R语言 ROptEst包 getInfRobIC()函数中文帮助文档(中英文对照)

loveR

getInfRobIC(ROptEst)
getInfRobIC()所属R语言包：ROptEst

                                         Generic Function for the Computation of Optimally Robust ICs
                                         通用函数的计算最理想的强大的集成电路

                                         译者：生物统计家园网 机器人LoveR

描述----------Description----------

Generic function for the computation of optimally robust ICs  in case of infinitesimal robust models. This function is  rarely called directly.
强大的芯片的情况下的无穷可靠的模型计算最佳的通用功能。很少直接调用此函数。


用法----------Usage----------


getInfRobIC(L2deriv, risk, neighbor, ...)

## S4 method for signature 'UnivariateDistribution,asCov,ContNeighborhood'
getInfRobIC(L2deriv,
                       risk, neighbor, Finfo, trafo, verbose = NULL)

## S4 method for signature 'UnivariateDistribution,asCov,TotalVarNeighborhood'
getInfRobIC(L2deriv,
                       risk, neighbor, Finfo, trafo, verbose = NULL)

## S4 method for signature 'RealRandVariable,asCov,UncondNeighborhood'
getInfRobIC(L2deriv, risk,
                       neighbor, Distr, Finfo, trafo, QuadForm = diag(nrow(trafo)),
                       verbose = NULL)

## S4 method for signature 'UnivariateDistribution,asBias,UncondNeighborhood'
getInfRobIC(L2deriv,
                       risk, neighbor, symm, trafo, maxiter, tol, warn, Finfo,
                       verbose = NULL, ...)

## S4 method for signature 'RealRandVariable,asBias,UncondNeighborhood'
getInfRobIC(L2deriv, risk,
                       neighbor, Distr, DistrSymm, L2derivSymm,
                       L2derivDistrSymm, z.start, A.start, Finfo, trafo,
                       maxiter, tol, warn, verbose = NULL, ...)

## S4 method for signature 'UnivariateDistribution,asHampel,UncondNeighborhood'
getInfRobIC(L2deriv,
                       risk, neighbor, symm, Finfo, trafo, upper = NULL,
                       lower=NULL, maxiter, tol, warn, noLow = FALSE,
                       verbose = NULL, checkBounds = TRUE)

## S4 method for signature 'RealRandVariable,asHampel,UncondNeighborhood'
getInfRobIC(L2deriv, risk,
                       neighbor, Distr, DistrSymm, L2derivSymm,
                       L2derivDistrSymm, Finfo, trafo, onesetLM = FALSE,
                       z.start, A.start, upper = NULL, lower=NULL,
                       OptOrIter = "iterate", maxiter, tol, warn,
                       verbose = NULL, checkBounds = TRUE, ...)

## S4 method for signature 'UnivariateDistribution,asAnscombe,UncondNeighborhood'
getInfRobIC(
                       L2deriv, risk, neighbor, symm, Finfo, trafo, upper = NULL,
                       lower=NULL, maxiter, tol, warn, noLow = FALSE,
                       verbose = NULL, checkBounds = TRUE)

## S4 method for signature 'RealRandVariable,asAnscombe,UncondNeighborhood'
getInfRobIC(L2deriv,
                       risk, neighbor, Distr, DistrSymm, L2derivSymm,
                       L2derivDistrSymm, Finfo, trafo, onesetLM = FALSE,
                       z.start, A.start, upper = NULL, lower=NULL,
                       OptOrIter = "iterate", maxiter, tol, warn,
                       verbose = NULL, checkBounds = TRUE, ...)

## S4 method for signature 'UnivariateDistribution,asGRisk,UncondNeighborhood'
getInfRobIC(L2deriv,
                       risk, neighbor, symm, Finfo, trafo, upper = NULL,
                       lower = NULL, maxiter, tol, warn, noLow = FALSE,
                       verbose = NULL)

## S4 method for signature 'RealRandVariable,asGRisk,UncondNeighborhood'
getInfRobIC(L2deriv, risk,
                       neighbor,  Distr, DistrSymm, L2derivSymm,
                       L2derivDistrSymm, Finfo, trafo, onesetLM = FALSE, z.start,
                       A.start, upper = NULL, lower = NULL, OptOrIter = "iterate",
                       maxiter, tol, warn, verbose = NULL, withPICcheck = TRUE, ...)

## S4 method for signature 'UnivariateDistribution,asUnOvShoot,UncondNeighborhood'
getInfRobIC(
                       L2deriv, risk, neighbor, symm, Finfo, trafo,
                       upper, lower, maxiter, tol, warn)



参数----------Arguments----------

参数：L2deriv
L2-derivative of some L2-differentiable family  of probability measures.
L2-衍生的一些L2-微家庭的概率措施。


参数：risk
object of class "RiskType".
对象类"RiskType"。


参数：neighbor
object of class "Neighborhood".
对象类"Neighborhood"。


参数：...
additional parameters (mainly for optim).
额外的参数（主要用于optim）。


参数：Distr
object of class "Distribution".
对象类"Distribution"。


参数：symm
logical: indicating symmetry of L2deriv.
逻辑：表示对称的L2deriv。


参数：DistrSymm
object of class "DistributionSymmetry".
对象类"DistributionSymmetry"。


参数：L2derivSymm
object of class "FunSymmList".
对象类"FunSymmList"。


参数：L2derivDistrSymm
object of class "DistrSymmList".
对象类"DistrSymmList"。


参数：Finfo
Fisher information matrix.
Fisher信息矩阵。


参数：z.start
initial value for the centering constant.
定心常数的初始值。


参数：A.start
initial value for the standardizing matrix.
标准化矩阵的初始值。


参数：trafo
matrix: transformation of the parameter.
矩阵变换的参数。


参数：upper
upper bound for the optimal clipping bound.
上界的最佳剪辑约束。


参数：lower
lower bound for the optimal clipping bound.
下界的最佳剪辑约束。


参数：OptOrIter
character; which method to be used for determining Lagrange multipliers A and a: if (partially) matched to "optimize", getLagrangeMultByOptim is used; otherwise: by default, or if matched to "iterate" or to "doubleiterate", getLagrangeMultByIter is used. More specifically, when using getLagrangeMultByIter, and if argument risk is of class "asGRisk", by default and if matched to "iterate" we use only one (inner) iteration, if matched to "doubleiterate" we use up to Maxiter (inner) iterations.
方法用于确定拉格朗日乘子的性格;A和a：如果（部分）匹配"optimize"，getLagrangeMultByOptim使用，否则默认情况下，或者如果相匹配的"iterate"或"doubleiterate"，getLagrangeMultByIter使用。更具体地，使用时：getLagrangeMultByIter，如果参数risk是类"asGRisk"，缺省情况下，和如果"iterate"匹配我们只使用一个（内）迭代，如果匹配"doubleiterate"的“我们使用Maxiter（内部）迭代。


参数：maxiter
the maximum number of iterations.
最大迭代次数。


参数：tol
the desired accuracy (convergence tolerance).
所需的精度（收敛宽容）。


参数：warn
logical: print warnings.
逻辑：打印警告。


参数：noLow
logical: is lower case to be computed?
符合逻辑的：是较低的情况下，要计算？


参数：onesetLM
logical: use one set of Lagrange multipliers?
逻辑：使用一组拉格朗日乘子吗？


参数：QuadForm
matrix of (or which may coerced to) class  PosSemDefSymmMatrix for use of different  (standardizing) norm
矩阵（或强迫）类PosSemDefSymmMatrix使用不同的（标准化）标准


参数：verbose
logical: if TRUE, some messages are printed
逻辑：如果TRUE，一些消息都印


参数：checkBounds
logical: if TRUE, minimal and maximal clipping bound are  computed to check if a valid bound was specified.
逻辑：如果TRUE，最小和最大限幅约束的计算，以检查是否一个有效的结合被指定。


参数：withPICcheck
logical: at the end of the algorithm, shall we check how accurately this is a pIC; this will only be done if withPICcheck && verbose.
逻辑：在算法结束时，我们应该如何准确，这是一个PIC，这将只能做withPICcheck && verbose。


值----------Value----------

The optimally robust IC is computed.
计算最优鲁棒的IC。


方法----------Methods----------

  


L2deriv = "UnivariateDistribution", risk = "asCov",  neighbor = "ContNeighborhood"  computes the classical optimal influence curve for L2 differentiable  parametric families with unknown one-dimensional parameter.
L2deriv =的“UnivariateDistribution”风险=的“asCov”邻居=“ContNeighborhood”的计算一维参数未知的经典最优L2微参数家庭的影响曲线。




L2deriv = "UnivariateDistribution", risk = "asCov",  neighbor = "TotalVarNeighborhood" computes the classical optimal influence curve for L2 differentiable  parametric families with unknown one-dimensional parameter.
L2deriv =的“UnivariateDistribution”风险=的“asCov”邻居=“TotalVarNeighborhood”的计算一维参数未知的经典最优L2微参数家庭的影响曲线。




L2deriv = "RealRandVariable", risk = "asCov",  neighbor = "UncondNeighborhood" computes the classical optimal influence curve for L2 differentiable  parametric families with unknown k-dimensional parameter  (k > 1) where the underlying distribution is univariate; for total variation neighborhoods only is implemented for the case where there is a 1 x k transformation trafo matrix.
L2deriv =“RealRandVariable的”风险=“asCov”的，邻居=“UncondNeighborhood”计算的经典最优L2微参数家庭与未知的的k维参数（k > 1）的潜在分布的影响曲线单因素，总的变化街区实施的情况下，有一个1 x k转型trafo矩阵。




L2deriv = "UnivariateDistribution", risk = "asBias",  neighbor = "UncondNeighborhood"  computes the bias optimal influence curve for L2 differentiable  parametric families with unknown one-dimensional parameter.
L2deriv =的“UnivariateDistribution”风险=的“asBias”邻居=“UncondNeighborhood”的计算一维参数未知的偏见的最佳L2微参数家庭的影响曲线。




L2deriv = "RealRandVariable", risk = "asBias",  neighbor = "UncondNeighborhood" computes the bias optimal influence curve for L2 differentiable  parametric families with unknown k-dimensional parameter  (k > 1) where the underlying distribution is univariate.
L2deriv =“RealRandVariable的”风险=的“asBias”邻居=“UncondNeighborhood”的计算偏置最佳的影响力与未知的的k维参数（k > 1）的潜在分布曲线L2微参数家庭单变量。




L2deriv = "UnivariateDistribution", risk = "asHampel",  neighbor = "UncondNeighborhood" computes the optimally robust influence curve for L2 differentiable  parametric families with unknown one-dimensional parameter.
L2deriv =的“UnivariateDistribution”，风险的“asHampel”邻居=“UncondNeighborhood”的L2微参数家庭与未知的一维参数计算最优强大的影响力曲线。




L2deriv = "RealRandVariable", risk = "asHampel",  neighbor = "UncondNeighborhood" computes the optimally robust influence curve for L2 differentiable  parametric families with unknown k-dimensional parameter  (k > 1) where the underlying distribution is univariate; for total variation neighborhoods only is implemented for the case where there is a 1 x k transformation trafo matrix.
L2deriv =“RealRandVariable的”风险=“asHampel”的，邻居=“UncondNeighborhood”计算最优强大的影响力，与未知的的k维参数（k > 1）的潜在分布曲线L2微参数家庭单因素，总的变化街区实施的情况下，有一个1 x k转型trafo矩阵。




L2deriv = "UnivariateDistribution", risk = "asAnscombe",  neighbor = "UncondNeighborhood" computes the optimally bias-robust influence curve to given ARE in the ideal model for L2 differentiable  parametric families with unknown one-dimensional parameter.
L2deriv =的“UnivariateDistribution”，风险的“asAnscombe”邻居=“UncondNeighborhood”的计算的最佳偏置强大的影响力，曲线给定的，是在一维未知参数L2微参数家庭的理想模型。




L2deriv = "RealRandVariable", risk = "asAnscombe",  neighbor = "UncondNeighborhood" computes the optimally bias-robust influence curve to given ARE in the ideal modelfor L2 differentiable  parametric families with unknown k-dimensional parameter  (k > 1) where the underlying distribution is univariate; for total variation neighborhoods only is implemented for the case where there is a 1 x k transformation trafo matrix.
L2deriv =“RealRandVariable的”风险=“asAnscombe”的，邻居=“UncondNeighborhood”的计算的最佳偏置强大的影响力，曲线L2的理想modelfor的微参数家庭与未知的的k维参数（<X >）的潜在分布是单变量的总变异街区实施的情况下，有一个k > 1转型1 x k矩阵。




L2deriv = "UnivariateDistribution", risk = "asGRisk",  neighbor = "UncondNeighborhood" computes the optimally robust influence curve for L2 differentiable  parametric families with unknown one-dimensional parameter.
L2deriv =的“UnivariateDistribution”，风险的“asGRisk”邻居=“UncondNeighborhood”的L2微参数家庭与未知的一维参数计算最优强大的影响力曲线。




L2deriv = "RealRandVariable", risk = "asGRisk",  neighbor = "UncondNeighborhood" computes the optimally robust influence curve for L2 differentiable  parametric families with unknown k-dimensional parameter  (k > 1) where the underlying distribution is univariate; for total variation neighborhoods only is implemented for the case where there is a 1 x k transformation trafo matrix.
L2deriv =“RealRandVariable的”风险=“asGRisk”的，邻居=“UncondNeighborhood”计算最优强大的影响力，与未知的的k维参数（k > 1）的潜在分布曲线L2微参数家庭单因素，总的变化街区实施的情况下，有一个1 x k转型trafo矩阵。




L2deriv = "UnivariateDistribution", risk = "asUnOvShoot",  neighbor = "UncondNeighborhood" computes the optimally robust influence curve for one-dimensional L2 differentiable parametric families and  asymptotic under-/overshoot risk.   
L2deriv =的“UnivariateDistribution”风险=的“asUnOvShoot”邻居=“UncondNeighborhood”的计算一维L2可微分的参数化家庭和渐近under-/overshoot的风险的最佳强大的影响曲线。


（作者）----------Author(s)----------


Matthias Kohl <a href="mailto:Matthias.Kohl@stamats.de">Matthias.Kohl@stamats.de</a>,<br>
Peter Ruckdeschel <a href="mailtoeter.Ruckdeschel@itwm.fraunhofer.de">eter.Ruckdeschel@itwm.fraunhofer.de</a>



参考文献----------References----------

Rieder, H. (1980) Estimates derived from robust tests. Ann. Stats. 8: 106-115.
Rieder, H. (1994) Robust Asymptotic Statistics. New York: Springer.
Ruckdeschel, P. and Rieder, H. (2004) Optimal Influence Curves for General Loss Functions. Statistics &amp; Decisions 22: 201-223.
Ruckdeschel, P. (2005) Optimally One-Sided Bounded Influence Curves. Mathematical Methods in Statistics 14(1), 105-131.
Kohl, M. (2005) Numerical Contributions to the Asymptotic Theory of Robustness.  Bayreuth: Dissertation.

参见----------See Also----------

InfRobModel-class
InfRobModel-class

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。