mst.fit(sn)
mst.fit()所属R语言包：sn
Fitting multivariate skew-t distributions
配件多变量偏斜t分布
译者：生物统计家园网 机器人LoveR
描述----------Description----------
Fits a multivariate skew-t (MST) distribution to data, or fits a linear regression model with multivariate skew-t errors, using maximum likelihood estimation. The outcome is then displayed in graphical form.
适用于多变量歪斜-T（MST）分布的数据，或符合一元线性回归模型的多变量偏斜-T的错误，用最大似然估计。然后，结果以图形的形式显示。
用法----------Usage----------
mst.fit(X, y, freq, start, fixed.df=NA, plot.it=TRUE, trace=FALSE, ...)
参数----------Arguments----------
参数：y
a matrix or a vector. If y is a matrix, its rows refer to observations, and its columns to components of the multivariate distribution. If y is a vector, it is converted to a one-column matrix, and a scalar skew-t distribution is fitted.
一个矩阵或矢量。如果y是一个矩阵，它的行是指观察，和它的列的多元分布的组件。如果y是一个矢量，它被转换到一个列的矩阵，和一个标量歪斜-t分布嵌合。
参数：X
a matrix of covariate values. If missing, a one-column matrix of 1's is created; otherwise, it must have the same number of rows of y.
矩阵的协变量值。如果缺少，矩阵中1的一列被创建，否则，它必须有相同数量的行y。
参数：freq
a vector of weights. If missing, a vector of 1's is created; otherwise it must have the same number of rows of y.
的权重的矢量。如果缺少，一个向量的1的创建，否则它必须有相同数量的行y。
参数：fixed.df
a scalar value containing the degrees of freedom (df), if these must be taken as fixed, or NA (default value) if df is a parameter to be estimated.
一个标量值，其中包含的程度的自由度（df），如果这些必须采取df是为固定的，或NA（缺省值），如果要估计参数。
参数：start
a list containing the components beta,Omega, alpha, df of the type described below. The dp component of the returned list from a previous call has the required format.
的列表中包含的组件beta，Omega，alpha，df，下面所描述的类型。 dp从以前的调用返回的列表的组成部分所需的格式。
参数：plot.it
logical value which controls the graphical output (default=TRUE); see below for description.
逻辑值，控制图形输出（默认值= TRUE），见下面的说明。
参数：trace
logical value which controls printing of the algorithm convergence. If trace=TRUE, details are printed. Default value is FALSE.
逻辑控制打印算法的收敛值。如果trace=TRUE，细节被打印出来。默认值为FALSE。
参数：...
additional parameters passed to msn.mle; in practice, the start, the algorithm and the control parameters can be passed. </table>
额外的参数传递给msn.mle，实际上，start，algorithm和control参数可以通过。 </ TABLE>
Details
详细信息----------Details----------
For computing the maximum likelihood estimates, mst.fit invokes mst.mle, while mst.fit displays the results in graphical form. See the documentation of mst.mle for details of the numerical procedure for maximum likelihood estimation.
对于计算的最大似然估计，mst.fit调用mst.mle，而mst.fit结果以图形的形式显示。最大似然估计的数值计算程序的详细信息，请参阅文档的mst.mle。
值----------Value----------
A list containing the following components:
一个列表，其中包含以下组件：
<table summary="R valueblock"> <tr valign="top"><td>call</td> <td> a string containing the calling statement. </td></tr> <tr valign="top"><td>dp</td> <td> a list containing the direct parameters beta, Omega, alpha, df. Here, beta is a matrix of regression coefficients with dim(beta)=c(nrow(X),ncol(y)), Omega is a covariance matrix of order ncol(y), alpha is a vector of shape parameters of length ncol(y), df is a positive scalar. </td></tr> <tr valign="top"><td>logL</td> <td> log-likelihood evaluated at dp. </td></tr> <tr valign="top"><td>se</td> <td> a list containing the components beta, alpha, info. Here, beta and alpha are the standard errors for the corresponding point estimates; info is the observed information matrix for the working parameter, as explained below. </td></tr> <tr valign="top"><td>algorithm</td> <td> see the documentation of mst.mle for its explanation </td></tr> <tr valign="top"><td>test.normality</td> <td> a list with elements test and p.value, which are the value of the likelihood ratio test statistic for normality (i.e. test that all components of the shape parameter are 0 and df=Inf), and the corresponding p-value. </td></tr> <tr valign="top"><td>mahalanobis</td> <td> a list of with elements distance, prob and df, which are the Mahalanobis distances of the residuals from the origin, with respect to the metric associated to the matrix Omega, and the values prob of the associated probabilities computed from the Snedecor's F distribution with degrees of freedom given by the df vector of length two, whose first component equals ncol(y) and the second component is equal to the df parameter of fitted value ST distribution unless this value has been selected by the used via fixed.df. </td></tr></table>
<table summary="R valueblock"> <tr valign="top"> <TD>call</ TD> <td>一个字符串，其中包含调用语句。 </ TD> </ TR> <tr valign="top"> <TD> dp</ TD> <td>一个列表，其中包含的直接参数beta，Omega， alpha，df。在这里，beta是一个矩阵的回归系数与dim(beta)=c(nrow(X),ncol(y))，Omega的协方差矩阵为了ncol(y)，alpha是一个矢量形状参数的长度ncol(y)，df是一个正标量。在logL</ TD> </ TR> <tr valign="top"> <TD> dp </ TD> <TD>log的可能性进行评估。 </ TD> </ TR> <tr valign="top"> <TD> se</ TD> <td>一个列表，其中包含的组件beta，alpha，info。在这里，beta和alpha的对应点的标准误差的估计;info是观察到的信息矩阵的工作参数，如下面解释。 </ TD> </ TR> <tr valign="top"> <TD>algorithm </ TD> <TD>看到的文档mst.mle其解释</ TD> </ TR > <tr valign="top"> <TD> test.normality </ TD> <td>一个列表中的元素test和p.value，它的似然比检验统计量的值为正常状态（即测试的所有组成部分的形状参数是0和df=Inf），以及相应的p值。 </ TD> </ TR> <tr valign="top"> <TD>mahalanobis </ TD> <td>一个列表中的元素distance，prob和df，它是从原点的残差的马氏距离，相对于相关联的度量矩阵Omega，probSnedecor F分布计算出的相关联的概率的值df的矢量的长度为2，其第一分量等于ncol(y)和第二组分是等于df参数的拟合值ST分布已被选中，除非此值由给定的自由程度经通过使用fixed.df。 </ TD> </ TR> </ TABLE>
副作用----------Side Effects----------
Graphical output is produced if (plot.it & missing(freq))==TRUE. Three plots are produced, and the programs pauses between each two of them, waiting for the <Enter> key to be pressed.
如果(plot.it & missing(freq))==TRUE图形输出。三幅图的生产和程序，它们两两之间的暂停，等待回车键被按下。
The first plot uses the variable y if X is missing, otherwise it uses the residuals from the regression. The form of this plot depends on the value of d=ncol(y); if d=1, an histogram is plotted with the fitted distribution superimposed. If d>1, a matrix of scatter-plots is produced, with superimposed the corresponding bivariate densities of the fitted distribution.
第一个图使用变量y如果X缺少的，否则它使用回归的残差。这个图的形式取决于d=ncol(y)，如果d=1，直方图绘制与拟合分布叠加。如果d>1，产生的散点图矩阵，与相应的二元拟合分布密度的叠加。
The second plot has two panels, each representing a QQ-plot of Mahalanobis distances. The first of these refers to the fitting of a multivariate normal distribution, a standard statistical procedure; the second panel gives the corresponding QQ-plot of suitable Mahalanobis distances for the multivariate skew-normal fit.
第二幅图有两个小组，每个代表一个QQ积马氏距离。这是指多元正态分布的拟合，标准的统计程序的第二个面板给出了相应的QQ积歪斜正常合身的多元合适的马氏距离。
The third plot is similar to the previous one, except that PP-plots are produced.
第三个图是前一个相似，不同的是PP图产生。
背景----------Background----------
The family of multivariate skew-t distributions is an extension of the multivariate Student's t family, via the introduction of a shape parameter which regulates skewness; when shape=0, the skew-t distribution reduces to the regular symmetric t-distribution. When df=Inf the distribution reduces to the multivariate skew-normal one; see dmsn. See the reference below for additional information.
多变量偏斜t分布的家庭是一个扩展的多元学生的T系列，通过引进一个shape参数调节偏度;shape=0，歪斜-t分布减少到正规的对称t分布。当df=Inf分布减少到多变量的偏移正常的;看到dmsn。下面的其他信息，请参阅参考。
注意----------Note----------
This function may be removed in future versions of the package, and (some of) its functionality transferred somewhere else
此功能可在未来版本的软件包中删除，其他地方（部分），其功能将
参考文献----------References----------
Azzalini, A. and Capitanio, A. (2003). Distributions generated by perturbation of symmetry with emphasis on a multivariate skew t distribution. J.Roy. Statist. Soc. B 65, 367–389.
参见----------See Also----------
mst.mle, msn.fit, dmst, dmsn
mst.mle，msn.fit，dmst，dmsn
实例----------Examples----------
data(ais, package="sn")
attach(ais)
# a simple-sample case[一个简单的样品的情况下，]
b <- mst.fit(y=cbind(Ht,Wt))
#[]
# a regression case:[一个回归的情况下：]
a <- mst.fit(X=cbind(1,Ht,Wt), y=bmi)
#[]
# refine the previous outcome[改进了先前的结果]
a1 <- mst.fit(X=cbind(1,Ht,Wt), y=bmi, start=a$dp)
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 11:19:32
