找回密码
 注册
查看: 1126|回复: 0

R语言 spdep包 sacsarlm()函数中文帮助文档(中英文对照)

[复制链接]
发表于 2012-9-30 14:44:23 | 显示全部楼层 |阅读模式
sacsarlm(spdep)
sacsarlm()所属R语言包:spdep

                                        Spatial simultaneous autoregressive SAC model estimation
                                         空间的同时自回归SAC模型估计

                                         译者:生物统计家园网 机器人LoveR

描述----------Description----------

Maximum likelihood estimation of spatial simultaneous autoregressive “SAC/SARAR” models of the form:
最大似然估计的空间同时自回归“SAC /萨拉尔”模型的形式:

where rho and lambda are found by nlminb or optim() first, and beta and other parameters by generalized least squares subsequently
rho和随后lambdanlminb或optim()第一,和beta和其他参数的广义最小二乘


用法----------Usage----------


sacsarlm(formula, data = list(), listw, listw2 = NULL, na.action, type="sac",
method = "eigen", quiet = NULL, zero.policy = NULL, tol.solve = 1e-10,
llprof=NULL, control = list())



参数----------Arguments----------

参数:formula
a symbolic description of the model to be fit. The details  of model specification are given for lm()
一个象征性的模型来描述是合适的。型号规格的细节给予lm()


参数:data
an optional data frame containing the variables in the model.  By default the variables are taken from the environment which the function  is called
一个可选的数据框包含在模型中的变量。默认情况下,变量取自该函数被调用时的环境


参数:listw
a listw object created for example by nb2listw
例如创建一个listw对象的nb2listw


参数:listw2
a listw object created for example by nb2listw, if not given, set to the same spatial weights as the listw argument
一个listwnb2listw创建的对象,例如,如果没有给出,设置为相同的空间权重的listw参数


参数:na.action
a function (default options("na.action")), can also be na.omit or na.exclude with consequences for residuals and fitted values - in these cases the weights list will be subsetted to remove NAs in the data. It may be necessary to set zero.policy to TRUE because this subsetting may create no-neighbour observations. Note that only weights lists created without using the glist argument to nb2listw may be subsetted.
一个函数(默认options("na.action")),也可以是na.omit或na.exclude残差和拟合值与后果 - 在这些情况下,将子集的权重列表中删除NAS的数据。这可能是必要的设置为TRUE zero.policy子集,因为这可能创建没有邻居观测。需要注意的是只重列表创建时没有使用的glist的参数nb2listw可能是子集。


参数:type
default "sac", may be set to "sacmixed" for the Manski model to include the spatially lagged independent variables added to X using listw; when "sacmixed", the lagged intercept is dropped for spatial weights style "W", that is row-standardised weights, but otherwise included
默认的“囊”,可以被设置为“sacmixed”为Manski模型包括的空间滞后独立变量附加到X使用listw;当“sacmixed”,滞后的截距下降空间权重风格“W”,即行标准化的权重,但包括在其他


参数:method
"eigen" (default) - the Jacobian is computed as the product  of (1 - rho*eigenvalue) using eigenw, and "spam" or "Matrix" for strictly symmetric weights lists of styles "B" and "C", or made symmetric by similarity (Ord, 1975, Appendix C) if possible for styles "W" and "S", using code from the spam or Matrix packages to calculate the determinant; "LU" provides an alternative sparse matrix decomposition approach. In addition, there are "Chebyshev" and Monte Carlo "MC" approximate log-determinant methods.
“本征”(默认) - 雅可比计算的产品(1  -  RHO *特征值)eigenw“和”垃圾邮件“或”黑客帝国“的严格对称的权重列表样式”B“和“C”,或对称的相似性风格“W”和“S”,使用代码包的垃圾邮件或矩阵计算行列式(条例“,1975年,附录C)如果可能的话,”LU“提供了另一种稀疏矩阵分解的方法。此外,还有“切比雪夫”蒙地卡罗“MC”近似数行列式的方法。


参数:quiet
default NULL, use !verbose global option value; if FALSE, reports function values during optimization.
默认为空!详细,使用全局选项值报告;如果为FALSE,函数值在优化过程中。


参数:zero.policy
default NULL, use global option value; if TRUE assign zero to the lagged value of zones without  neighbours, if FALSE (default) assign NA - causing sacsarlm() to terminate with an error
默认为空,请使用全局选项的值,如果是TRUE分配了零的滞后值的区域没有邻居,如果为FALSE(默认值)指定NA  - 导致sacsarlm()终止错误


参数:tol.solve
the tolerance for detecting linear dependencies in the columns of matrices to be inverted - passed to solve() (default=1.0e-10). This may be used if necessary to extract coefficient standard errors (for instance lowering to 1e-12), but errors in solve() may constitute indications of poorly scaled variables: if the variables have scales differing much from the autoregressive coefficient, the values in this matrix may be very different in scale, and inverting such a matrix is analytically possible by definition, but numerically unstable; rescaling the RHS variables alleviates this better than setting tol.solve to a very small value
检测线性依赖关系被倒置的矩阵中的列 - 通过solve()(默认= 1.0E-10)的公差。这可以用来如果要提取的系数的标准误差(例如降低到1e-12),但错误在solve()可能构成缩放差变量的指示:如果变量多不同的尺度从自回归系数,此矩阵中的值可能是非常不同的规模,和反相这样一个矩阵分析可以通过定义,但数值不稳定;重新缩放的RHS变量缓解这一优于设置tol.solve到一个非常小的值


参数:llprof
default NULL, can either be an integer, to divide the feasible ranges into a grid of points, or a two-column matrix of spatial coefficient values, at which to evaluate the likelihood function
默认为NULL,既可以是一个整数,可行范围划分成网格,点,或一个两列的矩阵的空间系数的值,在其中计算的似然函数的


参数:control
list of extra control arguments - see section below
额外的控制参数列表 - 见下文


Details

详细信息----------Details----------

Because numerical optimisation is used to find the values of lambda and rho, care needs to be shown. It has been found that the surface of the 2D likelihood function often forms a “banana trench” from (low rho, high lambda) through (high rho, high lambda) to (high rho, low lambda) values. In addition, sometimes the banana has optima towards both ends, one local, the other global, and conseqently the choice of the starting point for the final optimization becomes crucial. The default approach is not to use just (0, 0) as a starting point, nor the (rho, lambda) values from gstsls, which lie in a central part of the “trench”, but either four values at (low rho, high lambda), (0, 0), (high rho, high lambda), and (high rho, low lambda), and to use the best of these start points for the final optimization. Optionally, nine points can be used spanning the whole (lower, upper) space.
由于数值优化的lambda和Rho值是用来寻找,护理需要显示的。业已发现,通常的2D的似然函数的表面形成“香蕉沟槽”(低rho沸石,高λ)通过(高rho沸石,高拉姆达)(高rho沸石,低λ)值。另外,有时香蕉具有最优向两端,一个地方,其他全球,conseqently选择最终优化的起点变得至关重要。默认的方法是不使用(0,0)为出发点,也gstsls,位于中央部分的“沟”,但无论是四个值(ρ,λ)值(低rho沸石,高λ),(0,0),(高rho沸石,高拉姆达),和(高rho沸石,低拉姆达),和使用的最佳的最终优化这些开始点。任选地,可以使用九个点跨越整个(低级,上层)的空间。


值----------Value----------

A list object of class sarlm
一个List对象的类sarlm


参数:type
“sac”
“SAC”


参数:rho
lag simultaneous autoregressive lag coefficient
落后同时自回归滞后系数


参数:lambda
error simultaneous autoregressive error coefficient
错误,同时自回归误差系数


参数:coefficients
GLS coefficient estimates
GLS估计系数


参数:rest.se
asymptotic standard errors if ase=TRUE, otherwise approximate numeriacal Hessian-based values
如果ASE = TRUE,否则近似numeriacal的黑森州基于值的渐近标准误差


参数:ase
TRUE if method=eigen
TRUE如果方法特征


参数:LL
log likelihood value at computed optimum
对数似然值计算最佳


参数:s2
GLS residual variance
GLS剩余方差


参数:SSE
sum of squared GLS errors
总和平方GLS错误的


参数:parameters
number of parameters estimated
估计的参数的数量


参数:logLik_lm.model
Log likelihood of the non-spatial linear model
对数似然的非空间的线性模型


参数:AIC_lm.model
AIC of the non-spatial linear model
AIC的非空间的线性模型


参数:method
the method used to calculate the Jacobian
所使用的方法来计算的雅可比


参数:call
the call used to create this object
用于创建此对象的调用


参数:residuals
GLS residuals
GLS残差


参数:tarX
model matrix of the GLS model
GLS模型的模型矩阵


参数:tary
response of the GLS model
GLS模型的响应


参数:y
response of the linear model for rho=0
响应的线性模型rho=0


参数:X
model matrix of the linear model for rho=0
模型矩阵的线性模型rho=0


参数:opt
object returned from numerical optimisation
返回的对象从数值优化


参数:pars
starting parameter values for final optimization, either given or found by trial point evaluation
开始的参数值进行最后的优化,无论是试点评估


参数:mxs
if default input pars, optimal objective function values at trial points
如果默认输入杆收杆,在试点的最优目标函数值


参数:fitted.values
Difference between residuals and response variable
残差和响应变量之间的差异


参数:se.fit
Not used yet
尚未使用


参数:rho.se
if ase=TRUE, the asymptotic standard error of rho, otherwise approximate numeriacal Hessian-based value
如果ASE = TRUE,rho,否则近似numeriacal的黑森州基于价值的渐近标准误差


参数:lambda.se
if ase=TRUE, the asymptotic standard error of lambda
如果ASE = TRUE,渐近标准误差lambda


参数:resvar
the asymptotic coefficient covariance matrix for (s2, rho, lambda, B)
的渐近协方差系数矩阵(S2,ρ,λ,B)


参数:zero.policy
zero.policy for this model
zero.policy此模型


参数:aliased
the aliased explanatory variables (if any)
别名解释性变量(如果有的话)


参数:LLNullLlm
Log-likelihood of the null linear model
空的线性模型的对数似然


参数:fdHess
the numerical Hessian-based coefficient covariance matrix for (rho, B) if computed
Hessian的基于系数的数值协方差矩阵(卢,B)如果计算


参数:resvar

参数:optimHess
if TRUE and fdHess returned, optim used to calculate Hessian at optimum
如果返回TRUE和fdHess,optim用于计算黑森州在最佳


参数:timings
processing timings
处理时序


参数:na.action
(possibly) named vector of excluded or omitted observations if non-default na.action argument used
(可能)命名为向量的排除或省略的观察,如果使用非默认na.action参数


控制参数----------Control arguments----------




fdHess: default NULL, then set to (method != "eigen") internally; use fdHess to compute an approximate Hessian using finite differences when using sparse matrix methods; used to make a coefficient covariance matrix when the number of observations is large; may be turned off to save resources if need be
(方法=“特征”)fdHess:默认为空,则设置为内部,使用fdHess计算近似Hessian的使用稀疏矩阵的方法用有限差分时,使用系数协方差矩阵的当数观察大;可能会被关闭,以节约资源,如果需要的话




optimHess: default FALSE, use fdHess from nlme, if TRUE, use optim to calculate Hessian at optimum
optimHess:默认为false,使用fdHessnlme,如果为TRUE,使用optim来计算黑森州在最佳




LAPACK: default FALSE; logical value passed to qr in the SSE log likelihood function
LAPACK:默认为false;逻辑值传递给qr在上证所数似然函数




Imult: default 2; used for preparing the Cholesky decompositions for updating in the Jacobian function
IMULT:默认的Cholesky分解更新的雅可比函数准备




super: default FALSE using a simplicial decomposition for the sparse Cholesky decomposition, if TRUE, use a supernodal decomposition
超:默认为false的单纯分解为稀疏Cholesky分解,若为TRUE,使用一个supernodal的的分解




cheb_q: default 5; highest power of the approximating polynomial for the Chebyshev approximation
cheb_q 5:默认情况下,最高功率近似多项式的切比雪夫逼近




MC_p: default 16; number of random variates
mc_P的:默认16号的随机变数




MC_m: default 30; number of products of random variates matrix and spatial weights matrix
MC_m:默认为30;随机变数矩阵和空间权重矩阵的产品




opt_method: default “nlminb”, may be set to “L-BFGS-B” to use box-constrained optimisation in optim
opt_method“:默认的”nlminb“,可以设置为”L-BFGS-B“使用箱约束优化optim




opt_control: default list(), a control list to pass to nlminb or optim
opt_control:默认list(),控制列表,通过nlminb或optim




pars: default NULL, for which five trial starting values spanning the lower/upper range are tried and the best selected, starting values of rho and lambda
标准杆:默认NULL,五审判开始跨越低/高范围值都试过的最佳选择,初始值rho和lambda




npars default integer 4L, four trial points; if not default value, nine trial points
硬件分区默认的整数4L,4个试验点;如果不是默认值,9个试验点




lower: default c(-1.0, -1.0), lower bounds on rho and lambda
低:默认c(-1.0, -1.0),下限rho和lambda




upper: default c(1.0, 1.0), upper bounds on rho and lambda
上:默认c(1.0, 1.0),上限rho和lambda


(作者)----------Author(s)----------


Roger Bivand <a href="mailto:Roger.Bivand@nhh.no">Roger.Bivand@nhh.no</a>



参考文献----------References----------



参见----------See Also----------

help,
help,


实例----------Examples----------


data(oldcol)
COL.sacW.eig <- sacsarlm(CRIME ~ INC + HOVAL, data=COL.OLD,
nb2listw(COL.nb, style="W"))
summary(COL.sacW.eig, correlation=TRUE)
W <- as(as_dgRMatrix_listw(nb2listw(COL.nb, style="W")), "CsparseMatrix")
trMatc <- trW(W, type="mult")
summary(impacts(COL.sacW.eig, tr=trMatc, R=2000), zstats=TRUE, short=TRUE)
COL.msacW.eig <- sacsarlm(CRIME ~ INC + HOVAL, data=COL.OLD,
nb2listw(COL.nb, style="W"), type="sacmixed")
summary(COL.msacW.eig, correlation=TRUE)
summary(impacts(COL.msacW.eig, tr=trMatc, R=2000), zstats=TRUE, short=TRUE)

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。
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 注册

本版积分规则

手机版|小黑屋|生物统计家园 网站价格

GMT+8, 2025-6-18 06:27 , Processed in 0.025232 second(s), 16 queries .

Powered by Discuz! X3.5

© 2001-2024 Discuz! Team.

快速回复 返回顶部 返回列表