mt.maxT(multtest)
mt.maxT()所属R语言包：multtest
Step-down maxT and minP multiple testing procedures
降压maxT和minP多个测试程序
译者：生物统计家园网 机器人LoveR
描述----------Description----------
These functions compute permutation adjusted p-values for step-down multiple testing procedures described in Westfall & Young (1993).
这些函数计算排列调整p荒野及青年（1993年）中描述的降压多个测试程序值。
用法----------Usage----------
mt.maxT(X,classlabel,test="t",side="abs",fixed.seed.sampling="y",B=10000,na=.mt.naNUM,nonpara="n")
mt.minP(X,classlabel,test="t",side="abs",fixed.seed.sampling="y",B=10000,na=.mt.naNUM,nonpara="n")
参数----------Arguments----------
参数：X
A data frame or matrix, with m rows corresponding to variables (hypotheses) and n columns to observations. In the case of gene expression data, rows correspond to genes and columns to mRNA samples. The data can be read using read.table.
一个数据框或矩阵，m行相应的变量（假设）和n列观察。在基因表达数据的情况下，行对应mRNA样品的基因和列。可以读取数据，使用read.table。
参数：classlabel
A vector of integers corresponding to observation (column) class labels. For k classes, the labels must be integers between 0 and k-1. For the blockf test option, observations may be divided into n/k blocks of k observations each. The observations are ordered by block, and within each block, they are labeled using the integers 0 to k-1.
观察（列）类的标签对应的整数向量。对于k类，标签必须是0k-1之间的整数。 blockf测试选项，观测n/kk观察每块可分为。的意见，下令块，每块内，他们都使用整数0k-1标记。
参数：test
A character string specifying the statistic to be used to test the null hypothesis of no association between the variables and the class labels.<br> If test="t", the tests are based on two-sample Welch t-statistics (unequal variances). <br> If test="t.equalvar", the tests are based on two-sample t-statistics with equal variance for the two samples. The square of the t-statistic is equal to an F-statistic for k=2. <br> If test="wilcoxon", the tests are based on standardized rank sum Wilcoxon statistics.<br> If test="f", the tests are based on F-statistics.<br> If test="pairt", the tests are based on paired t-statistics. The square of the paired t-statistic is equal to a block F-statistic for k=2. <br> If test="blockf", the tests are based on F-statistics which adjust for block differences (cf. two-way analysis of variance).
如果一个字符串指定的统计，被用来测试空假设之间没有关联的变量和类的标签。参考test="t"，测试是基于两样本韦尔奇t-统计（不平等的差异）。 <br>如果test="t.equalvar"，测试是基于两样本t-统计量等于两个样本方差。 t-统计量的平方等于k=2F-统计。参考如果test="wilcoxon"，测试标准化秩秩统计基础。参考如果test="f"，测试F-统计基础。参考如果test="pairt"测试配对t-统计的基础上。配对的t-统计的平方等于块k=2F-统计。 <br>如果test="blockf"，测试是根据F-统计调整块的差异（参见双向方差分析）。
参数：side
A character string specifying the type of rejection region.<br> If side="abs", two-tailed tests, the null hypothesis is rejected for large absolute values of the test statistic.<br> If side="upper", one-tailed tests, the null hypothesis is rejected for large values of the test statistic.<br> If side="lower", one-tailed tests, the null hypothesis is rejected for small values of the test statistic.
如果一个字符串指定排斥区域类型。参考如果side="abs"，一个side="upper"，双尾检验，检验统计量的大绝对值拒绝零假设。参考尾检验，零假设被拒绝的检验统计量的大值。如果side="lower"，单尾测试参考，拒绝零假设检验统计量的小值。
参数：fixed.seed.sampling
If fixed.seed.sampling="y", a fixed seed sampling procedure is used, which may double the computing time, but will not use extra memory to store the permutations. If fixed.seed.sampling="n", permutations will be stored in memory. For the blockf test, the option n was not implemented as it requires too much memory.
fixed.seed.sampling="y"如果，一个固定的种子抽样程序使用，这可能会增加一倍的计算时间，但不会使用额外的内存来存储的排列。如果fixed.seed.sampling="n"，排列将存储在内存中。 blockf测试，选项n没有实施，因为它需要太多的内存。
参数：B
The number of permutations. For a complete enumeration, B should be 0 (zero) or any number not less than the total number of permutations.
排列数。对于一个完整的枚举，B应该是0（零）或任何数量不超过总数的排列。
参数：na
Code for missing values (the default is .mt.naNUM=--93074815.62). Entries with missing values will be ignored in the computation, i.e., test statistics will be based on a smaller sample size. This feature has not yet fully implemented.
缺失值的代码（默认为.mt.naNUM=--93074815.62）。与缺失值的参赛作品将在计算中忽略，即检验统计量将基于一个小样本大小。此功能尚未完全落实。
参数：nonpara
If nonpara="y", nonparametric test statistics are computed based on ranked data. <br> If nonpara="n", the original data are used.
如果nonpara“=”Y“，非参数检验统计排名数据计算。如果nonpara=“N”的参考，使用原始数据。
Details
详情----------Details----------
These functions compute permutation adjusted p-values for the step-down maxT and minP multiple testing procedures, which provide strong control of the family-wise Type I error rate (FWER). The adjusted p-values for the minP procedure are defined in equation (2.10) p. 66 of Westfall & Young (1993), and the maxT procedure is discussed p. 50 and 114. The permutation algorithms for estimating the adjusted p-values are given in Ge et al. (In preparation). The procedures are for the simultaneous test of m null hypotheses, namely, the null hypotheses of no association between the m variables corresponding to the rows of the data frame X and the class labels classlabel. For gene expression data, the null hypotheses correspond to no differential gene expression across mRNA samples.
这些函数计算排列调整p的降压maxT和minP的多个测试程序，它提供了强大的控制的明智的家庭类型，我的错误率（FWER）值。调整后的p为minP程序值的定义方程（2.10）P。 66荒野青年（1993年），和maxT过程进行了讨论页。 50和114。估计调整p值置换算法，给出了在锗等。 （准备中）。 m零假设，即没有关联空m变量之间的假说，相应的数据框X“类标签的行同步测试程序classlabel。对于基因表达数据，对应的零假设没有跨mRNA样品的基因差异表达。
值----------Value----------
A data frame with components
与组件的数据框
参数：index
Vector of row indices, between 1 and nrow(X), where rows are sorted first according to their adjusted p-values, next their unadjusted p-values, and finally their test statistics.
矢量行指数，介于1和nrow(X)，行进行排序，首先根据他们调整p值，明年他们未经调整的p值，最后他们的测试统计。
参数：teststat
Vector of test statistics, ordered according to index. To get the test statistics in the original data order, use teststat[order(index)].
向量测试统计，下令根据index。要获得原始数据以便在测试统计，使用teststat[order(index)]。
参数：rawp
Vector of raw (unadjusted) p-values, ordered according to index.
原料（未经调整）p的值的向量，下令根据index。
参数：adjp
Vector of adjusted p-values, ordered according to index.
调整p值的向量，下令根据index。
参数：plower
For mt.minP function only, vector of "adjusted p-values", where ties in the permutation distribution of the successive minima of raw p-values with the observed p-values are counted only once. Note that procedures based on plower do not control the FWER. Comparison of plower and adjp gives an idea of the discreteness of the permutation distribution. Values in plower are ordered according to index.
mt.minP函数，“调整p值”的向量，在原料p值连续极小的排列分布的关系与实测p值只计算一次。注意plower不的FWER控制的程序。比较plower和adjp给出了置换分布的离散性的想法。在值plower排序根据index。
作者（S）----------Author(s)----------
Yongchao Ge, <a href="mailto:yongchao.ge@mssm.edu">yongchao.ge@mssm.edu</a>, <br>
Sandrine Dudoit, <a href="http://www.stat.berkeley.edu/~sandrine">http://www.stat.berkeley.edu/~sandrine</a>.
参考文献----------References----------
multiple testing: Examples and methods for <code>p</code>-value adjustment. John Wiley \& Sons.
参见----------See Also----------
mt.plot, mt.rawp2adjp, mt.reject, mt.sample.teststat, mt.teststat, golub.
mt.plot，mt.rawp2adjp，mt.reject，mt.sample.teststat，mt.teststat，golub。
举例----------Examples----------
# Gene expression data from Golub et al. (1999)[Golub等基因表达数据。 （1999）]
# To reduce computation time and for illustrative purposes, we condider only[为了减少计算时间，并说明目的，我们只condider]
# the first 100 genes and use the default of B=10,000 permutations.[第100个基因，并使用默认的B =万排列。]
# In general, one would need a much larger number of permutations[在一般情况下，将需要一个更大的数目排列]
# for microarray data.[微阵列数据。]
data(golub)
smallgd<-golub[1:100,]
classlabel<-golub.cl
# Permutation unadjusted p-values and adjusted p-values [排列未经调整的p值和调整后的P-值]
# for maxT and minP procedures with Welch t-statistics[韦尔奇t-统计maxT和minP程序]
resT<-mt.maxT(smallgd,classlabel)
resP<-mt.minP(smallgd,classlabel)
rawp<-resT$rawp[order(resT$index)]
teststat<-resT$teststat[order(resT$index)]
# Plot results and compare to Bonferroni procedure[图的结果，并比较邦弗朗尼程序]
bonf<-mt.rawp2adjp(rawp, proc=c("Bonferroni"))
allp<-cbind(rawp, bonf$adjp[order(bonf$index),2], resT$adjp[order(resT$index)],resP$adjp[order(resP$index)])
mt.plot(allp, teststat, plottype="rvsa", proc=c("rawp","Bonferroni","maxT","minP"),leg=c(0.7,50),lty=1,col=1:4,lwd=2)
mt.plot(allp, teststat, plottype="pvsr", proc=c("rawp","Bonferroni","maxT","minP"),leg=c(60,0.2),lty=1,col=1:4,lwd=2)
mt.plot(allp, teststat, plottype="pvst", proc=c("rawp","Bonferroni","maxT","minP"),leg=c(-6,0.6),pch=16,col=1:4)
# Permutation adjusted p-values for minP procedure with F-statistics (like equal variance t-statistics)[置换调整后的P-值与F-统计过程minP（如等于方差t-统计）]
mt.minP(smallgd,classlabel,test="f",fixed.seed.sampling="n")
# Note that the test statistics used in the examples below are not appropriate [注意：在下面的例子中使用的测试统计，是不恰当的]
# for the Golub et al. data. The sole purpose of these examples is to [Golub等。数据。这些例子的唯一目的是]
# demonstrate the use of the mt.maxT and mt.minP functions.[证明使用的mt.maxT和mt.minP功能。]
# Permutation adjusted p-values for maxT procedure with paired t-statistics[置换调整后的P-值配对t-统计maxT程序]
classlabel<-rep(c(0,1),19)
mt.maxT(smallgd,classlabel,test="pairt")
# Permutation adjusted p-values for maxT procedure with block F-statistics[置换调整后的P-值maxT过程与块的F-统计]
classlabel<-rep(0:18,2)
mt.maxT(smallgd,classlabel,test="blockf",side="upper")
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 2012-2-26 07:38:37
