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

loveR

sensitivityJR(sensitivityPStrat)
sensitivityJR()所属R语言包：sensitivityPStrat

                                         Principal stratification sensitivity analysis relaxing the monotonicity assumption.
                                         主要分层放松的单调性假设的敏感性分析。

                                         译者：生物统计家园网 机器人LoveR

描述----------Description----------

Principal stratification sensitivity analysis relaxing monotonicity as described by Jemiai and Rotnitzky (2005) and implemented by Shepherd, Redman, and Ankerst (2008).
的主要分层敏感性分析放松的单调性所描述的Jemiai和Rotnitzky（2005），由牧羊人，雷德曼，Ankerst的（2008）和实施。


用法----------Usage----------


sensitivityJR(z, s, y, beta0, beta1, phi, Pi, psi,
              selection, groupings,
              ci = 0.95, ci.method = c("analytic","bootstrap"),
              ci.type = "twoSided", custom.FUN=NULL, na.rm = FALSE,
              N.boot = 100, interval = c(-100, 100),
              upperTest = FALSE, lowerTest = FALSE, twoSidedTest = TRUE,
              verbose=getOption("verbose"), isSlaveMode = FALSE)



参数----------Arguments----------

参数：z
vector; contains the grouping values (e.g., treatment assignment) for each record.
矢量包含分组的每条记录的值（例如，治疗分配）。


参数：s
vector; indicates whether a record is selected.
矢量表示一个记录是否被选中。


参数：y
vector; outcome values.  Can be NA for unselected records.
向量;结果值。可以NA未选中的记录。


参数：beta0
vector; values of the sensitivity parameter <VAR>&beta;0</VAR> linking outcome in group <VAR>g0</VAR> with selection if assigned group <VAR>g1</VAR>.
向量;的敏感性参数的值<VAR>&beta; 0 </ VAR>联组结果<VAR> G0 </ VAR>的选择，如果分配组<VAR>的G1 </ VAR>。


参数：beta1
vector; values of the sensitivity parameter <VAR>&beta;1</VAR> linking outcome in group <VAR>g1</VAR> with selection if assigned group <VAR>g0</VAR>.
向量;的敏感性参数的值<VAR> &beta; 1 </ VAR>联组<VAR> G1结果</ VAR>的选择，如果分配组<VAR> G0 </ VAR>。


参数：phi, Pi, psi
vector; sensitivity parameters specifying the joint distribution of S(\var{g0}), S(\var{g1}).  Only one of the three parameters should be specified. psi is the log-odds ratio of selection. Pi is the probability of being in the always selected principal stratum (Pr(S(\var{g0}) = S(\var{g1}) =       selected)). phi is the probability of selection in group <VAR>g0</VAR> given selection in group <VAR>g1</VAR> (Pr(S(\var{g0}) = 1|S(\var{g1}) = 1)).
向量;敏感性参数的联合分布S(\var{g0})，S(\var{g1})。只有一个的三个参数应该被指定。 psi的选择是对数的比值比。 Pi的概率是在总是选择主要的层（Pr(S(\var{g0}) = S(\var{g1}) =       selected)）。 phi的概率是选择组<VAR> G0 </ VAR>组给定的选择<VAR> G1 </ VAR>（Pr(S(\var{g0}) = 1|S(\var{g1}) = 1)）。


参数：selection
The value of s indicating selection.
的值s表示选择。


参数：groupings
vector of two elements c(<VAR>g0</VAR>,<VAR>g1</VAR>); describes to possible group values. The first element <VAR>g0</VAR> being the value of z the delineates the first group, the last element <VAR>g1</VAR> being the value of z which delineates the second group.
向量的两个元素c(<VAR>g0</VAR>,<VAR>g1</VAR>);描述可能的组值。第一元<VAR> G0 </ VAR>的价值z描绘了第一组的最后一个元素<VAR> G1 </ VAR>的价值z勾画出第二组。


参数：ci
numeric vector;  confidence interval value. Defaults to 0.95
数字矢量值的置信区间。默认为0.95


参数：ci.method
character;  method by which the confidence interval and variance are calculated.  Can be &ldquo;analytic&rdquo; or &ldquo;bootstrap&rdquo;. Defaults to c("analytic","bootstrap")
字符;方法，通过该方法计算的置信区间和方差。可以“分析”或“引导”。默认为c("analytic","bootstrap")


参数：ci.type
character vector; type of confidence interval that the corresponding ci element is referring to.  Can be &ldquo;upper&rdquo;, &ldquo;lower&rdquo;, or &ldquo;twoSided&rdquo;.  Defaults to "twoSided".
字符向量的置信区间相应的ci元素指的类型。可以是“上”，“下”，或“twoSided”。默认为"twoSided"的。


参数：custom.FUN
function; function to calculate custom result. mu0, mu1, p0, p1 are available to be used as arguments in the custom function, where \code{mu0} = E(Y(\var{g0})|S(\var{g0}) = S(\var{g1}) = selected), \code{mu1} = E(Y(\var{g1})|S(\var{g0}) = S(\var{g1}) = selected), \code{p0} = P(S(\var{g0}) = selected), and \code{p1} = P(S(\var{g1}) = selected).  The custom function must return a single value.
功能自定义的函数来计算结果。 mu0，mu1，p0，p1可被用来作为自定义函数的参数，其中\code{mu0} = E(Y(\var{g0})|S(\var{g0}) = S(\var{g1}) = selected)，\code{mu1} = E(Y(\var{g1})|S(\var{g0}) = S(\var{g1}) = selected)，\code{p0} = P(S(\var{g0}) = selected)和\code{p1} = P(S(\var{g1}) = selected)。自定义函数必须返回一个值。


参数：na.rm
logical; indicates whether records that are invalid due to NA values should be removed from the data set.
逻辑表示是无效的，由于NA值的记录是否应该从数据集。


参数：N.boot
integer; number of bootstrap repetitions that will be run when ci.method includes &ldquo;bootstrap&rdquo;.
整数，将运行时ci.method包括“引导”，引导重复数目。


参数：interval
numeric vector of length 2. Controls the range limits used by optimize to estimate <VAR>&alpha;0</VAR> and <VAR>&alpha;1</VAR>.
数字矢量长度为2。控件范围限制由优化估计<VAR>的使用的&alpha; 0 </ VAR>和<VAR>&alpha; 1 </ VAR>。


参数：lowerTest
logical.  Return the lower one sided p-value for the ACE. Defaults to FALSE
逻辑。传回较低双侧P值的ACE。默认为FALSE


参数：upperTest
logical.  Return the upper one sided p-value for the ACE. Defaults to FALSE
逻辑。返回上一个双面P值的ACE。默认为FALSE


参数：twoSidedTest
logical.  Return a two sided p-value for the ACE. Defaults to TRUE
逻辑。返回的双面p值的ACE。默认为TRUE


参数：verbose
logical;  prints dots when bootstrapping to show that something is happening. Bootstrapping can take a long time.
逻辑打印点在引导时显示某些事情正在发生。自举可能需要很长的时间。


参数：isSlaveMode
logical.  Internal Use only. Used in recursion.
逻辑。仅供内部使用。在递归使用。


Details

详细信息----------Details----------

Performs a sensitivity analysis estimating the average causal effect among those who would have been selected regardless of treatment assignment (ACE) without assuming monotonicity (i.e., that one of the principal strata is empty).  The method assumes no interference (i.e., potential outcomes of all subjects are unaffected by treatment assignment of other subjects) and ignorable (i.e., random) treatment assignment.  ACE is identified by assuming values for the sensitivity parameters beta0, beta1, and one of the parameters phi, psi, or Pi. The sensitivity parameters beta0 and beta1 have a log-odds ratio interpretation (see help for sensitivityGBH).
估计在那些谁被选中的治疗分配（ACE）没有假设单调性（也就是说，其中的主要阶层是空）的平均因果关系进行了敏感性分析。该方法假设没有干扰（即，所有科目的可能的结果是不受其他科目的处理分配）和可忽略处理分配（即随机）。 ACE是确定的假设值的灵敏度参数beta0，beta1，和的参数之一phi，psi或Pi。灵敏度参数beta0和beta1有一个数几率比解释（见sensitivityGBH）的帮助。

Only one of the parameters phi, psi, or Pi should be specified as all depend on each other.  psi is unrestrained taking any value on the real line.  The other parameters, psi and Pi have constraints and there will be estimation problems if these parameters are set at values outside the of their range of acceptable values based on the observed data.  See Shepherd, Gilbert, Dupont (in press) for more details.
只有一个参数phi，psi或Pi应指定为互相依赖的。 psi无拘无束的实线的任何值。其他参数，psi和Pi有限制，估计会有问题，如果这些参数设置为他们的观测数据的基础上可接受值的范围以外的值。有关详细信息，请参阅牧羊犬，吉尔伯特，杜邦（记者）。


值----------Value----------

object of class sensitivity3d
对象的类sensitivity3d

<table summary="R valueblock"> <tr valign="top"><td>ACE</td> <td>  array; estimated values of ACE for all combinations of beta0, beta1, and phi, Pi, psi.  Array dimensions are length(beta0), length(beta1), length(psi). </td></tr> <tr valign="top"><td>ACE.ci</td> <td>  array; confidence interval determined by quantile if ci.method includes &ldquo;bootstrap&rdquo;.  Otherwise calculated using analytic variance with large sample normal approximation. Array dimensions the same as ACE element. </td></tr> <tr valign="top"><td>ACE.var</td> <td>  array; estimated variance of ACE. Array dimensions the same as ACE element. </td></tr> <tr valign="top"><td>ACE.p</td> <td>  vector; estimated p-value of ACE. </td></tr> <tr valign="top"><td>beta0</td> <td>  vector; &beta; values used for the first group. </td></tr> <tr valign="top"><td>alphahat0</td> <td>  vector; estimated &alpha; values for the first group. </td></tr> <tr valign="top"><td>Fas0</td> <td>  function; estimator for the distribution function of <VAR>y0</VAR> in the first group in the always selected stratum. </td></tr> <tr valign="top"><td>beta1</td> <td>  vector; &beta; values used for the second group. </td></tr> <tr valign="top"><td>alphahat1</td> <td>  vector; estimated &alpha; values for the second group. </td></tr> <tr valign="top"><td>Fas1</td> <td>  function; estimator for the distribution function of <VAR>y1</VAR> in the second group in the always selected stratum. </td></tr> <tr valign="top"><td>phi</td> <td>  vector; phi values used. </td></tr> <tr valign="top"><td>Pi</td> <td>  vector; Pi values used. </td></tr> <tr valign="top"><td>psi</td> <td>  vector; psi values used. </td></tr> <tr valign="top"><td>ci.map</td> <td>  list; mapping of confidence interval to quantile probability.  Use numbers contained within as indices to the SCE.ci element. </td></tr> </table>
<table summary="R valueblock"> <tr valign="top"> <TD>ACE </ TD> <TD>阵列，ACE为估计值的所有组合beta0，beta1和phi，Pi，psi。阵列尺寸是length(beta0)，length(beta1)，length(psi)。 </ TD> </ TR> <tr valign="top"> <TD> ACE.ci </ TD> <TD>阵列，可信区间确定的quantile如果ci.method＆ldquo引导“。否则使用分析方差大样本正常逼近的计算。数组维数一样ACE元素。 </ TD> </ TR> <tr valign="top"> <TD>ACE.var </ TD> <TD>阵列;估计方差的ACE。数组维数一样ACE元素。 </ TD> </ TR> <tr valign="top"> <TD> ACE.p </ TD> <TD>矢量估计p值的ACE。 </ TD> </ TR> <tr valign="top"> <TD>beta0 </ TD> <TD>向量，“&beta;值用于第一组。 </ TD> </ TR> <tr valign="top"> <TD> alphahat0 </ TD> <TD>向量;估计&alpha;值第一组。 </ TD> </ TR> <tr valign="top"> <TD>Fas0 </ TD> <TD>功能;估计的分布函数<VAR> Y0 </ VAR>第一组总是选择阶层。 </ TD> </ TR> <tr valign="top"> <TD>beta1 </ TD> <TD>向量;&beta;用于第二组值。 </ TD> </ TR> <tr valign="top"> <TD> alphahat1 </ TD> <TD>向量;估计&alpha;值第二组。 </ TD> </ TR> <tr valign="top"> <TD>Fas1 </ TD> <TD>功能;估计的分布函数<VAR> Y1 </ VAR>第二组总是选择阶层。 </ TD> </ TR> <tr valign="top"> <TD>phi </ TD> <TD> phi向量;值。 </ TD> </ TR> <tr valign="top"> <TD>Pi </ TD> <TD> Pi向量;值。 </ TD> </ TR> <tr valign="top"> <TD>psi </ TD> <TD> psi向量;值。 </ TD> </ TR> <tr valign="top"> <TD>ci.map </ TD> <TD>名单;位数的概率的置信区间的映射。使用数字SCE.ci元素包含在作为指数。 </ TD> </ TR> </ TABLE>


（作者）----------Author(s)----------



Bryan E. Shepherd <br>
Department of Biostatistics<br>
Vanderbilt University<br>




Charles Dupont <br>
Department of Biostatistics<br>
Vanderbilt University<br>




参考文献----------References----------

Jemiai Y (2005), &ldquo;Semiparametric Methods for Inferring Treatment Effects on Outcomes Defined Only if a Post-Randomization Event Occurs,&rdquo; unpublished doctoral dissertation under the supervision of A. Rotnitzky, Harvard School of Public Health, Dept. of Biostatistics.
Shepherd BE, Redman MW, Ankerst DP (2008), &ldquo;Does Finasteride affect the severity of prostate cancer? A causal sensitivity analysis,&rdquo; Journal of the American Statistical Association 2008, 484, 1392-1404.
Shepherd BE, Gilbert PB, and Dupont CT, &ldquo;Sensitivity analyses comparing time-to-event outcomes only existing in a subset selected postrandomization and relaxing monotonicity,&rdquo; Biometrics, in press.

参见----------See Also----------

sensitivityGBH, sensitivitySGD
sensitivityGBH，sensitivitySGD


实例----------Examples----------




data(vaccine.trial)
ansJR<-with(vaccine.trial,
          sensitivityJR(z=treatment,s=hiv.outcome,y=logVL,
                    beta0=c(-1,-.75,-.5,-.25,0,.25,.5,.75,1),
                    beta1=c(-1,-.75,-.5,-.25,0,.25,.5,.75,1),
                    phi=c(0.95,0.90,0.80), selection="infected",
                    groupings=c("placebo","vaccine"),
                    N.boot=100)
         )
ansJR

data(vaccine.trial)
ansJR<-with(vaccine.trial,
          sensitivityJR(z=treatment,s=hiv.outcome,y=logVL,
                    beta0=c(-1,-.75,-.5,-.25,0,.25,.5,.75,1),
                    beta1=c(-1,-.75,-.5,-.25,0,.25,.5,.75,1),
                    phi=c(0.95,0.90,0.80), selection="infected",
                    groupings=c("placebo","vaccine"),
                    custom.FUN=function(mu0, mu1, ...) mu1 - mu0,
                    upperTest=TRUE, lowerTest=TRUE, twoSidedTest=TRUE,
                    N.boot=100)
         )
ansJR


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。