In this paper, we propose a new criterion, named PICa, to simultaneously select explanatory variables in the mean model and variance model in heteroscedastic linear models based on the model structure. We show that th...In this paper, we propose a new criterion, named PICa, to simultaneously select explanatory variables in the mean model and variance model in heteroscedastic linear models based on the model structure. We show that the new criterion can select the true mean model and a correct variance model with probability tending to 1 under mild conditions. Simulation studies and a real example are presented to evaluate the new criterion, and it turns out that the proposed approach performs well.展开更多
Consider heteroscedastic regression model Yni= g（xni） ＋ σniεni （1 〈 i 〈 n）, where σ2ni= f（uni）, the design points （xni, uni） are known and nonrandom, g（.） and f（.） are unknown functions defined on cl...Consider heteroscedastic regression model Yni= g（xni） ＋ σniεni （1 〈 i 〈 n）, where σ2ni= f（uni）, the design points （xni, uni） are known and nonrandom, g（.） and f（.） are unknown functions defined on closed interval [0, 1], and the random errors （εni, 1 ≤i≤ n） axe assumed to have the same distribution as （ξi, 1 ≤ i ≤ n）, which is a stationary and a-mixing time series with Eξi =0. Under appropriate conditions, we study asymptotic normality of wavelet estimators of g（.） and f（.）. Finite sample behavior of the estimators is investigated via simulations, too.展开更多
The linear weighted regression model is one of the models studied in many articles in recent years. Some further problems, such as disturbation, influence measure and estimate efficiency, have been discussed in this p...The linear weighted regression model is one of the models studied in many articles in recent years. Some further problems, such as disturbation, influence measure and estimate efficiency, have been discussed in this paper on the basis of the regression diagnosties. The partial conclusions of this paper are the extension of the familiar concepts in the regression diagnosties theory[2' 3,7] because they are representative of this kind of model.展开更多
Mixture of Experts(MoE)regression models are widely studied in statistics and machine learning for modeling heterogeneity in data for regression,clustering and classification.Laplace distribution is one of the most im...Mixture of Experts(MoE)regression models are widely studied in statistics and machine learning for modeling heterogeneity in data for regression,clustering and classification.Laplace distribution is one of the most important statistical tools to analyze thick and tail data.Laplace Mixture of Linear Experts(LMoLE)regression models are based on the Laplace distribution which is more robust.Similar to modelling variance parameter in a homogeneous population,we propose and study a new novel class of models:heteroscedastic Laplace mixture of experts regression models to analyze the heteroscedastic data coming from a heterogeneous population in this paper.The issues of maximum likelihood estimation are addressed.In particular,Minorization-Maximization(MM)algorithm for estimating the regression parameters is developed.Properties of the estimators of the regression coefficients are evaluated through Monte Carlo simulations.Results from the analysis of two real data sets are presented.展开更多
When dealing with regression analysis,heteroscedasticity is a problem that the authors have to face with.Especially if little information can be got in advance,detection of heteroscedasticity as well as estimation of ...When dealing with regression analysis,heteroscedasticity is a problem that the authors have to face with.Especially if little information can be got in advance,detection of heteroscedasticity as well as estimation of statistical models could be even more difficult.To this end,this paper proposes a quantile difference method(QDM) that can effectively estimate the heteroscedastic function.This method,being completely free from the estimation of mean regression function,is simple,robust and easy to implement.Moreover,the QDM method enables the detection of heteroscedasticity without any restrictions on error terms,consequently being widely applied.What is worth mentioning is that based on the proposed approach estimators of both mean regression function and heteroscedastic function can be obtained.In the end,the authors conduct some simulations to examine the performance of the proposed methods and use a real data to make an illustration.展开更多
Wavelets are applied to detect the jumps in a heteroscedastic regression model. It is shown that the wavelet coefficients of the data have significantly large absolute values across fine scale levels near the jump poi...Wavelets are applied to detect the jumps in a heteroscedastic regression model. It is shown that the wavelet coefficients of the data have significantly large absolute values across fine scale levels near the jump points. Then a procedure is developed to estimate the jumps and jump heights. All estimators are proved to be consistent.展开更多
The heteroscedastic regression model was established and the heteroscedastic regression analysis method was presented for mixed data composed of complete data,type-Ⅰ censored data and type-Ⅱ censored data from the l...The heteroscedastic regression model was established and the heteroscedastic regression analysis method was presented for mixed data composed of complete data,type-Ⅰ censored data and type-Ⅱ censored data from the location-scale distribution.The best unbiased estimations of regression coefficients,as well as the confidence limits of the location parameter and scale parameter were given.Furthermore,the point estimations and confidence limits of percentiles were obtained.Thus,the traditional multiple regression analysis method which is only suitable to the complete data from normal distribution can be extended to the cases of heteroscedastic mixed data and the location-scale distribution.So the presented method has a broad range of promising applications.展开更多
Consider the heteroscedastic regression model Yi = g（xi） ＋ σiei, 1 ≤ i ≤ n, where σi^2 = f（ui）, here （xi, ui） being fixed design points, g and f being unknown functions defined on [0, 1], ei being independe...Consider the heteroscedastic regression model Yi = g（xi） ＋ σiei, 1 ≤ i ≤ n, where σi^2 = f（ui）, here （xi, ui） being fixed design points, g and f being unknown functions defined on [0, 1], ei being independent random errors with mean zero. Assuming that Yi are censored randomly and the censored distribution function is known or unknown, we discuss the rates of strong uniformly convergence for wavelet estimators of g and f, respectively. Also, the asymptotic normality for the wavelet estimators of g is investigated.展开更多
Consider a repeated measurement partially linear regression model with anunknown vector parameter β_1, an unknown function g(·), and unknown heteroscedastic errorvariances. In order to improve the semiparametric...Consider a repeated measurement partially linear regression model with anunknown vector parameter β_1, an unknown function g(·), and unknown heteroscedastic errorvariances. In order to improve the semiparametric generalized least squares estimator (SGLSE) of ,we propose an iterative weighted semiparametric least squares estimator (IWSLSE) and show that itimproves upon the SGLSE in terms of asymptotic covariance matrix. An adaptive procedure is given todetermine the number of iterations. We also show that when the number of replicates is less than orequal to two, the IWSLSE can not improve upon the SGLSE. These results are generalizations of thosein [2] to the case of semiparametric regressions.展开更多
基金supported by National Natural Science Foundation of China (Grant No.10971007)Beijing Natural Science Fund (Grant No. 1072003)Science Fund of Beijing Education Committee
文摘In this paper, we propose a new criterion, named PICa, to simultaneously select explanatory variables in the mean model and variance model in heteroscedastic linear models based on the model structure. We show that the new criterion can select the true mean model and a correct variance model with probability tending to 1 under mild conditions. Simulation studies and a real example are presented to evaluate the new criterion, and it turns out that the proposed approach performs well.
基金supported by the National Natural Science Foundation of China under Grant No.10871146the Grant MTM2008-03129 from the Spanish Ministry of Science and Innovation
文摘Consider heteroscedastic regression model Yni= g（xni） ＋ σniεni （1 〈 i 〈 n）, where σ2ni= f（uni）, the design points （xni, uni） are known and nonrandom, g（.） and f（.） are unknown functions defined on closed interval [0, 1], and the random errors （εni, 1 ≤i≤ n） axe assumed to have the same distribution as （ξi, 1 ≤ i ≤ n）, which is a stationary and a-mixing time series with Eξi =0. Under appropriate conditions, we study asymptotic normality of wavelet estimators of g（.） and f（.）. Finite sample behavior of the estimators is investigated via simulations, too.
文摘The linear weighted regression model is one of the models studied in many articles in recent years. Some further problems, such as disturbation, influence measure and estimate efficiency, have been discussed in this paper on the basis of the regression diagnosties. The partial conclusions of this paper are the extension of the familiar concepts in the regression diagnosties theory[2' 3,7] because they are representative of this kind of model.
基金the National Natural Science Foundation of China(11861041,11261025).
文摘Mixture of Experts(MoE)regression models are widely studied in statistics and machine learning for modeling heterogeneity in data for regression,clustering and classification.Laplace distribution is one of the most important statistical tools to analyze thick and tail data.Laplace Mixture of Linear Experts(LMoLE)regression models are based on the Laplace distribution which is more robust.Similar to modelling variance parameter in a homogeneous population,we propose and study a new novel class of models:heteroscedastic Laplace mixture of experts regression models to analyze the heteroscedastic data coming from a heterogeneous population in this paper.The issues of maximum likelihood estimation are addressed.In particular,Minorization-Maximization(MM)algorithm for estimating the regression parameters is developed.Properties of the estimators of the regression coefficients are evaluated through Monte Carlo simulations.Results from the analysis of two real data sets are presented.
基金supported by the National Natural Science Foundation of China under Grant No.11271368the Major Program of Beijing Philosophy and Social Science Foundation of China under Grant No.15ZDA17+3 种基金the Specialized Research Fund for the Doctoral Program of Higher Education of China under Grant No.20130004110007the Key Program of National Philosophy and Social Science Foundation under Grant No.13AZD064the Fundamental Research Funds for the Central Universities,and the Research Funds of Renmin University of China under Grant No.15XNL008the Project of Flying Apsaras Scholar of Lanzhou University of Finance & Economics
文摘When dealing with regression analysis,heteroscedasticity is a problem that the authors have to face with.Especially if little information can be got in advance,detection of heteroscedasticity as well as estimation of statistical models could be even more difficult.To this end,this paper proposes a quantile difference method(QDM) that can effectively estimate the heteroscedastic function.This method,being completely free from the estimation of mean regression function,is simple,robust and easy to implement.Moreover,the QDM method enables the detection of heteroscedasticity without any restrictions on error terms,consequently being widely applied.What is worth mentioning is that based on the proposed approach estimators of both mean regression function and heteroscedastic function can be obtained.In the end,the authors conduct some simulations to examine the performance of the proposed methods and use a real data to make an illustration.
文摘Wavelets are applied to detect the jumps in a heteroscedastic regression model. It is shown that the wavelet coefficients of the data have significantly large absolute values across fine scale levels near the jump points. Then a procedure is developed to estimate the jumps and jump heights. All estimators are proved to be consistent.
基金Supported by the National Natural Science Foundation of China(Grant No.10472006)
文摘The heteroscedastic regression model was established and the heteroscedastic regression analysis method was presented for mixed data composed of complete data,type-Ⅰ censored data and type-Ⅱ censored data from the location-scale distribution.The best unbiased estimations of regression coefficients,as well as the confidence limits of the location parameter and scale parameter were given.Furthermore,the point estimations and confidence limits of percentiles were obtained.Thus,the traditional multiple regression analysis method which is only suitable to the complete data from normal distribution can be extended to the cases of heteroscedastic mixed data and the location-scale distribution.So the presented method has a broad range of promising applications.
基金the National Natural Science Foundation of China(10571136)a Wonkwang University Grant in 2007
文摘Consider the heteroscedastic regression model Yi = g（xi） ＋ σiei, 1 ≤ i ≤ n, where σi^2 = f（ui）, here （xi, ui） being fixed design points, g and f being unknown functions defined on [0, 1], ei being independent random errors with mean zero. Assuming that Yi are censored randomly and the censored distribution function is known or unknown, we discuss the rates of strong uniformly convergence for wavelet estimators of g and f, respectively. Also, the asymptotic normality for the wavelet estimators of g is investigated.
基金supported by a grant from the Natural Sciences and Engineering Research Council of Canada.
文摘Consider a repeated measurement partially linear regression model with anunknown vector parameter β_1, an unknown function g(·), and unknown heteroscedastic errorvariances. In order to improve the semiparametric generalized least squares estimator (SGLSE) of ,we propose an iterative weighted semiparametric least squares estimator (IWSLSE) and show that itimproves upon the SGLSE in terms of asymptotic covariance matrix. An adaptive procedure is given todetermine the number of iterations. We also show that when the number of replicates is less than orequal to two, the IWSLSE can not improve upon the SGLSE. These results are generalizations of thosein [2] to the case of semiparametric regressions.
