TML.noncensored(RobustAFT)
TML.noncensored()所属R语言包：RobustAFT
Truncated Maximum Likelihood Regression Without Censored Observations
截断极大似然回归没有定数截尾观测
译者：生物统计家园网 机器人LoveR
描述----------Description----------
This function computes the truncated maximum likelihood regression estimate described in Marazzi and Yohai (2004). The error distribution is assumed to follow approximately a Gaussian or a log-Weibull distribution. The cut-off values for outlier rejection are fixed or adaptive.
此函数计算截断的最大似然回归估计在马拉斯和Yohai的（2004年）。的误差分布假定约遵循高斯或log的Weibull分布。截止拒绝离群值是固定的或自适应。
用法----------Usage----------
TML.noncensored(formula, data, errors = "Gaussian", cu = NULL,
initial = "S",otp = "fixed", cov = "parametric",
参数----------Arguments----------
参数：formula
A formula, i.e., a symbolic description of the model to be fit (cf. glm or lm).
Aformula，即是一个象征性的描述模型拟合（参见glm或lm）。
参数：data
An optional data frame containing the variables in the model. If not found in data, the variables are taken from environment(formula), typically the environment from which TML.noncensored is called.
一个可选的数据框包含在模型中的变量。如果没有找到data，变量environment(formula)，通常是TML.noncensored被称为环境。
参数：errors
"Gaussian": the error distribution is assumed to be Gaussian.
“高斯”：误差分布被假定为高斯。
"logWeibull" : the error distribution is assumed to be log-Weibull. </ul>
“logWeibull”：，误差分布被假定为log威布尔。 </ ul>
参数：cu
Preliminary minimal upper cut-off. The default is 2.5 in the Gaussian case and 1.855356 in the log-Weibull case.
初步，最小上切断。在高斯的情况下的默认值是2.5和1.855356log威布尔情况下。
参数：initial
"S" : initial S-estimate.
“S”：最初的S-估计。
"input" : the initial estimate is given on input.</ul>
“输入”：初步估计给定的输入。</ ul>
参数：otp
"adaptive": adaptive cut-off.
“自适应”：自适应切断。
"fixed" : non adaptive cut-off.</ul>
“固定”：非自适应切断。</ ul>
参数：cov
"no": no estimate of the covariance matrix of the coefficients is provided on output.
“无”：没有被设置在输出估计的协方差矩阵的系数。
"parametric": a parametric estimate of the covariance matrix of the coefficients is provided (to be used when n is small).
“参数”：提供一个参数估计的协方差矩阵的系数（当n较小时，可以使用）。
"nonparametric": a nonparametric estimate of the covariance matrix of the coefficients is provided.</ul>
“非参数”：一个非参数估计的协方差矩阵的系数。</ ul>
参数：input
Initial input estimates of location and scale.<br> Required when initial="input".
最初的输入估计值的位置和规模。参考时需要初始=“输入”。
"Gaussian case" : list(theta=...,sigma=...) initial input estimates. theta: location; sigma: scale.
“高斯情况”：列表（θ= ...，σ= ...）最初的输入估计。 THETA的位置;西格玛：规模。
"logWeibull case" : list(tau=...,v=...) initial input estimates of location (tau) and scale (v).</ul>
“logWeibull情况”：名单（τ= ... = ...）最初的输入估计值的位置（头）和规模（V）。</ ul>
参数：control
Control parameters. For the default values, see the function TML.noncensored.control.
控制参数。对于默认值，请参阅功能TML.noncensored.control。
参数：...
If fastS=TRUE, parameters for lmrob.S. See the function lmrob.control (from the robustbase package) for the default values.
如果斋戒= TRUE，参数lmrob.S。见的功能lmrob.control（从robustbase包）为默认值。
值----------Value----------
TML.noncensored returns an object of class "TML". The function summary can be used to obtain or print a summary of the results. The generic extractor functions fitted, residuals and weights can be used to extract various elements of the value returned by TML.noncensored. The function update can be used to update the model.
TML.noncensored返回一个对象类的“TML”。函数summary可以用来获取或打印的汇总结果。通用提取功能fitted，residuals和weights可以用于提取各种元素的TML.noncensored返回的值。功能update可以用来更新模型。
An object of class "TML" is a list with the following components: <table summary="R valueblock"> <tr valign="top"><td>th0 </td> <td> Initial coefficient estimates (S or input).</td></tr> <tr valign="top"><td>v0 </td> <td> Initial scale (S or input).</td></tr> <tr valign="top"><td>nit0 </td> <td> Reached number of iteration in lmrob.S (available only if fastS is TRUE).</td></tr> <tr valign="top"><td>th1 </td> <td> Final coefficient estimates.</td></tr> <tr valign="top"><td>v1 </td> <td> Final scale (S or input).</td></tr> <tr valign="top"><td>nit1 </td> <td> Number of iterations reached by the IRLS algorithm for the final estimates.</td></tr> <tr valign="top"><td>tu,tl </td> <td> Final cut-off values.</td></tr> <tr valign="top"><td>alpha </td> <td> Estimated proportion of retained observations.</td></tr> <tr valign="top"><td>tn </td> <td> Number of retained observations.</td></tr> <tr valign="top"><td>beta </td> <td> Consistency constant for scale.</td></tr> <tr valign="top"><td>weights </td> <td> Vector of weights (0 for rejected observations, 1 for retained observations).</td></tr> <tr valign="top"><td>COV</td> <td> Covariance matrix of the final estimates (th1[1],...,th1[p],v1) (where p=ncol(X)).</td></tr> <tr valign="top"><td>residuals </td> <td> The residuals, that is response minus fitted values.</td></tr> <tr valign="top"><td>fitted.values </td> <td> The fitted mean values.</td></tr> <tr valign="top"><td>call </td> <td> The matched call.</td></tr> <tr valign="top"><td>formula </td> <td> The formula supplied.</td></tr> <tr valign="top"><td>terms </td> <td> The terms object used.</td></tr> <tr valign="top"><td>data </td> <td> The data argument.</td></tr></table>
“TML”类的一个对象是一个具有下列组件：<table summary="R valueblock"> <tr valign="top"> <TD>th0 </ TD> <TD>初步估计系数（S或输入）。</ TD> </ TR> <tr valign="top"> <TD> v0 </ TD> <TD>初始规模（S或输入）。</ TD> < / TR> <tr valign="top"> <TD> nit0 </ TD> <TD>达到迭代次数lmrob.S（仅适用于斋戒是TRUE）。</ TD> < / TR> <tr valign="top"> <TD> th1 </ TD> <TD>最终的系数估计值。</ TD> </ TR> <tr valign="top"> <TD> v1 </ TD> <TD>最终规模（S或输入）。</ TD> </ TR> <tr valign="top"> <TD> nit1 </ TD> <TD>达成的最终估计IRLS算法的迭代。</ TD> </ TR> <tr valign="top"> <TD> tu,tl </ TD> <TD>的Final Cut-off值。 </ TD> </ TR> <tr valign="top"> <TD>alpha </ TD> <TD>估计比例保留意见。</ TD> </ TR> <TR VALIGN =“顶“<TD>tn </ TD> <TD>保留意见。</ TD> </ TR> <tr valign="top"> <TD>beta </ TD > <TD>一致性恒定的规模。</ TD> </ TR> <tr valign="top"> <TD>weights </ TD> <TD>的权重向量（0被拒绝的观测，1保留意见）。</ TD> </ TR> <tr valign="top"> <TD> COV </ TD> <TD>协方差矩阵的最终估计值（TH1 [1]，... ，TH1 [P]，V1）（其中p = NCOL（X））</ TD> </ TR> <tr valign="top"> <TD> residuals </ TD> <TD>残差，，是响应减去拟合值。</ TD> </ TR> <tr valign="top"> <TD>fitted.values </ TD> <TD>拟合的平均值。</ TD> </ TR> <tr valign="top"> <TD> call </ TD> <TD>匹配的呼叫。</ TD> </ TR> <tr valign="top"> <TD> formula </ TD> <TD>提供的计算公式。</ TD> </ TR> <tr valign="top"> <TD>terms </ TD> <TD>terms对象。</ TD> </ TR> <tr valign="top"> <TD>data </ TD> <TD>data argument。</ TD> </ TR> </ TABLE>
参考文献----------References----------
Marazzi A., Yohai V. (2004). Adaptively truncated maximum likelihood regression with asymmetric errors. Journal of Statistical Planning and Inference, 122, 271-291.
参见----------See Also----------
TML.noncensored.control, TML1.noncensored, TML1.noncensored.control, TML.censored
TML.noncensored.control，TML1.noncensored，TML1.noncensored.control，TML.censored
实例----------Examples----------
data(D243)
Cost <- D243$Cost # Cost (Swiss francs)[费用（瑞士法郎）]
LOS <- D243$LOS # Length of stay (days)[住院天数（天）]
Adm <- D243$Typadm; Adm <- (Adm==" Urg")*1 # Type of admission [入院类型]
# (0=on notification, 1=Emergency)[（0 =通知，紧急）]
Ass <- D243$Typass; Ass <- (Ass=="P" )*1 # Type of insurance [保险类型]
# (0=usual, 1=private)[（0 =往常一样，1 =私人）]
Age <- D243$age # Age (years)[年龄（岁）]
Dst <- D243$dest; Dst <- (Dst=="DOMI")*1 # Destination [目的地]
# (1=Home, 0=another hospital)[（1 =首页，0 =另一个医院）]
Sex <- D243$Sexe; Sex <- (Sex=="M" )*1 # Sex (1=Male, 0=Female)[性别（1 = 0 =男，女）]
# Truncated maximum likelihood regression with Gaussian errors[被截断的最大似然回归与高斯错误]
z <- TML.noncensored(log(Cost)~log(LOS)+Adm+Ass+Age+Dst+Sex,
otp="adaptive",control=list(fastS=TRUE))
summary(z)
# Truncated maximum likelihood regression with log-Weibull errors[截断log韦伯错误的最大似然回归]
w <- TML.noncensored(log(Cost)~log(LOS)+Adm+Ass+Age+Dst+Sex,
errors="logWeibull",otp="adaptive",control=list(fastS=TRUE))
summary(w)
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 2012-9-27 22:05:15
