varbvsoptimize(varbvs)
varbvsoptimize()所属R语言包：varbvs
Coordinate ascent for variational approximation to Bayesian
协调上升的变分近似贝叶斯
译者：生物统计家园网 机器人LoveR
描述----------Description----------
varbvsoptimize implements the fully-factorized variational approximation for Bayesian variable selection in linear regression. It finds the "best" fully-factorized variational approximation to the posterior distribution of the coefficients in a linear regression model of a continuous outcome (quantitiative trait), with spike and slab priors on the coefficients. By "best", we mean the approximating distribution that locally minimizes the Kullback-Leibler divergence between the approximating distribution and the exact posterior.
varbvsoptimize实现的完全工厂化变的贝叶斯近似的线性回归变量选择。找到“最好的”完全工厂化变分近似的后验分布的连续的结果（quantitiative性状）线性回归模型中的系数，与穗板先验的系数。 “最好”，我们指的是近似的分布，局部最小化的Kullback-Leibler散度之间的近似分布和精确的后。
varbvsupdate runs a single iteration of the coordinate ascent updates to maximize the variational lower bound or, equivalently,
varbvsupdate运行的单次迭代的坐标上升更新最大化的变分下界，或等价地，
用法----------Usage----------
varbvsoptimize(X, y, sigma, sa, logodds, alpha0 = NULL,
mu0 = NULL, verbose = TRUE)
varbvsupdate(X, sigma, sa, logodds, xy, d, alpha0, mu0, Xr0, S)
参数----------Arguments----------
参数：X
Matrix of observations about the variables (or features). It has n rows and p columns, where n is the number of samples, and p is the number of variables.
矩阵观测的变量（或功能）。 n行p列，其中n的样本数，和p是变量的数目。
参数：sigma
Scalar giving the variance of the residual.
标量给残差的方差。
参数：sa
sa*sigma is the prior variance of the regression coefficients.
sa*sigma是先验方差的回归系数。
参数：logodds
Prior log-odds of inclusion for each variable. It is equal to logodds = log(q/(1-q)), where q is the prior probability that each variable is included in the linear model of Y. It may either be a scalar, in which case all the variables have the same prior inclusion probability, or it may be a vector of length p.
在此之前登录赔率包含的每个变量。这是等于logodds = log(q/(1-q))，q是先验概率，每个变量的线性模型Y的，它可以是一个标量，在这种情况下，所有的变量具有相同的前列入概率，或者它可以是一个矢量的长度p。
参数：alpha0
Initial variational estimate of posterior inclusion probabilities. It is a vector of length p. If alpha0 = NULL, the variational parameters are initialized at random.
初始变的估计后列入概率。它是一个向量的长度p。如果alpha0 = NULL，变参数的随机初始化。
参数：mu0
Initial variational estimate of posterior mean coefficients. It is a vector of length p. If mu0 = NULL, the variational parameters are randomly initialized.
首次变后平均系数的估计。它是一个向量的长度p。如果mu0 = NULL，变参数的随机初始化。
参数：y
Vector of observations about the outcome. It is a vector of length n.
矢量观测的结果。它是一个向量的长度n。
参数：verbose
Set verbose = FALSE to turn off reporting the algorithm's progress.
设置verbose = FALSE关闭算法的进展情况报告。
参数：xy
Equal to t(X) %*% y, where y is the vector of observations about the outcome.
t(X) %*% y，y是矢量观测的结果。
参数：d
Equal to diag(t(X) %*% X).
等于diag(t(X) %*% X)。
参数：Xr0
Equal to X %*% (alpha0*mu0).
等于X %*% (alpha0*mu0)。
参数：S
Order in which the coordinates are updated. It is a vector of any length. Each entry of S must be an integer between 1 and p.
顺序的坐标被更新。它是一个任意长度的向量。每个条目S必须是1之间的整数和p。
Details
详细信息----------Details----------
alpha, mu and s are the parameters of the variational approximation and, equivalently, variational estimates of posterior quantites: under the variational approximation, the ith regression coefficient is normal with probability alpha[i]; mu[i] and s[i] are the mean and variance of the coefficient given that it is included in the model. alpha, mu and s are always column vectors of length p.
alpha，mu和s的变分近似的参数，并等价，变分后分位数的估计：变分近似下，第i个回归系数的概率是正常<X >alpha[i]和mu[i]是，它是包含在模型中的系数的均值和方差。 s[i]，alpha和mu总是列向量的长度s。
To account for an intercept, y and X must be centered beforehand so that y and each column of X has a mean of zero.
占为拦截，y和X必须围绕事先y和X每列有一个均值为零。
The computational complexity of running varbvsupdate is O(n*length(S)). For efficient computation, most of the work is done by varbvsupdateR, a function implemented in C. The call to the C function in the shared library is made using .C.
计算复杂度的运行varbvsupdate是O(n*length(S))。为了有效地进行计算，大部分的工作是由varbvsupdateR，用C实现的功能，在共享库中的C函数的调用是使用.C。
值----------Value----------
varbvsoptimize returns a list containing four components: variational parameters alpha, mu and s, and the variational estimate of the marginal log-likelihood lnZ.
varbvsoptimize返回一个列表，其中包含四个组成部分：变参数alpha，mu和s，和变估计的边际对数似然lnZ。
varbvsupdate returns a list containing three components: the updated variational parameters alpha and mu, and the
varbvsupdate返回一个列表，其中包含三个组成部分：更新的变参数alpha和mu，和
（作者）----------Author(s)----------
Peter Carbonetto
参见----------See Also----------
varsimbvs
varsimbvs
实例----------Examples----------
## Randomly generate genotypes and quantitative trait measurements for[＃随机生成基因型和数量性状的测量]
## 1000 SNPs and 500 individuals, in which the variance of the residual[＃1000 SNPs和500个个体，其中所述的残余方差]
## error is 4. Of these SNPs, 10 have nonzero additive effects on the[＃误差为4。这些SNPs中，有非零的加性效应]
## trait.[＃特征。]
se <- 4
snps <- create.snps(1000,10)
data <- create.data(snps$maf,snps$beta,se,500)
## Compute the variational approximation given (appropriate) choices for[＃变分近似计算（适当的）选择]
## the hyperparameters.[＃的超。]
result <- varbvsoptimize(data$X,data$y,4,1/4,log(0.01/0.99))
## View the posterior inclusion probabilities for the (true) causal SNPs.[＃查看后入选的概率（真）因果单核苷酸多态性。]
S <- which(snps$beta != 0)
cbind(snps$beta[S],result$alpha[S])
## View the largest posterior inclusion probability for a SNP that has[＃查看最大后验的，有一个SNP包含概率]
## no effect on the quantitative trait.[＃没有影响的数量性状。]
S <- which(snps$beta == 0)
i <- S[which.max(result$alpha[S])]
cbind(snps$beta[i],result$alpha[i])
转载请注明:出自 生物统计家园网(http://www.biostatistic.net)。
注：
注1：为了方便大家学习，本文档为生物统计家园网机器人LoveR翻译而成，仅供个人R语言学习参考使用，生物统计家园保留版权。
注2：由于是机器人自动翻译，难免有不准确之处，使用时仔细对照中、英文内容进行反复理解，可以帮助R语言的学习。
注3：如遇到不准确之处，请在本贴的后面进行回帖，我们会逐渐进行修订。
|
发表于 2012-10-1 14:22:06
