wle.aic(wle)
wle.aic()所属R语言包：wle
Weighted Akaike Information Criterion
加权赤池信息准则
译者：生物统计家园网 机器人LoveR
描述----------Description----------
The Weighted Akaike Information Criterion.
加权赤池信息准则。
用法----------Usage----------
wle.aic(formula, data=list(), model=TRUE, x=FALSE,
y=FALSE, boot=30, group, var.full=0, num.sol=1,
raf="HD", smooth=0.031, tol=10^(-6),
equal=10^(-3), max.iter=500, min.weight=0.5,
method="full", alpha=2, contrasts=NULL, verbose=FALSE)
参数----------Arguments----------
参数：formula
a symbolic description of the model to be fit. The details of model specification are given below.
一个象征性的模型来描述是合适的。模型规范的细节在下面给出。
参数：data
an optional data frame containing the variables in the model. By default the variables are taken from the environment which wle.aic is called from.
一个可选的数据框包含在模型中的变量。默认情况下，变量是从wle.aic被称为从环境。
参数：model, x, y
logicals. If TRUE the corresponding components of the fit (the model frame, the model matrix, the response.)
的逻辑。如果TRUE拟合的相应部件（模型框架，模型矩阵，响应。）
参数：boot
the number of starting points based on boostrap subsamples to use in the search of the roots.
基于自举子样本的起点，使用在搜索的根的数目。
参数：group
the dimension of the bootstap subsamples. The default value is max(round(size/4),var) where size is the number of observations and var is the number of variables.
的维度的bootstap子样本。默认值是max(round(size/4),var)size的一些意见和var是变量的数目。
参数：var.full
the value of variance to be used in the denominator of the WAIC, if 0 the variance estimated from the full model is used.
中要使用的分母的WAIC方差的值，如果为0用于从完整的模型估计的方差。
参数：num.sol
maximum number of roots to be searched.
要搜索的最大根数。
参数：raf
type of Residual adjustment function to be use:
类型的残余调节功能，可以使用：
raf="HD": Hellinger Distance RAF,
raf="HD"：Hellinger距离RAF，
raf="NED": Negative Exponential Disparity RAF,
raf="NED"：负指数差异RAF，
raf="SCHI2": Symmetric Chi-Squared Disparity RAF.
raf="SCHI2"：对称卡方差异皇家空军。
参数：smooth
the value of the smoothing parameter.
的平滑化参数的值。
参数：tol
the absolute accuracy to be used to achieve convergence of the algorithm.
要使用的绝对精度实现算法的收敛性。
参数：equal
the absolute value for which two roots are considered the same. (This parameter must be greater than tol).
绝对的值，两个根被认为是相同的。 （此参数必须大于tol）。
参数：max.iter
maximum number of iterations.
最大迭代次数。
参数：min.weight
see details.
查看详细信息。
参数：method
see details.
查看详细信息。
参数：alpha
penalty value.
惩罚值。
参数：contrasts
an optional list. See the contrasts.arg of model.matrix.default.
可选列表。请参阅contrasts.argmodel.matrix.default。
参数：verbose
if TRUE warnings are printed.
如果TRUE警告被打印出来。
Details
详细信息----------Details----------
Models for wle.aic are specified symbolically. A typical model has the form response ~ terms where response is the (numeric) response vector and terms is a series of terms which specifies a linear predictor for response. A terms specification of the form first+second indicates all the terms in first together with all the terms in second with duplicates removed. A specification of the form first:second indicates the the set of terms obtained by taking the interactions of all terms in first with all terms in second. The specification first*second indicates the cross of first and second. This is the same as first+second+first:second.
模型wle.aic的符号。典型的模型形式response ~ terms其中response是响应向量（数字）和terms是一系列的条款，指定一个线性预测response。一个术语规范的形式first+second表示first一起在second重复删除的所有条款中的所有条款。一个规范的形式first:second的表示的术语集firstsecond的所有条款的相互作用的所有条款。规格first*second表明first和second交叉的。这是相同first+second+first:second。
min.weight: the weighted likelihood equation could have more than one solution. These roots appear for particular situation depending on contamination level and type. The presence of multiple roots in the full model can create some problem in the set of weights we should use. Actually, the selection of the root is done by the minimum scale error provided. Since this choice is not always the one would choose, we introduce the min.weight parameter in order to choose only between roots that do not down weight everything. This is not still the optimal solution, and perhaps, in the new release, this part will be change.
min.weight：加权似然方程可以有一个以上的解决方案。这些根出现特定情况下，根据污染程度和类型。组中的权重，我们应该用多根完整的模型的存在可以创造出一些问题。事实上，根的选择是通过提供最小刻度误差。由于这种选择并不总是一个选择，我们引进了min.weight参数，以便选择之间不下来的重量一切的根源。这是不是仍然是最佳的解决方案，也许，在新版本中，这部分将有所改变。
method: this parameter, when set to "reduced", allows to use weights based on the reduced model. This is strongly discourage since the robust and asymptotic property of this kind of weighted AIC are not as good as the one based on method="full".
method：此参数，当设置为“减少”，允许使用简化模型的基础上的权重。这是极力劝阻，因为这种加权AIC的鲁棒性和渐近性的基础上method="full"不如。
值----------Value----------
wle.aic returns an object of class "wle.aic".
wle.aic返回一个对象的class"wle.aic"的。
The function summary is used to obtain and print a summary of the results. The generic accessor functions coefficients and residuals extract coefficients and residuals returned by wle.aic. The object returned by wle.aic are:
函数summary用于获取和打印结果的摘要。一般的访问功能coefficients和residuals的提取系数和残差返回wle.aic。对象返回wle.aic是：
<table summary="R valueblock"> <tr valign="top"><td>waic</td> <td> Weighted Akaike Information Criterion for each submodels</td></tr> <tr valign="top"><td>coefficients</td> <td> the parameters estimator, one row vector for each root found and each submodel.</td></tr> <tr valign="top"><td>scale</td> <td> an estimation of the error scale, one value for each root found and each submodel.</td></tr> <tr valign="top"><td>residuals</td> <td> the unweighted residuals from the estimated model, one column vector for each root found and each submodel.</td></tr> <tr valign="top"><td>tot.weights</td> <td> the sum of the weights divide by the number of observations, one value for each root found and each submodel.</td></tr> <tr valign="top"><td>weights</td> <td> the weights associated to each observation, one column vector for each root found and each submodel.</td></tr> <tr valign="top"><td>freq</td> <td> the number of starting points converging to the roots.</td></tr> <tr valign="top"><td>call</td> <td> the match.call().</td></tr> <tr valign="top"><td>contrasts</td> <td> </td></tr> <tr valign="top"><td>xlevels</td> <td> </td></tr> <tr valign="top"><td>terms</td> <td> the model frame.</td></tr> <tr valign="top"><td>model</td> <td> if model=TRUE a matrix with first column the dependent variable and the remain column the explanatory variables for the full model.</td></tr> <tr valign="top"><td>x</td> <td> if x=TRUE a matrix with the explanatory variables for the full model.</td></tr> <tr valign="top"><td>y</td> <td> if y=TRUE a vector with the dependent variable.</td></tr> <tr valign="top"><td>info</td> <td> not well working yet, if 0 no error occurred.</td></tr> </table>
<table summary="R valueblock"> <tr valign="top"> <TD>waic </ TD> <TD>加权赤池信息准则对每个子模型</ TD> </ TR> <TR VALIGN =“”> <TD>coefficients </ TD> <TD>的参数估计，每一根发现，每个子模型的一个行向量。</ TD> </ TR> <TR VALIGN =“顶” > <TD> scale </ TD> <TD>的错误规模的估计，每一根和每个子模型。</ TD> </ TR> <tr valign="top"> < residuals TD> </ TD> <TD>未加权的估计模型的残差，每一根发现，每个子模型的一个列向量。</ TD> </ TR> <tr valign="top"> < TD> tot.weights </ TD> <TD>的权重总和除以观测值的数量，每一根发现的一个值，每个子模型。</ TD> </ TR> <TR VALIGN =“顶部“> <TD> weights </ TD> <TD>相关的权重给每个观察每一根发现，一个列向量，每个子模型。</ TD> </ TR> <TR VALIGN =”顶“ > <TD> freq </ TD> <TD>收敛的根源出发点的数量。</ TD> </ TR> <tr valign="top"> <TD>call </ TD> <TD> match.call（）。</ TD> </ TR> <tr valign="top"> <TD>contrasts </ TD> <TD> </ TD> < / TR> <tr valign="top"> <TD>xlevels </ TD> <TD> </ TD> </ TR> <tr valign="top"> <TD>terms <TD>的模型框架</ TD> </ TD> </ TR> <tr valign="top"> <TD> model </ TD> <TD>如果model=TRUE矩阵与第一列中的因变量和列的是整个模型的解释变量。</ TD> </ TR> <tr valign="top"> <TD> x</ TD> <td>如果如果x=TRUE的是整个模型的解释变量矩阵。</ TD> </ TR> <tr valign="top"> <TD> y</ TD> <TD> y=TRUE与因变量的向量。</ TD> </ TR> <tr valign="top"> <TD>info </ TD> <TD>以及工作尚未，如果0没有错误发生。</ TD> </ TR> </ TABLE>
（作者）----------Author(s)----------
Claudio Agostinelli
参考文献----------References----------
Agostinelli, C., (1999) Robust model selection in regression via weighted likelihood methodology, Working Paper n. 1999.4, Department of Statistics, Universiy of Padova.
Agostinelli, C., (2002) Robust model selection in regression via weighted likelihood methodology, Statistics \& Probability Letters, 56, 289-300.
Agostinelli, C., (1998) Inferenza statistica robusta basata sulla funzione di verosimiglianza pesata: alcuni sviluppi, Ph.D Thesis, Department of Statistics, University of Padova.
Agostinelli, C., Markatou, M., (1998) A one-step robust estimator for regression based on the weighted likelihood reweighting scheme, Statistics \& Probability Letters, Vol. 37, n. 4, 341-350.
Agostinelli, C., (1998) Verosimiglianza pesata nel modello di regressione lineare, XXXIX Riunione scientifica della Societa' Italiana di Statistica, Sorrento 1998.
实例----------Examples----------
library(wle)
x.data <- c(runif(60,20,80),runif(5,73,78))
e.data <- rnorm(65,0,0.6)
y.data <- 8*log(x.data+1)+e.data
y.data[61:65] <- y.data[61:65]-4
z.data <- c(rep(0,60),rep(1,5))
plot(x.data,y.data,xlab="X",ylab="Y")
xx.data <- cbind(x.data,x.data^2,x.data^3,log(x.data+1))
colnames(xx.data) <- c("X","X^2","X^3","log(X+1)")
result <- wle.aic(y.data~xx.data,boot=10,group=10,num.sol=2)
summary(result)
result <- wle.aic(y.data~xx.data+z.data,boot=10,group=10,num.sol=2)
summary(result)
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 22:38:30
