Objective： To summarize the experience of management for primary retroperitoneal tumor （PRPT） and to analyze the factors influencing the outcome after operation. Methods： The data of 600 cases of PRPT in General H...Objective： To summarize the experience of management for primary retroperitoneal tumor （PRPT） and to analyze the factors influencing the outcome after operation. Methods： The data of 600 cases of PRPT in General Hospital of PLA were reviewed retrospectively. Results： Of 600 cases of PRPT, 546 were surgically treated. Among theme 369 were malignant and 177 benign. 366 cases were followed up for 1 month to 15 years. The 1-years 3-year, and 5-year survival rate in the patients subject to complete resection was 90.5%, 73.2% and 53.6%, respectively, and that in incomplete resection patients was 70.6%, 32.0%, 5.7% respectively （P〈0.01）. The Cox multi-various regression analysis revealed showed completeness of tumor resection, sex and histologic type were associated closely with local recurrence. Conclusion： Sufficient preoperative preparation and complete tumor resection play important roles for reducing recurrence and improving survival.展开更多
Variable selection is one of the most fundamental problems in regression analysis. By sampling from the posterior distributions of candidate models, Bayesian variable selection via MCMC （Markov chain Monte-Carlo） is...Variable selection is one of the most fundamental problems in regression analysis. By sampling from the posterior distributions of candidate models, Bayesian variable selection via MCMC （Markov chain Monte-Carlo） is effective to overcome the computational burden of all-subset variable selection approaches. However, the convergence of the MCMC is often hard to determine and one is often not sure about if obtained samples are unbiased. This complication has limited the application of Bayesian variable selection in practice. Based on the idea of CFTP （coupling from the past）, perfect sampling schemes have been developed to obtain independent samples from the posterior distribution for a variety of problems. Here the authors propose an efficient and effective perfect sampling algorithm for Bayesian variable selection of linear regression models, which independently and identically sample from the posterior distribution of the model space and can efficiently handle thousands of variables. The effectiveness of the authors＇ algorithm is illustrated by three simulation studies, which have up to thousands of variables, the authors＇ method is further illustrated in SNPs （single nucleotide polymorphisms） association study among RA （rheumatoid arthritis） patients.展开更多
This paper proposes an objective Bayesian method to study the degradation model with respect to a Wiener process.The Jeffreys prior and reference prior for the parameters are derived,and the propriety of the posterior...This paper proposes an objective Bayesian method to study the degradation model with respect to a Wiener process.The Jeffreys prior and reference prior for the parameters are derived,and the propriety of the posteriors under these priors is validated.Two sampling algorithms are introduced to compute the posteriors.A simulation study is conducted to investigate the performance of the objective Bayesian procedure.Finally,the authors apply the approach to a degradation data.展开更多
Phylogenetic and phylogeographic studies rely on the accurate quantification of biodiversity. In recent studies of taxonomically ambiguous groups, species boundaries are often determined based on multi-locus sequence ...Phylogenetic and phylogeographic studies rely on the accurate quantification of biodiversity. In recent studies of taxonomically ambiguous groups, species boundaries are often determined based on multi-locus sequence data. Bayesian Phylogenetics and Phylogeography （BPP） is a coalescent-based method frequently used to delimit species; however, empirical studies suggest that the requirement of a user-specified guide tree biases the range of possible outcomes. We evaluate fifteen multi-locus datasets using the most recent iteration of BPP, which eliminates the need for a user-specified guide tree and reconstructs the species tree in synchrony with species delimitation （= unguided species delimitation）. We found that the number of species recovered with guided versus unguided species delimitation was the same except for two cases, and that posterior probabilities were generally lower for the unguided analyses as a result of searching across species trees in addition to species delimitation models. The guide trees used in previous studies were often discordant with the species tree topologies estimated by BPP. We also compared species trees estimated using BPP and ＊BEAST and found that when the topologies are the same, BPP tends to give higher posterior probabilities [Current Zoology 61 （5）： 866-873, 2015].展开更多
The authors first prove a convergence result on the Ka(?)anov method for solving generalnonlinear variational inequalities of the second kind and then apply the Kacanov method tosolve a nonlinear variational inequalit...The authors first prove a convergence result on the Ka(?)anov method for solving generalnonlinear variational inequalities of the second kind and then apply the Kacanov method tosolve a nonlinear variational inequality of the second kind arising in elastoplasticity. In additionto the convergence result, an a posteriori error estimate is shown for the Kacanov iterates. Ineach step of the Ka(?)anov iteration, one has a (linear) variational inequality of the secondkind, which can be solved by using a regularization technique. The Ka(?)anov iteration andthe regularization technique together provide approximations which can be readily computednumerically. An a posteriori error estimate is derived for the combined effect of the Ka(?)anoviteration and the regularization.展开更多
文摘Objective： To summarize the experience of management for primary retroperitoneal tumor （PRPT） and to analyze the factors influencing the outcome after operation. Methods： The data of 600 cases of PRPT in General Hospital of PLA were reviewed retrospectively. Results： Of 600 cases of PRPT, 546 were surgically treated. Among theme 369 were malignant and 177 benign. 366 cases were followed up for 1 month to 15 years. The 1-years 3-year, and 5-year survival rate in the patients subject to complete resection was 90.5%, 73.2% and 53.6%, respectively, and that in incomplete resection patients was 70.6%, 32.0%, 5.7% respectively （P〈0.01）. The Cox multi-various regression analysis revealed showed completeness of tumor resection, sex and histologic type were associated closely with local recurrence. Conclusion： Sufficient preoperative preparation and complete tumor resection play important roles for reducing recurrence and improving survival.
文摘Variable selection is one of the most fundamental problems in regression analysis. By sampling from the posterior distributions of candidate models, Bayesian variable selection via MCMC （Markov chain Monte-Carlo） is effective to overcome the computational burden of all-subset variable selection approaches. However, the convergence of the MCMC is often hard to determine and one is often not sure about if obtained samples are unbiased. This complication has limited the application of Bayesian variable selection in practice. Based on the idea of CFTP （coupling from the past）, perfect sampling schemes have been developed to obtain independent samples from the posterior distribution for a variety of problems. Here the authors propose an efficient and effective perfect sampling algorithm for Bayesian variable selection of linear regression models, which independently and identically sample from the posterior distribution of the model space and can efficiently handle thousands of variables. The effectiveness of the authors＇ algorithm is illustrated by three simulation studies, which have up to thousands of variables, the authors＇ method is further illustrated in SNPs （single nucleotide polymorphisms） association study among RA （rheumatoid arthritis） patients.
基金supported by the National Natural Science Foundation of China under Grant Nos.11201005,11526070 and 11601008the Project of National Bureau of Statistics under Grant No.2013LZ17+1 种基金the Project of Anhui Educational Committee under Grant No.gxfx ZD2016015the Natural Science Foundation of Anhui Province under Grant No.1408085MA07
文摘This paper proposes an objective Bayesian method to study the degradation model with respect to a Wiener process.The Jeffreys prior and reference prior for the parameters are derived,and the propriety of the posteriors under these priors is validated.Two sampling algorithms are introduced to compute the posteriors.A simulation study is conducted to investigate the performance of the objective Bayesian procedure.Finally,the authors apply the approach to a degradation data.
基金We thank the authors of species delimitation studies listed in Table 1 for permission to use their datasets in our study. We also thank J. Grummer for providing feedback on an earlier draft of the manuscript. This work was facilitated though the use of advanced computational, storage, and networking infrastructure provided by the Hyak supercomputer system at the University of Washington. I.W.C.S. was supported by a graduate scholarship from the Consejo Nacional de Ciencia y Tecnologia （CONACYT）, and N.M.B was supported by the National Science Foundation Graduate Research Fellowship （NSF-GRFP）.
文摘Phylogenetic and phylogeographic studies rely on the accurate quantification of biodiversity. In recent studies of taxonomically ambiguous groups, species boundaries are often determined based on multi-locus sequence data. Bayesian Phylogenetics and Phylogeography （BPP） is a coalescent-based method frequently used to delimit species; however, empirical studies suggest that the requirement of a user-specified guide tree biases the range of possible outcomes. We evaluate fifteen multi-locus datasets using the most recent iteration of BPP, which eliminates the need for a user-specified guide tree and reconstructs the species tree in synchrony with species delimitation （= unguided species delimitation）. We found that the number of species recovered with guided versus unguided species delimitation was the same except for two cases, and that posterior probabilities were generally lower for the unguided analyses as a result of searching across species trees in addition to species delimitation models. The guide trees used in previous studies were often discordant with the species tree topologies estimated by BPP. We also compared species trees estimated using BPP and ＊BEAST and found that when the topologies are the same, BPP tends to give higher posterior probabilities [Current Zoology 61 （5）： 866-873, 2015].
基金Project supported by the ONR grant N00014-90-J-1238
文摘The authors first prove a convergence result on the Ka(?)anov method for solving generalnonlinear variational inequalities of the second kind and then apply the Kacanov method tosolve a nonlinear variational inequality of the second kind arising in elastoplasticity. In additionto the convergence result, an a posteriori error estimate is shown for the Kacanov iterates. Ineach step of the Ka(?)anov iteration, one has a (linear) variational inequality of the secondkind, which can be solved by using a regularization technique. The Ka(?)anov iteration andthe regularization technique together provide approximations which can be readily computednumerically. An a posteriori error estimate is derived for the combined effect of the Ka(?)anoviteration and the regularization.
