Mahmoud M. Smadi, M. T. Alodat · Journal of Modern Applied Statistical Methods · 2011
A Bayesian approach in threshold moving average model for time series with two regimes is provided. The posterior distribution of the delay and threshold parameters are used to examine and investigate the intrinsic characteristics of this nonlinear time series model. The proposed approach is applied to both simulated data and a real data set obtained from a chemical system. Key words: Threshold time series, moving average model, Bayesian
Cited by 3Open access
Shimin Yang · 1999
Cited by 0
Average Bioequivalence, Pulak Ghosh · 2007
Bioequivalence trials are usually conducted to compare two or more formula-tions of a drug. Simultaneous assessment of bioequivalence on multiple endpoints is called multivariate bioequivalence. Despite the fact that some tests for multivariate bioequivalence are suggested, current practice usually involves univariate bioequiv-alence assessments ignoring the correlations between the endpoints such as AUC and Cmax. In this paper we develop a semiparametric Bayesian test for bioequivalence under multiple endpoints. Specifically, we show how the correlation between the endpoints can be incorporated in the analysis and how this correlation affects the inference. Resulting estimates and posterior probabilities “borrow strength” ’ from one another where the amount and direction of the strength borrowed are deter-
Cited by 0
Pulak Ghosh · 2007
Bioequivalence trials are usually conducted to compare two or more formula-tions of a drug. Simultaneous assessment of bioequivalence on multiple endpoints is called multivariate bioequivalence. Despite the fact that some tests for multivariate bioequivalence are suggested, current practice usually involves univariate bioequiv-alence assessments ignoring the correlations between the endpoints such as AUC and Cmax. In this paper we develop a semiparametric Bayesian test for bioequivalence under multiple endpoints. Specifically, we show how the correlation between the endpoints can be incorporated in the analysis and how this correlation affects the inference. Resulting estimates and posterior probabilities “borrow strength” ’ from one another where the amount and direction of the strength borrowed are deter-
Cited by 0
Pulak Ghosh, Mithat Gönen · Statistics in Medicine · 2007
Bioequivalence trials are usually conducted to compare two or more formulations of a drug. Simultaneous assessment of bioequivalence on multiple endpoints is called multivariate bioequivalence. Despite the fact that some tests for multivariate bioequivalence are suggested, current practice usually involves univariate bioequivalence assessments ignoring the correlations between the endpoints such as AUC and C(max). In this paper we develop a semiparametric Bayesian test for bioequivalence under multiple endpoints. Specifically, we show how the correlation between the endpoints can be incorporated in the analysis and how this correlation affects the inference. Resulting estimates and posterior probabilities 'borrow strength' from one another where the amount and the direction of the strength borrowed are determined by the prior correlations. The method developed is illustrated using a real data set.
Cited by 24
Shaarawy, Samir Moustafa · SHAREOK (University of Oklahoma) · 2015
Cited by 0Open access
Samir M. Shaarawy, Emad E. A. Soliman, Sherif S. Ali · Communication in Statistics- Theory and Methods · 2007
This study approaches the Bayesian identification of moving average processes using an approximate likelihood function and a normal gamma prior density. The marginal posterior probability mass function of the model order is developed in a convenient form. Then one may investigate the posterior probabilities over the grid of the order and choose the order with the highest probability to solve the identification problem. A comprehensive simulation study is carried out to demonstrate the performance of the proposed procedure and check its adequacy in handling the identification problem. In addition, the proposed Bayesian procedure is compared with some non Bayesian automatic techniques and another Bayesian technique. The numerical results support the adequacy of using the proposed procedure in solving the identification problem of moving average processes.
Cited by 14
Pulak Ghosh, Gary L. Rosner · 2005
Bioequivalence assessment is an issue of great interest. Development of statistical methods for assessing bioequivalence is an important area of research for statisticians. Bioequivalence is usually determined based on the normal distribution. We relax this assumption and develop a semiparametric mixed model for bioequivalence data. The proposed method is quite flexible and practically meaningful. Our proposed method is based on a mixture normal distribution and a nonparametric Bayesian approach using mixture of Dirichlet process prior. A numerical example illustrates the use of our procedure.
Cited by 0
S. Prabakaran, M. R. Srinivasan · 2015
Ranking the mixed information as categorical, nominal and score card of the product under different values which help to identify the top priority from customer performance. This paper widely concentrate on averaging the score which obtain from textual information, dichotomo leads us to mixed attribute data values from feature of the product, rating and opinion or sentimental score. Organization will get benefited on understand about their service, product requirement expectations from customer prudence opinion. Thus, ranking or scoring is required to alter such service in online recommender system Ranking the mixed information as categorical, nominal and score card values to stream and identify average performance of the product under different values which help to identify the top priority from customer performance. This paper widely concentrate on averaging the score which obtain from textual information, dichotomo leads us to mixed attribute data values from feature of the product, rating and opinion or sentimental score. Organization will get benefited on understand about their service, product requirement expectations from customer prudence opinion. Thus, ranking or scoring is required to alter such service in online recommender system Average Score card, Bayesian, Text Mining and Mixed attributed data
Cited by 0
S.Ali, Sherif · The Egyptian Statistical Journal/The Egyptian Statistical Journal · 2015
Forecasting is the final and one of the most important phases of a multivariate time series analysis. This article develops an approximate Bayesian methodology to forecast the future observations of vector moving average processes. By employing an approximate conditional likelihood and a matrix normal-Wishart, or Jeffreys vague prior, the proposed Bayesian forecasting methodology is based on deriving an approximate posterior probability density of the future observations in a convenient form. Then one may easily calculate the posterior mean vector and precision of the future vector of observations and hence develops a Highest Predictive Density (HPD) region for the future observations. Four simulation studies, with Jeffreys' vague prior, have been conducted in order to demonstrate the idea of the proposed methodology and test its adequacy in solving the forecasting problems of vector moving average processes. The numerical results show that the proposed methodology can efficiently forecast the vector moving average processes with high precision for moderate and large time series length.
Cited by 1
Yao, Yuling, Vehtari, Aki, Simpson, Daniel et al. · arXiv (Cornell University) · 2017
The widely recommended procedure of Bayesian model averaging is flawed in the M-open setting in which the true data-generating process is not one of the candidate models being fit. We take the idea of stacking from the point estimation literature and generalize to the combination of predictive distributions, extending the utility function to any proper scoring rule, using Pareto smoothed importance sampling to efficiently compute the required leave-one-out posterior distributions and regularization to get more stability. We compare stacking of predictive distributions to several alternatives: stacking of means, Bayesian model averaging (BMA), pseudo-BMA using AIC-type weighting, and a variant of pseudo-BMA that is stabilized using the Bayesian bootstrap. Based on simulations and real-data applications, we recommend stacking of predictive distributions, with BB-pseudo-BMA as an approximate alternative when computation cost is an issue.
Cited by 25Open access
M.Shaarawy, Samir, E.A.Soliman, Emad, M.Elsouda, Rasha · The Egyptian Statistical Journal/The Egyptian Statistical Journal · 2011
This study approaches the Bayesian identification of seasonal moving average processes using an approximate likelihood function and a normal gamma prior density. The marginal posterior probability mass function of the model orders is developed in a convenient form. Then one may investigate the posterior probabilities over the grid of the orders and choose the orders combination with the highest probability to solve the identification problem. A comprehensive simulation study is carried out to demonstrate the performance of the proposed procedure and check its adequacy in handling the identification problem. In addition, the proposed Bayesian procedure is compared with the AIC automatic technique. The numerical results support the adequacy of using the proposed procedure in solving the identification problem of seasonal moving average processes.
Cited by 2
Thelma Sáfadi, Pedro A. Morettin · 2008
In this paper we consider a Bayesian analysis for threshold autoregressive moving average models. Two different methods are used for the special case of two regimes. In the first we consider a hierarchical prior and obtain posterior distributions in closed form. In the second, a rearranged procedure due Tsay (1989) is used, in conjunction with the Gibbs sampler and Metropolis-Hastings algorithm. Applications are given for a simulated series and for the sunspot data.
Cited by 0
Pulak Ghosh, Gary L. Rosner · Statistics in Medicine · 2006
Bioequivalence assessment is an issue of great interest. Development of statistical methods for assessing bioequivalence is an important area of research for statisticians. Bioequivalence is usually determined based on the normal distribution. We relax this assumption and develop a semi-parametric mixed model for bioequivalence data. The proposed method is quite flexible and practically meaningful. Our proposed method is based on a mixture normal distribution and a non-parametric Bayesian approach using a Dirichlet process mixture prior. A numerical example illustrates the use of our procedure.
Cited by 19
Pat Langley, Stephanie Sage · 1999
In this paper we present an average-case analysis of the naive Bayesian clas-si er, a simple induction algorithm that performs well in many domains. Our analysis assumes a monotone `M of N ' target concept and training data that consists of independent Boolean attributes. The analysis supposes a known target concept and distribution of instances, but includes parameters for the number of training cases, the number of irrelevant, relevant, and necessary at-tributes, the probability of each attribute, and the amount of class noise. Our approach diers from previous average-case analyses by introducing approxi-mations to achieve computational tractability. This lets us explore the behav-ioral implications of the model for larger training and attribute sets than the earlier exact analyses, and experimental studies show that the analysis makes very accurate predictions despite its use of approximations. In closing, we suggest promising directions for future research on the average-case analysis of induction.
Cited by 0
Journal of Statistics Applications & Probability · 2023
This paper utilizes the Gibbs sampling technique to develop a Bayesian inference for Seasonal Moving Average (SMA) model, which includes parameters that distinguish between Multiplicative and Non-multiplicative models (referred to as Augmented Seasonal Moving Average hereafter). The construction of Bayesian inference involves several steps. Firstly, the method of Non-linear least squares (NLS) is used to estimate unknown lagged errors, allowing for the approximation of the complex likelihood function. Secondly, both a semi-conjugate prior distribution and a non- informative prior distribution are applied to the unknown parameters and initial errors. Thirdly, the prior distributions are combined with the approximated likelihood function to obtain the joint posterior distribution. Lastly, the full conditional distributions are derived as part of the Gibbs sampling process. The proposed method is notable for its simplicity in assessing the significance of the parameters that distinguish between Multiplicative and Non-multiplicative models, a task that is challenging to accomplish using classical analysis. The convergence of the method was verified, ensuring that it reached stable and reliable results.
Cited by 0Open access
Pulak Ghosh, Ravindra Khattree · Journal of Biopharmaceutical Statistics · 2003
In recent years, bioavailability studies for assessment of bioequivalence between two or more drug formulations have become very popular in drug development. However the current practice for the assessment of bioequivalence suffers from certain serious drawbacks. For example, sometimes these tests fail to control the consumer's risk. In this article a new methodology based on the application of Bayes' factor for solving the average bioequivalence problem is proposed. We compare our approach with the existing methods by using real data sets from the Food and Drug Administration (FDA). Results are further explored using simulation studies.
Cited by 11
Morettin, Pedro Alberto · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · 2000
Cited by 0Open access
Howaida Elsayed · المجلة العملیة التجارة والتمویل · 2023
In this article, a new Bayesian approach is used to identify the autoregressive moving average models. Employing approximation error is the foundation of the suggested Bayesian methodology. We take into consideration presence of an approximation error when substituting lagged errors of the original autoregressive moving average model with suitably lagged residuals from along autoregression . The direct Bayesian identification approach is utilized for solving the Bayesian identification issue of autoregressive moving average processes employing both informative and non-informative priors. The theoretical derivations of the direct Bayesian identification approach are carried out utilizing the aforementioned priors. We compare the effectiveness of the Broemeling and Shaarawy approach with proposed Bayesian approach for determining the orders of autoregressive moving average models by utilizing an actual data set and numerous simulated experiments. The outcomes of simulations and actual data demonstrate that the suggested approach is superior to the Broemeling and Shaarawy approach for determining the orders of autoregressive moving average processes.
Cited by 0Open access
Mohamed A. Ismail, Essam A. Ahmed, Howaida M. Ezz El-Din · Advances and Applications in Statistics · 2015
Cited by 3