فهرست مطالب

Journal of Iranian Statistical Society
Volume:20 Issue: 2, Autumn 2021

  • تاریخ انتشار: 1401/01/30
  • تعداد عناوین: 8
|
  • Yasser Al Zaim, MohammadReza Faridrohani* Pages 1-28

    In this paper, we present the Anderson-Darling (AD) and Kolmogorov-Smirnov (KS) goodness of fit statistics for stationary and non-stationary random fields. Namely, we adopt an easy-to-apply method based on a random projection of a Hilbert-valued random field onto the real line R, and then, applying the well-known AD and KS goodness of fit tests. We conclude this paper by studying the behavior of the proposed approach in the wide range of simulation studies and in a case study of autistic and healthy individuals.

    Keywords: Goodness of Fit Tests, Multiple Testing, One-dimensional Random Projection, Random Field
  • Sahar Asili, Adel Mohammadpour*, Omid Naghshineh Arjmand, Mousa Golalizazdedh Pages 29-42

    Recently, some statistical studies have been done using the shape data. One of these studies is clustering shape data, which is the main topic of this paper. We are going to study some clustering algorithms on shape data and then introduce the best algorithm based on accuracy, speed, and scalability criteria. In addition, we propose a method for representing the shape data that facilitates and speeds up the shape clustering algorithms. Although the mentioned method is not very accurate, it is fast; therefore, it is useful for datasets with a high number of landmarks or observations, which take a long time to be clustered by means of other algorithms. It should be noted that this method is not new, but in this article we apply it in shape data analysis.

    Keywords: Shape Data Clustering, Hierarchical, Partitioning, Fuzzy Clustering
  • Abdolreza Sayyareh* Pages 43-63

    The two main goals in model selection are firstly introducing an approach to test homogeneity of several rival models and secondly selecting a set of reasonable models or estimating the best rival model to the true one. In this paper we extend Vuong's method for several models to cluster them. Based on the working paper of Katayama $(2008)$, we propose an approach to test whether rival models have expected relations. The multivariate extension of Vuong's test gives the opportunity to examine some hypotheses about the rival models and their relations with respect to the unknown true model. On the other hand, the standard method of model selection provides an implementation of Occam's razor, in which parsimony or simplicity is balanced against goodness of fit. Therefore, we are interested in clustering the rival models based on their divergence from the true model to select a suitable set of rival models. In this paper we have introduced two approaches to select suitable sets of rival models based on the multivariate extension of Vuong's test and quasi clustering approach.

    Keywords: Akaike Information Criterion, Clustering, Kullback-Leibler Divergence, Mis-specified Models, Non-nested Models
  • Mostafa Hossaini, Abdolhamid Rezaei Roknabadi* Pages 65-78

    Sometimes in order to estimate population parameters such as mean and total values, we extract a random sample by cluster sampling method, and after completing sampling, we are interested in using the same sample to estimate the desired parameters in a subset of the population, which is said subpopulation. In this paper, we try to estimate subpopulation parameters in different cases when one-stage cluster sampling design is used.

    Keywords: Finite Population, Subpopulation, Cluster Sampling, Unbiased
  • Nahid Ganjealivand, Fatemeh Ghapani*, Ali Zaherzadeh, Farshin Hormozinejad Pages 79-102

    In this study, the stochastic restricted and unrestricted two-parameter estimators of fixed and random effects are investigated in the linear mixed measurement error models. For this purpose, the asymptotic properties and then the comparisons under the criterion of mean squared error matrix (MSEM) are derived. Furthermore, the proposed methods are used for estimating the biasing parameters. Finally, a real data analysis and a simulation study are provided to evaluate the performance of the proposed estimators.

    Keywords: Linear Mixed Measurement Error Model, Two Parameter Estimation, Stochastic Restricted Two Parameter Estimation, Mean-square Error Matrix
  • Zahra Barkhordar, Zahra Khodadadi*, Karim Zare, Mohsen Maleki Pages 103-116

    Various types of Coronaviruses are enveloped RNA viruses from the Corona-viridae family and part of the Coronavirinae subfamily. This family of viruses affects neurological, gastrointestinal, hepatic, and respiratory systems. Recently, a new memb-er of this family, named Covid-19, is moving around the world. The expansion of Covid-19 carries many risks, and its control requires strict planning and special policies. Iran is one of the countries in the world where the outbreak of the disease has been serious and the daily number of confirmed cases is increasing in some places. Prediction of future confirmed cases of the COVID-19 is planning with a certain policy to provide the clinical and medical supplementary. Time series models based on the statistical methodology are useful to model and forecast time-indexed data. In many situations in the real world, the ordinary classical time series models based on the symmetrical and light-tailed distributions cannot lead to a satisfactory result (or predicion). Thus, in our methodology, we consider the analysis of symmetrical/asymmetrical and light/heavy-tailed time series data based on the two-piece scale mixture of the normal (TP-SMN) distribution. The proposed model is useful for symmetrical and light-tailed time series data, and it can work well relative to the ordinary Gaussian and symmetry models (especially for COVID-19 datasets). In this study, we fit the proposed model to the historical COVID-19 datasets in Iran. We show that the proposed time series model is the best fitted model to each dataset. Finally, we predict the number of confirmed COVID-19 cases in Iran.

    Keywords: Coronaviruses, COVID-19, Prediction, Time Series Modeling, Two Pieces Distributions, Scale Mixture of Normal Distribution
  • Hossein Nadeb*, Hamzeh Torabi Pages 117-128

    This paper discusses the preservation of some stochastic orders between two interdependent series and parallel systems when the survival and distribution functions of all components switch to the exponentiated model. For the series systems, the likelihood ratio, hazard rate, usual, aging faster, aging intensity, convex transform, star, superadditive and dispersive orderings, and for the parallel systems the reversed hazard, usual, convex transform, star, superadditive and dispersive orderings are studied. Also, we present a necessary and sufficient condition for being finiteness of the moments of the switched series and switched parallel systems.

    Keywords: Exponentiated models, max-stable copulas, parallel system, series system, stochastic ordering
  • Jiju Gillariose, Lishamol Tomy, Farrukh Jamal, Christophe Chesneau* Pages 129-152

    Finding new families of distributions has become a popular tool in statistical research. In this article, we introduce a new flexible four-parameter discrete model based on the Marshall-Olkin approach, namely, the discrete Kumaraswamy Marshall-Olkin exponential distribution. The proposed distribution can be viewed as another generalization of the geometric distribution and enfolds some important distributions as special cases. Some properties of the new distribution are derived. The model parameters are estimated by the maximum likelihood method, with validation through a complete simulation study. The usefulness of the new model is illustrated via count-type real data sets.

    Keywords: Discrete Distributions, Exponential Distribution, Generalized Family, Geometric Distribution, Marshall-Olkin Extended Distribution, Maximum Likelihood Estimation