impRZilr(robCompositions)
impRZilr()所属R语言包:robCompositions
EM-based replacement of rounded zeros in compositional data
EM为基础的替代成分数据的圆形零
译者:生物统计家园网 机器人LoveR
描述----------Description----------
Parametric replacement of rounded zeros for compositional data using classical and robust methods based on ilr-transformations with special choice of balances.
ILR-结余的特殊选择的转换与经典和可靠的方法,使用的成分数据四舍五入为零参数更换。
用法----------Usage----------
impRZilr(x, maxit = 10, eps = 0.1, method = "roundedZero", dl = rep(0.05, ncol(x)), bruteforce = FALSE)
参数----------Arguments----------
参数:x
data.frame or matrix
数据框或矩阵
参数:maxit
maximum number of iterations
最大迭代次数
参数:eps
convergency criteria
收敛标准
参数:method
either “roundedZeor” or “roundedZeroRobust”
“roundedZeor”或“roundedZeroRobust的”
参数:dl
Detection limit for each variable
检测限为每个变量
参数:bruteforce
sets imputed values above the detection limit to the detection limit. Replacement above the detection limit are only exeptionally occur due to numerical instabilities. The default is FALSE!
设置上面的检测限为检出限的插补值。更换以上的检出限exeptionally会出现由于数值不稳定。默认值是假的!
Details
详细信息----------Details----------
Statistical analysis of compositional data including zeros runs into problems, because log-ratios cannot be applied. Usually, rounded zeros are considerer as missing not at random missing values.
成分数据的统计分析,包括零过程中遇到问题,,因为log比例不能适用。通常情况下,圆润的零considerer不是随机的遗漏值的失踪。
The algorithm iteratively imputes parts with rounded zeros whereas in each step (1) an specific ilr transformation is applied (2) tobit regression is applied (3) the rounded zeros are replaced by the expected values (4) the corresponding inverse ilr transformation is applied. After all parts are imputed, the algorithm starts again until the imputations do not change.
该算法迭代责难具有圆形的零,而在每个步骤中的部分(1)施加一个特定的ILR变换(2)被施加Tobit回归(3)所取代的圆角零(4)对应的逆ILR变换施加的预期值。所有部件都归咎于后,该算法重新开始,直到指摘不改变。
值----------Value----------
参数:xOrig
Original data frame or matrix
原始数据框或矩阵
参数:xImp
Imputed data
估算数据
参数:wind
Index of the missing values in the data
在数据中的缺失值指数
参数:iter
Number of iterations
迭代次数。
参数:eps
eps
每股盈利
(作者)----------Author(s)----------
Matthias Templ and Peter Filzmoser
参见----------See Also----------
impRZalr
impRZalr
实例----------Examples----------
data(arcticLake)
x <- arcticLake
## generate rounded zeros artificially:[#生成圆角零人为:]
x[x[,1] < 5, 1] <- 0
x[x[,2] < 47, 2] <- 0
xia <- impRZilr(x, dl=c(5,47,9999), eps=0.05)
xia$xImp
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。
|