cvSGL(SGL)
cvSGL()所属R语言包：SGL
Fit and cross-validate a GLM with a combination of lasso and group lasso regularization
安装并验证GLM的套索，套索正规化组相结合
译者：生物统计家园网 机器人LoveR
描述----------Description----------
Fits and cross-validates a regularized generalized linear model via penalized maximum likelihood. The model is fit for a path of values of the penalty parameter, and a parameter value is chosen by cross-validation. Fits linear, logistic and Cox models.
适合和交叉验证通过惩罚最大似然正规化广义线性模型。该模型是适合的罚参数的值的路径，并选择一个参数值是由交叉验证。适用于线性，MF和Cox模型。
用法----------Usage----------
cvSGL(data, index, type = "linear", maxit = 1000, thresh = 0.001, min.frac = 0.05, nlam = 20, gamma = 0.8, nfold = 10, standardize = TRUE, verbose = FALSE, step = 1, reset = 10, alpha = 0.95, lambdas = NULL)
参数----------Arguments----------
参数：data
For type="linear" should be a list with $x$ an input matrix of dimension n-obs by p-vars, and $y$ a length $n$ response vector. For type="logit" should be a list with $x$, an input matrix, as before, and $y$ a length $n$ binary response vector. For type="cox" should be a list with x as before, time, an n-vector corresponding to failure/censor times, and status, an n-vector indicating failure (1) or censoring (0).
对于type="linear"应该是一个列表，$ X $输入矩阵的维N-OBS对增值分销商，和$ Y $的长度为$ n $响应向量。对于type="logit"应该是一个列表$ X $，输入矩阵，和以前一样，和$ y $的长度$ n $的二进制响应向量。对于type="cox"应与x是一个列表，像以前一样，time，对应于故障的n矢量/检查员倍，和status，一个n矢量表示失败（1）或设限（0）。
参数：index
A p-vector indicating group membership of each covariate
一个P-矢量表示组成员的每个协
参数：type
model type: one of ("linear","logit", "cox")
（“线性”，“的罗吉特”，“考克斯”）模型类型：
参数：maxit
Maximum number of iterations to convergence
最大迭代次数收敛
参数：thresh
Convergence threshold for change in beta
收敛阈值处于测试阶段的变化
参数：min.frac
The minimum value of the penalty parameter, as a fraction of the maximum value
罚参数的最小值，作为最大值的一小部分
参数：nlam
Number of lambda to use in the regularization path
号码的lambda使用的规范化路径
参数：gamma
Fitting parameter used for tuning backtracking (between 0 and 1)
拟合参数用于调整回溯（0和1之间）
参数：nfold
Number of folds of the cross-validation loop
倍数交叉验证循环数
参数：standardize
Logical flag for variable standardization prior to fitting the model.
逻辑标志变量标准化拟合模型之前。
参数：verbose
Logical flag for whether or not step number will be output
逻辑标志是否步数，将输出
参数：step
Fitting parameter used for inital backtracking step size (between 0 and 1)
拟合参数用于>初始回溯步长（在0和1之间）
参数：reset
Fitting parameter used for taking advantage of local strong convexity in nesterov momentum (number of iterations before momentum term is reset)
拟合参数用于利用当地的强凸涅斯捷罗夫势头（迭代次数动量项是复位前）
参数：alpha
The mixing parameter. alpha = 1 is the lasso penalty.
混合参数。 alpha= 1是的套索处罚。
参数：lambdas
A user inputted sequence of lambda values for fitting. We recommend leaving this NULL and letting SGL self-select values
用户输入序列的lambda值拟合。我们建议保留这个NULL，让SGL自我选择的值
Details
详细信息----------Details----------
The function runs SGL nfold+1 times; the initial run is to find the lambda sequence, subsequent runs are used to compute the cross-validated error rate and its standard deviation.
功能运行SGLnfold+1倍的初始运行lambda序列，随后的运行中被用来计算的交叉验证错误率及其标准差。
值----------Value----------
An object with S3 class "cv.SGL"
对象与S3类"cv.SGL"
参数：lldiff
An nlam vector of cross validated negative log likelihoods (squared error loss in the linear case, along the regularization path)
nlam向量的跨验证的负对数似然（平方误差损失linear情况下，正规化路径）
参数：llSD
An nlame vector of approximate standard deviations of lldiff
nlame矢量近似标准差lldiff的
参数：lambdas
The actual list of lambda values used in the regularization path.
实际的lambda列表中使用的值的正则路径。
参数：type
Response type (linear/logic/cox)
响应类型（线性/逻辑/ COX）
参数：fit
A model fit object created by a call to SGL on the entire dataset
模型适合创建的对象通过调用SGL对整个数据集的
（作者）----------Author(s)----------
Noah Simon, Jerry Friedman, Trevor Hastie, and Rob Tibshirani<br>
Maintainer: Noah Simon <a href="mailto:nsimon@stanford.edu">nsimon@stanford.edu</a>
参考文献----------References----------
A Sparse-Group Lasso, <br> http://www-stat.stanford.edu/~nsimon/SGL.pdf
参见----------See Also----------
SGL
SGL
实例----------Examples----------
set.seed(1)
n = 50; p = 100; size.groups = 10
index <- ceiling(1:p / size.groups)
X = matrix(rnorm(n * p), ncol = p, nrow = n)
beta = (-2:2)
y = X[,1:5] %*% beta + 0.1*rnorm(n)
data = list(x = X, y = y)
cvFit = cvSGL(data, index, type = "linear")
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 2012-9-30 01:46:41
