http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Bayesian model selection for generalized linear models using non-local priors
Shi, Guiling,Lim, Chae Young,Maiti, Tapabrata Elsevier 2019 Computational statistics & data analysis Vol.133 No.-
<P><B>Abstract</B></P> <P>Variable selection is currently an important research topic under both frequentist and Bayesian framework. While most developments in Bayesian model selection literature are based on a local prior on regression parameters, a nonlocal prior for model selection can be also used. In this article, we extend nonlocal prior approach to logistic regression and to generalized linear models. Laplace approximation is used in implementation to avoid integration in the likelihood. A convergence rate is derived under some regularity conditions. The selection based on a nonlocal prior eliminates unnecessary variables and recommends a simple model. The method is validated by simulation study and illustrated by a real data example.</P>
Model selection using mass-nonlocal prior
Shi, Guiling,Lim, Chae Young,Maiti, Tapabrata Elsevier 2019 STATISTICS & PROBABILITY LETTERS - Vol.147 No.-
<P><B>Abstract</B></P> <P>Bayesian variable selection is an active research area. The paper proposes a variable selection technique by taking advantages of two distinctive approaches of Bayesian variable selection, namely spike and slab prior and nonlocal prior. Contrary to the local priors, nonlocal priors put zero mass at null values of the parameters. The proposed method uses posterior median as the parameter estimates and asymptotic consistency is established. The Bayesian implementation is proposed via Gibbs sampling. The full conditional distributions are provided. Extensive numerical study indicates superiority of the proposed procedure compared to its competitors. Most importantly, the procedure works well in low signal situation which is not the case in general.</P>
( Ruo Peng Cai ),( Yan Long Jiang ),( Wei Yang ),( Wen Tao Yang ),( Shao Hua Shi ),( Chun Wei Shi ),( Jing Tao Hu ),( Wei Gu ),( Li Ping Ye ),( Fang Yu Zhou ),( Qing Long Gong ),( Wen Yu Han ),( Guil 한국미생물 · 생명공학회 2016 Journal of microbiology and biotechnology Vol.26 No.2
Recently, poly-γ-glutamic acid synthetase A (pgsA) has been applied to display exogenous proteins on the surface of Lactobacillus casei or Lactococcus lactis, which results in a surfacedisplayed component of bacteria. However, the ability of carrying genes encoded by plasmids and the expression efficiency of recombinant bacteria can be somewhat affected by the longer gene length of pgsA (1,143 bp); therefore, a truncated gene, pgsA, was generated based on the characteristics of pgsA by computational analysis. Using murine IL-10 as an exogenous gene, recombinant Lactobacillus plantarum was constructed and the capacity of the surface-displayed protein and functional differences between exogenous proteins expressed by these strains were evaluated. Surface expression of IL-10 on both recombinant bacteria with anchorins and the higher expression levels in L. plantarum-pgsA’-IL-10 were confirmed by western blot assay. Most importantly, up-regulation of IL-1β, IL-6, TNF-α, IFN-γ, and the nuclear transcription factor NF-κB p65 in RAW264.7 cells after stimulation with Poly(I:C) or LPS was exacerbated after co-culture with L. plantarum-pgsA. By contrast, IL-10 expressed by these recombinant strains could reduce these factors, and the expression of these factors was associated with recombinant strains that expressed anchorin (especially in L. plantarum-pgsA’-IL-10) and was significantly lower compared with the anchorin-free strains. These findings indicated that exogenous proteins could be successfully displayed on the surface of L. plantarum by pgsA or pgsA’, and the expression of recombinant bacteria with pgsA’ was superior compared with bacteria with pgsA.