model.average(secr)
model.average()所属R语言包：secr
Model averaging for SECR Models
SECR模型的模型平均
译者：生物统计家园网 机器人LoveR
描述----------Description----------
AICc-weighted average of estimated "real" or "beta" parameters from multiple fitted secr models.
国际会议中心从多个装SECR模型的参数估计真正的或测试版的加权平均。
用法----------Usage----------
model.average(..., realnames = NULL, betanames = NULL, newdata = NULL,
alpha = 0.05, dmax = 10, covar = FALSE, average = "link")
collate (..., realnames = NULL, betanames = NULL, newdata = NULL,
scaled = FALSE, alpha = 0.05, perm = 1:4, fields = 1:4)
参数----------Arguments----------
参数：...
secr objects
secr对象
参数：realnames
character vector of real parameter names
向量的实际参数名称字符
参数：betanames
character vector of beta parameter names
测试参数名称的字符向量
参数：newdata
optional dataframe of values at which to evaluate models
可选的数据框的值，以评估模型
参数：scaled
logical for scaling of sigma and g0 (see Details)
逻辑缩放西格玛和G0（见详情）
参数：alpha
alpha level for confidence intervals
α水平置信区间
参数：dmax
numeric, the maximum AIC difference for inclusion in confidence set
数字包含在置信集，最大的AIC差异
参数：covar
logical, if TRUE then return variance-covariance matrix
逻辑，如果为真则返回方差 - 协方差矩阵
参数：average
character string for scale on which to average real parameters
字符串规模平均实际参数
参数：perm
permutation of dimensions in output from collate
排列尺寸输出collate
参数：fields
vector to restrict summary fields in output
矢量限制在输出的汇总字段
Details
详细信息----------Details----------
Models to be compared must have been fitted to the same data and use the same likelihood method (full vs conditional). If realnames == NULL and betanames == NULL then all real parameters will be averaged; in this case all models must use the same real parameters. To average beta parameters, specify betanames (this is ignored if a value is provided for realnames). See predict.secr for an explanation of the optional argument newdata; newdata is ignored when averaging beta parameters.
以进行比较的模型必须已被安装到相同的数据，并使用相同的似然方法（全与条件）。如果realnames== NULL和betanames== NULL，则所有的实际参数将被平均，在这种情况下，所有的模型都必须使用相同的参数。对于一般的测试参数，指定betanames（这提供了一个值被忽略，如果realnames）。 predict.secr的可选参数的说明newdatanewdata平均测试参数时，被忽略。
Model-averaged estimates for parameter theta are given by
模型的平均估计的参数theta给出
where the subscript k refers to a specific model and the w_k are AIC weights with small sample adjustment (see AIC.secr for details). Averaging of real parameters may be done on the link scale before back-transformation (average="link") or after back-transformation (average="real").
下标k是指一个特定的模式和w_k是AIC的权重小样本调整（见AIC.secr）。平均的实际参数可能会在链接上规模前回转型（average="link"）或回转型后（average="real"）。
Models for which dAICc > dmax are given a weight of zero and effectively are excluded from averaging.
模型dAICc>dmax给出权重为零，有效地排除从平均。
Also,
另外，
where beta-hat_k = theta-hat_k -- theta-hat and the variances are asymptotic estimates from fitting each model k. This follows Burnham and Anderson (2004) rather than Buckland et al. (1997).
其中beta-hat_k = theta-hat_k -- theta-hat和的方差的渐近估计，拟合每个模型k。在此之前，伯纳姆和安德森（2004年），而不是巴克兰等。 （1997年）。
collate extracts parameter estimates from a set of fitted secr model objects. fields may be used to select a subset of summary fields ("estimate","SE.estimate","lcl","ucl") by name or number.
collate提取的参数估计一套合身的秘书服务模型对象。 fields可用于选择一个子集的汇总字段（“估计”，“SE.estimate”，“LCL”，“伦敦大学学院”）的名称或编号。
The argument scaled applies only to the detection parameters g0 and sigma, and only to models fitted with scalesigma or scaleg0 switched on. If scaled is TRUE then each estimate is multiplied by its scale factor (1/D^0.5 and 1/sigma^2 respectively).
参数scaled仅适用于检测参数g0和标准差，而且只配备了scalesigma或scaleg0打开的模型。如果scaled是TRUE，则每个估计值是其比例因子乘以（1 / D ^ 0.5和1/sigma ^ 2）。
值----------Value----------
For model.average, an array of model-averaged estimates, their standard errors, and a 100(1-alpha)% confidence interval. The interval for real parameters is backtransformed from the link scale. If there is only one row in newdata or beta parameters are averaged or averaging is requested for only one parameter then the array is collapsed to a matrix. If covar = TRUE then a list is returned with separate components for the estimates and the variance-covariance matrices.
对于model.average，阵列模型的平均估计，其标准误差，以及一个100(1-alpha)％的置信区间。实际参数的逆转换的时间间隔从链接的规模。如果有中只有一行newdata或β参数的平均值或平均要求只有一个参数，则该数组已倍数到一个矩阵。如果covar = TRUE然后返回一个列表的估计和方差 - 协方差矩阵与单独的组件。
For collate, a 4-dimensional array of model-specific parameter estimates. By default, the dimensions correspond respectively to rows in newdata (usually sessions), models, statistic fields (estimate, SE.estimate, lcl, ucl), and parameters ("D", "g0" etc.). For particular comparisons it often helps to reorder the dimensions with the perm argument.
对于collate，一个4维数组的特定模型的参数估计。默认情况下，尺寸分别对应于newdata（通常会话中的行），模型，统计字段（的估计，SE.estimate，LCL，UCL）和参数（“D”，“G0”等。 ）。对于特定的比较，它常常有助于重新排序的尺寸与perm参数。
警告----------Warning----------
model.average may conflict with a method of the
model.average可能会发生冲突的方法
参考文献----------References----------
selection: an integral part of inference. Biometrics 53, 603–618.
Multimodel Inference: A Practical Information-Theoretic Approach. Second edition. New York: Springer-Verlag.
understanding AIC and BIC in model selection. Sociological Methods & Research 33, 261–304.
参见----------See Also----------
AIC.secr, secr.fit
AIC.secr，secr.fit
实例----------Examples----------
## Compare two models fitted previously[＃比较两种模型以前]
## secrdemo.0 is a null model[＃secrdemo.0是一个空的模型]
## secrdemo.b has a learned trap response[＃secrdemo.b有一个博学多才的陷阱响应]
model.average(secrdemo.0, secrdemo.b)
model.average(secrdemo.0, secrdemo.b, betanames = c("D","g0","sigma"))
## In this case we find the difference was actually trivial...[＃在这种情况下，我们发现其实是微不足道的差异...]
## (subscripting of output is equivalent to setting fields = 1)[＃（标输出设置字段= 1）]
collate (secrdemo.0, secrdemo.b, perm = c(4,2,3,1))[,,1,]
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 00:00:07
