreased. Thus, the probability of transition to other regime will be increased if process were in a specific regime.
Masoud Ajami, Vaheed Fakoor, Sara Jomhoori,
Volume 5, Issue 1 (9-2011)
Abstract
In sampling, arisen data with probability proportional to its length is called Length-bised. Nonparametric density estimation in length-biased sampling is more difficult than other states. One of the famous estimators in this context is the one introduced by Jones (1991). In this paper, we calculate the bandwidth parameter of this estimator by Bayes'method. The strong consistency of this estimator have been proved with a random Bandwidth. We have compared the performance of Bayes'method with cross validation by using simulation studies.
Mojdeh Esmailzadeh, Farzad Eskandari, Sima Naghizadeh Ardabili,
Volume 5, Issue 2 (2-2012)
Abstract
Forecasting the future status for underlying systems or random process, is one of the most important problems. In such situations, in addition to variables, the parameters may vary during the time and hence, the independence assumption between variables and parameters is broken. For analyzing this systems, usually the dynamic generalized linear models are used based on Markov chain Monte Carlo algorithm. The purpose of this paper is applying the Bayesian dynamic generalized linear models in non-conjugate discrete structures. First, the concepts of dynamic generalized linear models are reviewed. Then, the Bayesian modeling of non-conjugated discrete structures using MCMC algorithm is studied. Finally, using the investigated model the real data set related to the economic activity condition in three provinces of Iran during the years 2006-2008 are analysed.
Ebrahim Khodaie, Roohollah Shojaei,
Volume 6, Issue 1 (8-2012)
Abstract
Sampling weights are calibrated according to the theory of calibration when the sum of population total for auxiliary variables is known. Under known population, totals for auxiliary variables and some conditions Devile and Sarndal showed that generalized regression estimators could approximate calibration estimators and their variances. In this paper, under unknown population totals for auxiliary variables, an estimator for the population total is proposed and its variance is obtained. It is shown that our estimator for the population total is more efficient than the Horvitz-Thompson estimators by theoretically and simulation results.
Abouzar Bazyari,
Volume 6, Issue 1 (8-2012)
Abstract
In the individual risk processes of an insurance company with dependent claim sizes, determination of the ruin probability and time to ruin are very important. Exact computing of theses probabilities, because of it's complex structure, is not easy. In this paper, Monte Carlo simulation method is used to obtain the ruin probabilities estimates, times to ruin and confidence interval for the ruin probability estimates of the mentioned process for different dependence level of claims. In this simulation the multivariate Frank copula function and Marshall and Olkin's algorithm are provided to generate the dependent claims. Then it has shown that with increasing the dependence level of claim sizes the ruin probability of the risk process increases, while its time to ruin decreases
Sayedeh Fatemeh Miri, Ehsan Bahrami Samani,
Volume 6, Issue 1 (8-2012)
Abstract
In this paper a general model is proposed for the joint distribution of nominal, ordinal and continuous variables with and without missing data. Closed forms are presented for likelihood functions of general location models. Also the Joe approximation is used for the parameters of general location models with mixed continuous, ordinal and nominal data with non-ignorable missing responses. To explain the ability of proposed models some simulation studies are performed and some real data are analyzed from a foreign language achievement study.
Mohammad Amini, Hadi Jabbari Noughabi, Mahla Ghasemnejad Farsangi,
Volume 6, Issue 2 (2-2013)
Abstract
In this paper, three new non-parametric estimator for upper tail dependence measure are introduced and it is shown that these estimators are consistent and asymptotically unbiased. Also these estimators are compared using the Mont Carlo simulation of three different copulas and present a new method in order to select the best estimator by applying the real data.
Hamidreza Fotouhi, Mousa Golalizadeh,
Volume 6, Issue 2 (2-2013)
Abstract
One of the typical aims of statistical shape analysis, in addition to deriving an estimate of mean shape, is to get an estimate of shape variability. This aim is achived through employing the principal component analysis. Because the principal component analysis is limited to data on Euclidean space, this method cannot be applied for the shape data which are inherently non-Euclidean data. In this situation, the principal geodesic analysis or its linear approximation can be used as a generalization of the principal component analysis in non-Euclidean space. Because the main root of this method is the gradient descent algorithm, revealing some of its main defects, a new algorithm is proposed in this paper which leads to a robust estimate of mean shape and also preserves the geometrical structure of shape. Then, providing some theoretical aspects of principal geodesic analysis, its application is evaluated in a simulation study and in real data.
Abdollah Safari, Ali Sharifi, Hamid Pezeshk, Peyman Nickchi, Sayed-Amir Marashi, Changiz Eslahchi,
Volume 6, Issue 2 (2-2013)
Abstract
There are several methods for inference about gene networks, but there are few cases in which the historical information have been considered. In this research we deal with Bayesian inference on gene network. We apply a Bayesian framework to use the available information. Assuming a proper prior distribution and taking the dependency of parameters into account, we seek a model to obtain promising results. We also deal with the hyper parameter estimation. Two methods are considered. The results will be compared by the use of a simulation based on Gibbs sampler. The strengths and weaknesses of each method are briefly mentioned.
Arezou Mojiri, Soroush Alimoradi, Mohammadreza Ahmadzade,
Volume 7, Issue 1 (9-2013)
Abstract
Logistic regression models in classification problems by assuming the linear effects of covariates is a modeling for class membership posterior probabilities. The main problem that includes nonlinear combinations of covariates is maximum likelihood estimation (MLE) of the model parameters. In recent investigations, an approach of solving this problem is combination of neural networks, evolutionary algorithms and MLE methods. In this paper, another type of radial basis functions, namely inverse multiquadratic functions and hybrid method, are considered for estimating the parameters of these models. The experimental results of comparing the proposed models show that the inverse multiquadratic functions compared to the Gaussian functions have better precision in classification problems.
|
|
