gam.fit3(mgcv)
gam.fit3()所属R语言包：mgcv
P-IRLS GAM estimation with GCV \& UBRE/AIC or RE/ML derivative calculation
的P-IRLS自由亚齐运动估计与GCV的\＆UBRE / AIC或者RE /毫升计算导数的
译者：生物统计家园网 机器人LoveR
描述----------Description----------
Estimation of GAM smoothing parameters is most stable if optimization of the UBRE/AIC, GCV, GACV, REML or ML score is outer to the penalized iteratively re-weighted least squares scheme used to estimate the model given smoothing parameters.
GAM平滑参数的估计是最稳定的，如果优化UBRE /工商局，GCV的，GACV，REML法或ML得分外处罚迭代重新加权最小二乘计划用于估计平滑参数模型。
This routine estimates a GAM (any quadratically penalized GLM) given log smoothing paramaters, and evaluates derivatives of the smoothness selection scores of the model with respect to the log smoothing parameters. Calculation of exact derivatives is generally faster than approximating them by finite differencing, as well as generally improving the reliability of GCV/UBRE/AIC/REML score minimization.
这个例程估计的GAM（任何二次处罚的GLM）给定的日志平滑paramaters，平滑参数的日志和评估衍生工具的平滑的模型选择分数。计算精确的衍生物，是一般的速度比有限差分逼近，以及普遍提高的GCV / UBRE的/工商局/ REML法得分最小的可靠性。
The approach is to run the P-IRLS to convergence, and only then to iterate for first and second derivatives.
方法是运行的P-IRLS收敛，然后重复第一和第二衍生物。
Not normally called directly, but rather service routines for gam.
通常不直接调用，但gam而服务程序。
用法----------Usage----------
gam.fit3(x, y, sp, Eb ,UrS=list(),
weights = rep(1, nobs), start = NULL, etastart = NULL,
mustart = NULL, offset = rep(0, nobs), U1 = diag(ncol(x)),
Mp = -1, family = gaussian(), control = gam.control(),
intercept = TRUE,deriv=2,gamma=1,scale=1,
printWarn=TRUE,scoreType="REML",null.coef=rep(0,ncol(x)),
pearson.extra=0,dev.extra=0,n.true=-1,...)
参数----------Arguments----------
参数：x
The model matrix for the GAM (or any penalized GLM).
在GAM模型矩阵（或任何处罚的GLM）。
参数：y
The response variable.
响应变量。
参数：sp
The log smoothing parameters.
日志平滑参数。
参数：Eb
A balanced version of the total penalty matrix: usd for numerical rank determination.
一个平衡的总罚矩阵版本：美元的数值秩的决心。
参数：UrS
List of square root penalties premultiplied by transpose of orthogonal basis for the total penalty.
平方根处罚，罚款总额为正交基转左乘名单。
参数：weights
prior weights for fitting.
装修前的重量。
参数：start
optional starting parameter guesses.
可选的启动参数的猜测。
参数：etastart
optional starting values for the linear predictor.
可选的初始值的线性预测。
参数：mustart
optional starting values for the mean.
可选的起始值的意思。
参数：offset
the model offset
模型偏移
参数：U1
An orthogonal basis for the range space of the penalty — required for ML smoothness estimation only.
罚款的范围空间的正交基 - 仅ML平滑估计所需。
参数：Mp
The dimension of the total penalty null space — required for ML smoothness estimation only.
对总罚款空空间的维度 - 需要只有ML平滑估计。
参数：family
the family - actually this routine would never be called with gaussian()
家庭 - 其实这个例程将永远不会被调用gaussian()
参数：control
control list as returned from glm.control
从glm.control控制列表返回
参数：intercept
does the model have and intercept, TRUE or FALSE
有模型和拦截，TRUE或FALSE
参数：deriv
Should derivatives of the GCV and UBRE/AIC scores be calculated? 0, 1 or 2, indicating the maximum order of differentiation to apply.
衍生物的GCV和UBRE的/ AIC的分数如何计算？ 0，1或2，说明分化申请的最大订单。
参数：gamma
The weight given to each degree of freedom in the GCV and UBRE scores can be varied (usually increased) using this parameter.
给每个在GCV和UBRE的分数的自由程度的体重可以是多种多样的（通常是增加），使用此参数。
参数：scale
The scale parameter - needed for the UBRE/AIC score.
尺度参数 - 需要的UBRE / AIC的得分。
参数：printWarn
Set to FALSE to suppress some warnings. Useful in order to ensure that some warnings are only printed if they apply to the final fitted model, rather than an intermediate used in optimization.
设置FALSE压制一些警告。有用的，以确保只印一些警告，如果他们申请到最终的拟合模型，而不是用于在优化中间，。
参数：scoreType
specifies smoothing parameter selection criterion to use.
指定平滑参数的选择标准使用。
参数：null.coef
coefficients for a model which gives some sort of upper bound on deviance. This allows immediate divergence problems to be controlled.
系数为模型，给出了一些排序上的偏差上限。这种允许立即分歧问题进行控制。
参数：pearson.extra
Extra component to add to numerator of pearson statistic in P-REML/P-ML smoothness selection criteria.
额外的组件添加到分子皮尔逊统计在P-REML/P-ML平整度的选择标准。
参数：dev.extra
Extra component to add to deviance for REML/ML type smoothness selection criteria.
额外的组件添加到REML法/ ML型平滑的选择标准的偏差。
参数：n.true
Number of data to assume in smoothness selection criteria. <=0 indicates that it should be the number of rows of X.
数的数据假设在光滑的选择标准。 <= 0表示，它应该是X行的数目。
参数：...
Other arguments: ignored.
其他参数：被忽略。
Details
详情----------Details----------
This routine is basically glm.fit with some modifications to allow (i) for quadratic penalties on the log likelihood; (ii) derivatives of the model coefficients with respect to log smoothing parameters to be obtained by use of the implicit function theorem and (iii) derivatives of the GAM GCV, UBRE/AIC, REML or ML scores to be evaluated at convergence.
这个例程基本上是glm.fit允许一些修改（一）对数似然二次处罚;（ii）衍生工具方面的模型系数登录平滑参数的获取和利用隐函数定理（三）衍生工具被GCV的“自由亚齐运动，UBRE /工商局，REML法或ML分数评价收敛。
In addition the routines apply step halving to any step that increases the penalized deviance substantially.
此外，例程申请步骤减半任何步骤，大大增加了处罚的偏差。
The most costly parts of the calculations are performed by calls to compiled C code (which in turn calls LAPACK routines) in place of the compiled code that would usually perform least squares estimation on the working model in the IRLS iteration.
计算的最昂贵的部分进行编译的C代码编译的代码，通常会执行工作模型在IRLS迭代的最小二乘估计的地方（这反过来又调用LAPACK例程）调用。
Estimation of smoothing parameters by optimizing GCV scores obtained at convergence of the P-IRLS iteration was proposed by O'Sullivan et al. (1986), and is here termed "outer" iteration.
奥沙利文等人提出了优化GCV的成绩获得的P-IRLS迭代收敛，平滑参数的估计。 （1986年），这里被称为“外”的迭代。
Note that use of non-standard families with this routine requires modification of the families as described in fix.family.link.
请注意这个例程，非标准家庭的使用需要修改的家庭，在fix.family.link。
作者（S）----------Author(s)----------
Simon N. Wood <a href="mailto:simon.wood@r-project.org">simon.wood@r-project.org</a>
The routine has been modified from <code>glm.fit</code> in R 2.0.1, written
by the R core (see <code><a href="../../mgcv/help/glm.fit">glm.fit</a></code> for further credits).
参考文献----------References----------
and marginal likelihood estimation of semiparametric generalized linear models. Journal of the Royal Statistical Society (B) 73(1):3-36
functions in generalized linear models. J. Amer. Statist. Assoc. 81:96-103.
参见----------See Also----------
gam.fit, gam, mgcv, magic
gam.fit，gam，mgcv，magic
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 2012-2-16 20:27:09
