R语言 robustbase包 plot.mcd()函数中文帮助文档(中英文对照)

loveR

plot.mcd(robustbase)
plot.mcd()所属R语言包：robustbase

                                        Robust Distance Plots
                                         强大的远程图

                                         译者：生物统计家园网 机器人LoveR

描述----------Description----------

Shows the Mahalanobis distances based on robust and classical estimates of the location and the covariance matrix in different plots. The following plots are available:
显示的马氏距离，根据不同图的位置和协方差矩阵的强大的和古典的估计。下面的图是：

index plot of the robust and mahalanobis distances
指数图的鲁棒性和马氏距离

distance-distance plot
距离 - 距离图

Chisquare QQ-plot of the robust and mahalanobis distances
卡方QQ图的鲁棒性和马氏距离

plot of the tolerance ellipses (robust and classic)
图的公差椭圆形（强大的和经典的）

Scree plot - Eigenvalues comparison plot
卵石图 - 特征值比较图


用法----------Usage----------


## S3 method for class 'mcd'
plot(x,
     which = c("all", "dd", "distance", "qqchi2",
               "tolEllipsePlot", "screeplot"),
     classic = FALSE, ask = (which=="all" && dev.interactive()),
     cutoff, id.n, labels.id = rownames(x$X), cex.id = 0.75,
     label.pos = c(4,2), tol = 1e-7, ...)

covPlot(x,
     which = c("all", "dd", "distance", "qqchi2",
               "tolEllipsePlot", "screeplot"),
     classic = FALSE, ask = (which == "all" && dev.interactive()),
     m.cov = covMcd(x),
     cutoff = NULL, id.n, labels.id = rownames(x), cex.id = 0.75,
     label.pos = c(4,2), tol = 1e-07, ...)







参数----------Arguments----------

参数：x
For the plot() method, a mcd object, typically result of covMcd.<br> For covPlot(), the numeric data matrix such as the X component as returned from covMcd.
有关的plot()方法，一个mcd对象，典型结果，covMcd。<br>如需covPlot()，如X组件作为数值数据矩阵返回covMcd。


参数：which
string indicating which plot to show.  See the Details section for a description of the options.  Defaults to "all". </table>
字符串，表示的曲线图显示。请参阅“详细资料”节中描述的选项。默认为"all"的。 </ TABLE>


参数：classic
whether to plot the classical distances too. Defaults to FALSE. </table>
是否绘制古典的距离。默认为FALSE的。 </ TABLE>


参数：ask
logical indicating if the user should be asked before each plot, see par(ask=.).  Defaults to which == "all" &amp;&amp; dev.interactive().  
逻辑表示，如果用户应该要求每个小区前，看到par(ask=.)。默认为which == "all" &amp;&amp; dev.interactive()的。


参数：cutoff
the cutoff value for the distances.
的临界值的距离。


参数：id.n
number of observations to be identified by a label.  If not supplied, the number of observations with distance larger than cutoff is used.
一个标签来识别观测到的数量。如果未提供，观察距离大于cutoff的数量。


参数：labels.id
vector of labels, from which the labels for extreme points will be chosen.  NULL uses observation numbers.
向量的标签，从极值点的标签将被选择。 NULL使用观察数。


参数：cex.id
magnification of point labels.
点标签的放大倍率。


参数：label.pos
positioning of labels, for the left half and right half of the graph respectively (used as text(.., pos=*)).
定位的标签，为的左半边和右半边的曲线图分别（用作text(.., pos=*)）。


参数：tol
tolerance to be used for computing the inverse, see solve.  Defaults to tol = 1e-7.
公差要用于计算逆，请参阅solve。默认为tol = 1e-7的。


参数：m.cov
an object similar to those of class "mcd"; however only its components center and cov will be used.  If missing, the MCD will be computed (via covMcd()).
一个类的对象"mcd"，但只有它的成分center和cov使用。如果缺少，MCD将被计算（通过covMcd()）。


参数：...
other parameters to be passed through to plotting functions.
其他参数被传递到绘图功能。


Details

详细信息----------Details----------

These functions produce several plots based on the robust and classical location and covariance matrix.  Which of them to select is specified by the attribute  which.  The plot method for "mcd" objects is calling covPlot() directly, whereas covPlot() should also be useful for plotting other (robust) covariance estimates.  The possible options are:
这些功能产生强大的和古典的位置和协方差矩阵的基础上的几个图。他们选择指定的属性which。 plot"mcd"对象调用covPlot()直接，而covPlot()也应该是有用的图（强大）的协方差估计的方法。可能的选项包括：




distance index plot of the robust distances
distance指数图强劲的距离




dd distance-distance plot
dd距离 - 距离图




qqchi2 a qq-plot of the robust distances versus the
qqchi2图强劲的距离与一个QQ




tolEllipsePlot a tolerance ellipse plot, via
tolEllipsePlot一个的宽容椭圆曲线，通过




screeplot an eigenvalues comparison plot - screeplot
screeplot的特征值比较图 -  screeplot

The Distance-Distance Plot, introduced by Rousseeuw and van Zomeren (1990), displays the robust distances versus the classical Mahalanobis distances.  The dashed line is the set of points where the robust distance is equal to the classical distance. The horizontal and vertical lines are drawn at values equal to the cutoff which defaults to square root of the 97.5% quantile of a chi-squared distribution with p degrees of freedom.  Points beyond these lines can be considered outliers.
距离 - 距离图，引入Rousseeuw和：面包车Zomeren（1990年），显示强劲的距离相对于传统的马氏距离。虚线是鲁棒的距离为等于经典的距离的点的集合。水平线和垂直线绘制值等于默认为与p自由度的卡方分布的97.5％分位数的平方根截止。点超越这些线可以认为是异常值。


参考文献----------References----------

Unmasking Multivariate Outliers and Leverage Points. Journal of the American Statistical Association 85, 633&ndash;639.
A fast algorithm for the minimum covariance determinant estimator. Technometrics 41, 212&ndash;223.

参见----------See Also----------

tolEllipsePlot
tolEllipsePlot


实例----------Examples----------


data(Animals, package ="MASS")
brain <- Animals[c(1:24, 26:25, 27:28),]
mcd <- covMcd(log(brain))

plot(mcd, which = "distance", classic = TRUE)# 2 plots[2图]
plot(mcd, which = "dd")
plot(mcd, which = "tolEllipsePlot", classic = TRUE)
op <- par(mfrow = c(2,3))
plot(mcd) ## -&gt; which = "all" (5 plots)[＃ - > =“所有”（图）]
par(op)

## same plots for another robust Cov estimate:[＃相同图的另一个强大的覆盖估计：]
data(hbk)
hbk.x <- data.matrix(hbk[, 1:3])
cOGK <- covOGK(hbk.x, n.iter = 2, sigmamu = scaleTau2,
               weight.fn = hard.rejection)
covPlot(hbk.x, m.cov = cOGK, classic = TRUE)




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。