getPowerFit(simsem)
getPowerFit()所属R语言包：simsem
Find power in rejecting alternative models based on fit indices criteria
查找权力拒绝的替代车型的基础上拟合指数标准
译者：生物统计家园网 机器人LoveR
描述----------Description----------
Find the proportion of fit indices that indicate worse fit than a specified cutoffs. The cutoffs may be calculated from getCutoff of the null model.
寻找表明糟糕适合的比指定的临界值的拟合指数的比例。从getCutoff空模型，可以计算的截止时间。
用法----------Usage----------
getPowerFit(altObject, cutoff, revDirec = FALSE, usedFit=NULL, ...)
参数----------Arguments----------
参数：altObject
SimResult that indicates alternative model that users wish to reject
SimResult，表示另一种模式，用户希望拒绝
参数：cutoff
Fit indices cutoffs from null model or users. This should be a vector with a specified fit indices names as the name of vector elements. This argument can be missing if the SimResult is specified in the altObject and the SimResult of the null model is specified.
拟合指数临界值从空模型或用户。这应该是一个向量，其指定的拟合指数作为向量元素的名称的名称。这种说法，可以丢失，如果SimResultaltObject和SimResult空模型被指定在指定。
参数：revDirec
The default is to count the proportion of fit indices that indicates lower fit to the model, such as how many RMSEA in the alternative model that is worse than cutoffs. The direction can be reversed by setting as TRUE.
默认值是数的比例拟合指数，表明适合的模型，如RMSEA的另一种模式，更糟糕的是比临界值多少。的方向是可以逆转的通过设置TRUE。
参数：usedFit
Vector of names of fit indices that researchers wish to getCutoffs from. The default is to getCutoffs of all fit indices.
矢量的拟合指数，研究人员希望getCutoffs的名字。默认值是拟合指数的所有getCutoffs。
参数：...
Additional arguments
附加参数
值----------Value----------
List of power given different fit indices.
赋予的权力不同的拟合指数列表。
方法----------Methods----------
This method will find the fit indices indicated in the altObject that provides worse fit than the cutoff. The additional arguments are predictor, predictorVal, condCutoff, and df, which allows the fit indices predicted by any arbitrary independent variables (such as sample size or percent MCAR). The predictor is the data.frame of the predictor values. The number of rows of the predictor argument should be equal to the number of rows in the object. The predictorVal is the values of predictor that researchers would like to find the power from. The condCutoff is a logical. If TRUE, the cutoff is applicable only a given value of predictorVal. If FALSE, the cutoff is applicable in any values of predictor. The df is the degree of freedom used in spline method in predicting the fit indices by the predictors. If df is 0, the spline method will not be applied.
这种方法就可以找到合适的指数表示在altObject，提供适合比cutoff差。额外的参数predictor，predictorVal，condCutoff和df，它允许任意的独立变量（如样本量或百分比MCAR）的拟合指数预测。 predictor是data.frame的预测值。行predictor参数的数量应等于在object的行数。 predictorVal是，研究人员希望能够找到电源的预测值。 condCutoff是一个逻辑。如果TRUE，截止是只适用的给定值predictorVal。如果FALSE，截止适用于任何值predictor。 df程度的自由中使用的样条方法在预测的拟合指数的预测。如果df是0，样条方法将不适用。
The details are similar to the method for altObject="data.frame" and cutoff="vector".
的细节是类似altObject="data.frame"和cutoff="vector"的方法。
This method will find the fit indices indicated in the altObject that provides worse fit than the cutoff. The additional arguments are nVal, pmMCARval, pmMARval, condCutoff, and df, which are needed when using varying sample sizes or percent missing across replications in SimResult. The nVal is the sample size value that researchers wish to find the fit indices cutoffs from. The pmMCARval is the percent missing completely at random value that researchers wish to find the fit indices cutoffs from. The pmMARval is the percent missing at random value that researchers wish to find the fit indices cutoffs from. The condCutoff is a logical. If TRUE, the cutoff is applicable only a given set of nVal, pmMCARval, and pmMARval. If FALSE, the cutoff is applicable in any values of sample size and percent missing. The df is the degree of freedom used in spline method in predicting the fit indices by the predictors. If df is 0, the spline method will not be applied.
这种方法就可以找到合适的指数表示在altObject，提供适合比cutoff差。额外的参数是nVal，pmMCARval，pmMARval，condCutoff和df，使用时需要不同的样本量或百分比在重复，缺少 SimResult。 nVal为样本，研究人员希望找到拟合指数临界值的大小值。 pmMCARval是完全随机值，研究人员希望找到拟合指数临界值的百分比失踪。 pmMARval是失踪的随机值，研究人员希望找到拟合指数临界值的百分比。 condCutoff是一个逻辑。如果TRUE，截止仅适用于一组给定的nVal，pmMCARval，pmMARval。如果FALSE，截止适用于任何值的样本的大小和百分比失踪。 df程度的自由中使用的样条方法在预测的拟合指数的预测。如果df是0，样条方法将不适用。
The details are similar to the method for altObject="SimResult" and cutoff="vector". The cutoff argument must not be specified. Rather, the nullObject, which is an additional argument of this method, is required. The nullObject is the SimResult that contains the simulation result from fitting the null model by the data from the null model.
的细节是类似altObject="SimResult"和cutoff="vector"的方法。 cutoff参数必须不被指定。相反，nullObject，这是该方法的一个额外的参数，是必需的。 nullObject是SimResult包含空模型的数据拟合空模型的模拟结果。
（作者）----------Author(s)----------
Sunthud Pornprasertmanit (University of Kansas; <a href="mailto:psunthud@ku.edu">psunthud@ku.edu</a>)
参见----------See Also----------
getCutoff to find the cutoffs from null model.
getCutoff找到空模型的截断。
SimResult to see how to create simResult
SimResult来看看如何创建simResult
实例----------Examples----------
## Not run: [＃不运行：]
loading.null <- matrix(0, 6, 1)
loading.null[1:6, 1] <- NA
LX.NULL <- simMatrix(loading.null, 0.7)
RPH.NULL <- symMatrix(diag(1))
RTD <- symMatrix(diag(6))
CFA.Model.NULL <- simSetCFA(LY = LX.NULL, RPS = RPH.NULL, RTE = RTD)
SimData.NULL <- simData(CFA.Model.NULL, 500)
SimModel <- simModel(CFA.Model.NULL)
# We make the examples running only 5 replications to save time.[我们的例子只有5次重复，以节省时间。]
# In reality, more replications are needed.[在现实中，需要更多的复制。]
Output.NULL <- simResult(5, SimData.NULL, SimModel)
Cut.NULL <- getCutoff(Output.NULL, 0.95)
u79 <- simUnif(0.7, 0.9)
loading.alt <- matrix(0, 6, 2)
loading.alt[1:3, 1] <- NA
loading.alt[4:6, 2] <- NA
LX.ALT <- simMatrix(loading.alt, 0.7)
latent.cor.alt <- matrix(NA, 2, 2)
diag(latent.cor.alt) <- 1
RPH.ALT <- symMatrix(latent.cor.alt, "u79")
CFA.Model.ALT <- simSetCFA(LY = LX.ALT, RPS = RPH.ALT, RTE = RTD)
SimData.ALT <- simData(CFA.Model.ALT, 500)
Output.ALT <- simResult(5, SimData.ALT, SimModel)
getPowerFit(Output.ALT, cutoff=Cut.NULL)
Rule.of.thumb <- c(RMSEA=0.05, CFI=0.95, TLI=0.95, SRMR=0.06)
getPowerFit(Output.ALT, cutoff=Rule.of.thumb, usedFit=c("RMSEA", "CFI", "TLI", "SRMR"))
Output.NULL2 <- simResult(NULL, SimData.NULL, SimModel, n=seq(50, 500, 50))
Output.ALT2 <- simResult(NULL, SimData.ALT, SimModel, n=seq(50, 500, 50))
getPowerFit(Output.ALT2, nullObject=Output.NULL2, nVal=250)
## End(Not run)[＃（不执行）]
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 2012-9-30 09:20:49
