As an extension of linear regression in functional data analysis, functional linear regression has been studied by many researchers and applied in various fields. However, in many cases, data is collected sequentially...As an extension of linear regression in functional data analysis, functional linear regression has been studied by many researchers and applied in various fields. However, in many cases, data is collected sequentially over time, for example the financial series, so it is necessary to consider the autocorrelated structure of errors in functional regression background. To this end, this paper considers a multiple functional linear model with autoregressive errors. Based on the functional principal component analysis, we apply the least square procedure to estimate the functional coefficients and autoregression coefficients. Under some regular conditions, we establish the asymptotic properties of the proposed estimators. A simulation study is conducted to investigate the finite sample performance of our estimators. A real example on China's weather data is applied to illustrate the validity of our model.展开更多
Assessing the influence of individual observations of the functional linear models is important and challenging,especially when the observations are subject to missingness.In this paper,we introduce three case-deletio...Assessing the influence of individual observations of the functional linear models is important and challenging,especially when the observations are subject to missingness.In this paper,we introduce three case-deletion diagnostic measures to identify influential observations in functional linear models when the covariate is functional and observations on the scalar response are subject to nonignorable missingness.The nonignorable missing data mechanism is modeled via an exponential tilting semiparametric functional model.A semiparametric imputation procedure is developed to mitigate the effects of missing data.Valid estimations of the functional coefficients are based on functional principal components analysis using the imputed dataset.A smoothed bootstrap samplingmethod is introduced to estimate the diagnostic probability for each proposed diagnostic measure,which is helpful to unveil which observations have the larger influence on estimation and prediction.Simulation studies and a real data example are conducted to illustrate the finite performance of the proposed methods.展开更多
We propose sieve M-estimator for a semi-functional linear model in which the scalar response is explained by a linear operator of functional predictor and smooth functions of some real-valued random variables.Spline e...We propose sieve M-estimator for a semi-functional linear model in which the scalar response is explained by a linear operator of functional predictor and smooth functions of some real-valued random variables.Spline estimators of the functional coefficient and the smooth functions are considered,and by selecting appropriate knot numbers the optimal convergence rate and the asymptotic normality can be obtained under some mild conditions.Some simulation results and a real data example are presented to illustrate the performance of our estimation method.展开更多
Emerging integrative analysis of genomic and anatomical imaging data which has not been well developed, provides invaluable information for the holistic discovery of the genomic structure of disease and has the potent...Emerging integrative analysis of genomic and anatomical imaging data which has not been well developed, provides invaluable information for the holistic discovery of the genomic structure of disease and has the potential to open a new avenue for discovering novel disease susceptibility genes which cannot be identified if they are analyzed separately. A key issue to the success of imaging and genomic data analysis is how to reduce their dimensions. Most previous methods for imaging information extraction and RNA-seq data reduction do not explore imaging spatial information and often ignore gene expression variation at the genomic positional level. To overcome these limitations, we extend functional principle component analysis from one dimension to two dimensions （2DFPCA） for representing imaging data and develop a multiple functional linear model （MFLM） in which functional principal scores of images are taken as multiple quantitative traits and RNA-seq profile across a gene is taken as a function predictor for assessing the association of gene expression with images. The developed method has been applied to image and RNA- seq data of ovarian cancer and kidney renal clear cell carcinoma （KIRC） studies. We identified 24 and 84 genes whose expressions were associated with imaging variations in ovarian cancer and KIRC studies, respectively. Our results showed that many significantly associated genes with images were not differentially expressed, but revealed their morphological and metabolic functions. The results also demonstrated that the peaks of the estimated regression coefficient function in the MFLM often allowed the discovery of splicing sites and multiple isoforms of gene expressions.展开更多
For the functional partially linear models including flexible nonparametric part and functional linear part,the estimators of the nonlinear function and the slope function have been studied in existing literature.How ...For the functional partially linear models including flexible nonparametric part and functional linear part,the estimators of the nonlinear function and the slope function have been studied in existing literature.How to test the correlation between response and explanatory variables,however,still seems to be missing.Therefore,a test procedure for testing the linearity in the functional partially linear models will be proposed in this paper.A test statistic is constructed based on the existing estimators of the nonlinear and the slope functions.Further,we prove that the approximately asymptotic distribution of the proposed statistic is a chi-squared distribution under some regularity conditions.Finally,some simulation studies and a real data application are presented to demonstrate the performance of the proposed test statistic.展开更多
The class of bi-directional optimal velocity models can describe the bi-directional looking effect that usually exists in the reality and is even enhanced with the development of the connected vehicle technologies. It...The class of bi-directional optimal velocity models can describe the bi-directional looking effect that usually exists in the reality and is even enhanced with the development of the connected vehicle technologies. Its combined string stability condition can be obtained through the method of the ring-road based string stability analysis. However, the partial string stability about traffic fluctuation propagated backward or forward was neglected, which will be analyzed in detail in this work by the method of transfer function and its H∞ norm from the viewpoint of control theory. Then, through comparing the conditions of combined and partial string stabilities, their relationships can make traffic flow be divided into three distinguishable regions, displaying various combined and partial string stability performance. Finally, the numerical experiments verify the theoretical results and find that the final displaying string stability or instability performance results from the accumulated and offset effects of traffic fluctuations propagated from different directions.展开更多
This paper presents a robust estimation procedure by using modal regression for the partial functional linear regression,which combines the common linear model with the functional linear regression model.The outstandi...This paper presents a robust estimation procedure by using modal regression for the partial functional linear regression,which combines the common linear model with the functional linear regression model.The outstanding merit of the new method is that it is robust against outliers or heavy-tail error distributions while performs no worse than the least-square-based estimation method for normal error cases.The slope function is fitted by B-spline.Under suitable conditions,the authors obtain the convergence rates and asymptotic normality of the estimators.Finally,simulation studies and a real data example are conducted to examine the finite sample performance of the proposed method.Both the simulation results and the real data analysis confirm that the newly proposed method works very well.展开更多
We propose a new functional single index model, which called dynamic single-index model for functional data, or DSIM, to efficiently perform non-linear and dynamic relationships between functional predictor and functi...We propose a new functional single index model, which called dynamic single-index model for functional data, or DSIM, to efficiently perform non-linear and dynamic relationships between functional predictor and functional response. The proposed model naturally allows for some curvature not captured by the ordinary functional linear model. By using the proposed two-step estimating algorithm, we develop the estimates for both the link function and the regression coefficient function, and then provide predictions of new response trajectories. Besides the asymptotic properties for the estimates of the unknown functions, we also establish the consistency of the predictions of new response trajectories under mild conditions. Finally, we show through extensive simulation studies and a real data example that the proposed DSIM can highly outperform existed functional regression methods in most settings.展开更多
This paper considers partial function linear models of the form Y =∫X(t)β(t)dt + g(T)with Y measured with error. The authors propose an estimation procedure when the basis functions are data driven, such as with fun...This paper considers partial function linear models of the form Y =∫X(t)β(t)dt + g(T)with Y measured with error. The authors propose an estimation procedure when the basis functions are data driven, such as with functional principal components. Estimators of β(t) and g(t) with the primary data and validation data are presented and some asymptotic results are given. Finite sample properties are investigated through some simulation study and a real data application.展开更多
It is shown theoretically that the viscoelasticity of polymer melts is determined by three combining factorst they are the primary molecular weight and its distribution, the number of entanglement sites on polymer cha...It is shown theoretically that the viscoelasticity of polymer melts is determined by three combining factorst they are the primary molecular weight and its distribution, the number of entanglement sites on polymer chain and the sequence distribution of constituent chains in entanglement spacings. A unified quantity for the three combing factors is the average constrained dimensional number of constituent chains in the long entanglement spacings (v). A new relation of v to the primary molecular weight and the number of testing polymers were derived from the multiple entanglement and reptation model, and a new method for determining v was proposed. The dependences of linear viscoelastic functions on the primary molecular weight and its distribution were derived by the statistical method. When Mn=6Me to 18 Me, the values of (v) can range from 3.33 to 3.70. Their values are in a good agreement with the experiment data, and it can slightjy vary with the different species of polymers and the different ranges of molecular weight of polymers展开更多
We propose a dynamically integrated regression model to predict the price of online auctions,including the final price.Different from existing models,the proposed method uses not only the historical price but also the...We propose a dynamically integrated regression model to predict the price of online auctions,including the final price.Different from existing models,the proposed method uses not only the historical price but also the information from bidding time.Consequently,the prediction accuracy is improved compared with the existing methods.An estimation method based on B-spline approximation is proposed for the estimation and the inference of parameters and nonparametric functions in this model.The minimax rate of convergence for the prediction risk and large-sample results including the consistency and the asymptotic normality are established.Simulation studies verify the finite sample performance and the appealing prediction accuracy and robustness.Finally,when we apply our method to a 7-day auction of iPhone 6s during December 2015 and March 2016,the proposed method predicts the ending price with a much smaller error than the existing models.展开更多
基金supported by National Nature Science Foundation of China(No.11861074,No.11371354 and N0.11301464)Key Laboratory of Random Complex Structures and Data Science,Chinese Academy of Sciences,Beijing 100190,China(No.2008DP173182)Applied Basic Research Project of Yunnan Province(No.2019FB138).
文摘As an extension of linear regression in functional data analysis, functional linear regression has been studied by many researchers and applied in various fields. However, in many cases, data is collected sequentially over time, for example the financial series, so it is necessary to consider the autocorrelated structure of errors in functional regression background. To this end, this paper considers a multiple functional linear model with autoregressive errors. Based on the functional principal component analysis, we apply the least square procedure to estimate the functional coefficients and autoregression coefficients. Under some regular conditions, we establish the asymptotic properties of the proposed estimators. A simulation study is conducted to investigate the finite sample performance of our estimators. A real example on China's weather data is applied to illustrate the validity of our model.
基金supported by the General Project of National Natural Science Foundation of China(Grant No.12071416).
文摘Assessing the influence of individual observations of the functional linear models is important and challenging,especially when the observations are subject to missingness.In this paper,we introduce three case-deletion diagnostic measures to identify influential observations in functional linear models when the covariate is functional and observations on the scalar response are subject to nonignorable missingness.The nonignorable missing data mechanism is modeled via an exponential tilting semiparametric functional model.A semiparametric imputation procedure is developed to mitigate the effects of missing data.Valid estimations of the functional coefficients are based on functional principal components analysis using the imputed dataset.A smoothed bootstrap samplingmethod is introduced to estimate the diagnostic probability for each proposed diagnostic measure,which is helpful to unveil which observations have the larger influence on estimation and prediction.Simulation studies and a real data example are conducted to illustrate the finite performance of the proposed methods.
基金supported by National Natural Science Foundation of China(Grant Nos.71420107025,11071022,11231010 and 11471223)the Innovation Foundation of Beijing University of Aeronautics and Astronautics for Ph.D.graduates(Grant No.YWF-14-YJSY-027)+2 种基金the National High Technology Research and Development Program of China(863 Program)(Grant No.SS2014AA012303)Beijing Center for Mathematics and Information Interdisciplinary Sciences,Key Project of Beijing Municipal Educational Commission(Grant No.KZ201410028030)Youth Doctor Development Funding Project for"121"Human Resources of Central University of Finance and Economics(Grant No.QBJ1423)
文摘We propose sieve M-estimator for a semi-functional linear model in which the scalar response is explained by a linear operator of functional predictor and smooth functions of some real-valued random variables.Spline estimators of the functional coefficient and the smooth functions are considered,and by selecting appropriate knot numbers the optimal convergence rate and the asymptotic normality can be obtained under some mild conditions.Some simulation results and a real data example are presented to illustrate the performance of our estimation method.
文摘Emerging integrative analysis of genomic and anatomical imaging data which has not been well developed, provides invaluable information for the holistic discovery of the genomic structure of disease and has the potential to open a new avenue for discovering novel disease susceptibility genes which cannot be identified if they are analyzed separately. A key issue to the success of imaging and genomic data analysis is how to reduce their dimensions. Most previous methods for imaging information extraction and RNA-seq data reduction do not explore imaging spatial information and often ignore gene expression variation at the genomic positional level. To overcome these limitations, we extend functional principle component analysis from one dimension to two dimensions （2DFPCA） for representing imaging data and develop a multiple functional linear model （MFLM） in which functional principal scores of images are taken as multiple quantitative traits and RNA-seq profile across a gene is taken as a function predictor for assessing the association of gene expression with images. The developed method has been applied to image and RNA- seq data of ovarian cancer and kidney renal clear cell carcinoma （KIRC） studies. We identified 24 and 84 genes whose expressions were associated with imaging variations in ovarian cancer and KIRC studies, respectively. Our results showed that many significantly associated genes with images were not differentially expressed, but revealed their morphological and metabolic functions. The results also demonstrated that the peaks of the estimated regression coefficient function in the MFLM often allowed the discovery of splicing sites and multiple isoforms of gene expressions.
基金supported by the National Natural Science Foundation of China(No.12271370)。
文摘For the functional partially linear models including flexible nonparametric part and functional linear part,the estimators of the nonlinear function and the slope function have been studied in existing literature.How to test the correlation between response and explanatory variables,however,still seems to be missing.Therefore,a test procedure for testing the linearity in the functional partially linear models will be proposed in this paper.A test statistic is constructed based on the existing estimators of the nonlinear and the slope functions.Further,we prove that the approximately asymptotic distribution of the proposed statistic is a chi-squared distribution under some regularity conditions.Finally,some simulation studies and a real data application are presented to demonstrate the performance of the proposed test statistic.
基金Projects(51108465,71371192)supported by the National Natural Science Foundation of ChinaProject(2014M552165)supported by China Postdoctoral Science FoundationProject(20113187851460)supported by Technology Project of the Ministry of Transport of China
文摘The class of bi-directional optimal velocity models can describe the bi-directional looking effect that usually exists in the reality and is even enhanced with the development of the connected vehicle technologies. Its combined string stability condition can be obtained through the method of the ring-road based string stability analysis. However, the partial string stability about traffic fluctuation propagated backward or forward was neglected, which will be analyzed in detail in this work by the method of transfer function and its H∞ norm from the viewpoint of control theory. Then, through comparing the conditions of combined and partial string stabilities, their relationships can make traffic flow be divided into three distinguishable regions, displaying various combined and partial string stability performance. Finally, the numerical experiments verify the theoretical results and find that the final displaying string stability or instability performance results from the accumulated and offset effects of traffic fluctuations propagated from different directions.
基金supported by the National Natural Science Foundation of China under Grant Nos.11671096,11690013,11731011。
文摘This paper presents a robust estimation procedure by using modal regression for the partial functional linear regression,which combines the common linear model with the functional linear regression model.The outstanding merit of the new method is that it is robust against outliers or heavy-tail error distributions while performs no worse than the least-square-based estimation method for normal error cases.The slope function is fitted by B-spline.Under suitable conditions,the authors obtain the convergence rates and asymptotic normality of the estimators.Finally,simulation studies and a real data example are conducted to examine the finite sample performance of the proposed method.Both the simulation results and the real data analysis confirm that the newly proposed method works very well.
基金supported by National Natural Science Foundation of China (Grant No. 11271080)
文摘We propose a new functional single index model, which called dynamic single-index model for functional data, or DSIM, to efficiently perform non-linear and dynamic relationships between functional predictor and functional response. The proposed model naturally allows for some curvature not captured by the ordinary functional linear model. By using the proposed two-step estimating algorithm, we develop the estimates for both the link function and the regression coefficient function, and then provide predictions of new response trajectories. Besides the asymptotic properties for the estimates of the unknown functions, we also establish the consistency of the predictions of new response trajectories under mild conditions. Finally, we show through extensive simulation studies and a real data example that the proposed DSIM can highly outperform existed functional regression methods in most settings.
基金supported by the National Natural Science Foundation of China under Grant Nos.11561006 and 11471127Master Foundation of Guangxi University of Technology under Grant No.070235+2 种基金Doctoral Foundation of Guangxi University of Science and Technology under Grant No.14Z07Research Projects of Colleges and Universities in Guangxi under Grant No.KY2015YB171the Open Fund Project of Guangxi Colleges and Universities Key Laboratory of Mathematics and Statistical Model under Grant No.2016GXKLMS005
文摘This paper considers partial function linear models of the form Y =∫X(t)β(t)dt + g(T)with Y measured with error. The authors propose an estimation procedure when the basis functions are data driven, such as with functional principal components. Estimators of β(t) and g(t) with the primary data and validation data are presented and some asymptotic results are given. Finite sample properties are investigated through some simulation study and a real data application.
文摘It is shown theoretically that the viscoelasticity of polymer melts is determined by three combining factorst they are the primary molecular weight and its distribution, the number of entanglement sites on polymer chain and the sequence distribution of constituent chains in entanglement spacings. A unified quantity for the three combing factors is the average constrained dimensional number of constituent chains in the long entanglement spacings (v). A new relation of v to the primary molecular weight and the number of testing polymers were derived from the multiple entanglement and reptation model, and a new method for determining v was proposed. The dependences of linear viscoelastic functions on the primary molecular weight and its distribution were derived by the statistical method. When Mn=6Me to 18 Me, the values of (v) can range from 3.33 to 3.70. Their values are in a good agreement with the experiment data, and it can slightjy vary with the different species of polymers and the different ranges of molecular weight of polymers
基金supported by National Natural Science Foundation of China(Grant Nos.11528102 and 11571282)Fundamental Research Funds for the Central Universities of China(Grant Nos.JBK120509 and 14TD0046)supported by the National Science Foundation of USA(Grant No.DMS-1620898)。
文摘We propose a dynamically integrated regression model to predict the price of online auctions,including the final price.Different from existing models,the proposed method uses not only the historical price but also the information from bidding time.Consequently,the prediction accuracy is improved compared with the existing methods.An estimation method based on B-spline approximation is proposed for the estimation and the inference of parameters and nonparametric functions in this model.The minimax rate of convergence for the prediction risk and large-sample results including the consistency and the asymptotic normality are established.Simulation studies verify the finite sample performance and the appealing prediction accuracy and robustness.Finally,when we apply our method to a 7-day auction of iPhone 6s during December 2015 and March 2016,the proposed method predicts the ending price with a much smaller error than the existing models.
