summaryGOF(semGOF)
summaryGOF()所属R语言包：semGOF
Goodness-of-Fit indexes in structural equation models for sem
善良的SEM结构方程模型的拟合指数
译者：生物统计家园网 机器人LoveR
描述----------Description----------
summaryGOF computes fourteen Goodness–of–Fit indexes in addiction to the output of sem (Fox, Byrnes, Culbertson, Friendly, Kramer & Monette; 2011).
summaryGOF计算14善良的拟合指数上瘾的输出sem（福克斯，伯恩斯，卡伯特森，友好，克莱默和Monette; 2011）。
用法----------Usage----------
summaryGOF(object, digits = 5, ...)
参数----------Arguments----------
参数：object
an object of class sem returned by the sem function (see Examples below).
扫描电镜的类的对象返回sem功能（见下面的例子）。
参数：digits
number of digits for printed output.
用于印刷输出的数字数。
参数：...
additional arguments affecting the summary produced (see summary).
额外的参数摘要（见summary“）。
Details
详细信息----------Details----------
The goodness of fit indexes calculated in semGOF:
善良的拟合指数计算semGOF：
ICOMP Information Complexity (Bozdogan, 1990)
的ICOMP信息复杂（Bozdogan，1990）
Fml Fit Function of maximum likelihood (Long, 1986).
FML拟合函数的最大似然（长，1986年）。
d Estimate of minimized population discrepancy function (McDonald, 1989).
ð估计人口差异最小化功能（麦当劳，1989年）。
Mc McDonald's Centrality Index (McDonald, 1989).
MC麦当劳掌的指数（麦当劳，1989年）。
RNI Relative Noncentrality Index (Bentler, 1990).
RNI的相对非中心指数（特勒，1990年）。
IFI Incremental Fit Index (Bollen, 1989).
IFI增量拟合指数（博伦，1989年）。
chisq.df Chi-square/df ratio (Marsh & al., 1988).
chisq.df Chi-square/df比率（沼泽＆人，1988）。
CAK Rescaled version of AIC (Cudeck and Browne, 1983).
CAK重新调整的AIC（Cudeck和布朗，1983）版本。
CSK Information Criterion (Schwartz, 1978).
的CSK信息标准（施瓦茨，1978）。
CN Critical N (Hoelter, 1983), (Hu & Bentler, 1999).
CN临界氮（Hoelter，1983），（胡特勒，1999年）。
Gamma.hat Gamma hat (Steiger, 1989), (Hu & Bentler, 1999).
Gamma.hat伽玛帽子（斯泰格尔，1989），（胡特勒，1999年）。
BL86 Bollen's Fit Index (Bollen, 1986).
BL86博伦的拟合指数（博伦，1986年）。
W Wheaton Index (Wheaton et al., 1977).
W威敦指数（Wheaton等人，1977年）。
ECVI Expected Cross Validation Index (Browne & Cudeck, 1992).
ECVI预期交叉验证指数（布朗＆Cudeck的，1992年）。
警告----------Warning ----------
semGOF must be used with sem.
semGOF，必须使用sem。
（作者）----------Author(s)----------
Bertossi Elena <a href="mailto:bertossielena@gmail.com">bertossielena@gmail.com</a>
参考文献----------References----------
Comparative fit indexes in structural equation models. Psychological Bulletin 107:238–246.
Sample size and Bentler and Bonnett's nonnormed fit index. Psychometrika 51:375–377.
A new incremental fit index for general structural equation models. Sociological Methods and Research 17:303–316.
Akaike's criterion and recent developments in information complexity. Journal of Mathematical Psychology 44:62–91.
Alternative ways of assessing model fit. Sociological Methods and Research 21:230–258.
Cross–validation of covariance structure. Multivariate Behavioral Research 18:147–167.
Michael Friendly, Adam Kramer and Georges Monette. (2011) sem: Structural Equation Models. R package version 2.1-1. http://CRAN.R-project.org/package=sem
Structural equation modeling with the sem package in R. Structural equation modeling 13:465–486.
The analysis of covariance structure: goodness of fit indexes. Sociological Methods and Research 11:325–344.
Cutoff criteria for fit indexes in covariance structure analysis: conventional criteria versus new alternatives. Stuctural equation modeling 6:1–55.
Confirmatory Factor Analysis. California, SAGE.
Goodness–of–fit in confirmatory factor analysis: the effect of sample size. Psychological Bulletin 3:391–410.
An index of goodeness of fit based on noncentrality. Journal of Classification 6:97–103.
Estimating the dimantion of the model. Annals of Statistics 6:461–464.
Modern Applied Statistics with S. Fourth Edition. Springer, New York. ISBN 0-387-95457-0.
Assessing reliability and stability in panel models. Sociological Methodology 8:84–136.
参见----------See Also----------
sem
sem
实例----------Examples----------
# The following model has been created with[下面的模型已创建]
# six observed endogenous variables, [六个观测到的内生变量，]
# two unobserved endogenous variables and[未观测到的内生变量和]
# four unobserved exogenous variables.[4个不可观测的外生变量。]
S <- matrix(c(
1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0,
0.6321, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0,
0.5932, 0.5881, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0,
0.0965, 0.0987, 0.1564, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0,
0.1785, 0.1256, 0.1124, 0.4567, 1.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0,
0.2135, 0.2003, 0.0762, 0.5589, 0.6097, 1.0000, 0.0000, 0.0000, 0.0000, 0,
0.3875, 0.4011, 0.3211, 0.0134, 0.0189, 0.0556, 1.0000, 0.0000, 0.0000, 0,
0.3569, 0.3989, 0.3301, 0.1323, 0.1036, 0.1132, 0.3215, 1.0000, 0.0000, 0,
0.1034, 0.1201, 0.1010, 0.2981, 0.3265, 0.2920, 0.1092, 0.0981, 1.0000, 0,
0.1324, 0.0622, 0.0123, 0.3056, 0.3525, 0.2661, 0.1234, 0.1207, 0.2221, 1
), ncol=10, byrow=TRUE)
rownames(S) <- c("Y1", "Y2", "Y3", "Y4", "Y5", "Y6",
"CSI1", "CSI2", "CSI3", "CSI4")
colnames(S) <- c("Y1", "Y2", "Y3", "Y4", "Y5", "Y6",
"CSI1", "CSI2", "CSI3", "CSI4")
ram.I <- matrix(c(
# heads to from param start[头从参数开始]
1, 1, 11, 1, NA, # lam1[lam1]
1, 2, 11, 0, 0.750,
1, 3, 11, 2, NA, # lam2[lam2]
1, 4, 12, 3, NA, # lam3[LAM3]
1, 5, 12, 4, NA, # lam4[lam4]
1, 6, 12, 0, 0.800,
1, 11, 7, 5, NA, # gam1[gam1]
1, 11, 8, 6, NA, # gam2[gam2]
1, 12, 9, 7, NA, # gam3[gam3]
1, 12, 10, 8, NA, # gam4[gam4]
2, 1, 1, 9, NA, # theta1[THETA1]
2, 2, 2, 10, NA, # theta2[theta2]
2, 3, 3, 11, NA, # theta3[theta3]
2, 4, 4, 12, NA, # theta4[theta4]
2, 5, 5, 13, NA, # theta5[theta5]
2, 6, 6, 14, NA, # theta6[theta6]
2, 11, 11, 15, NA, # psi1[PSI1]
2, 12, 12, 16, NA # psi2[PSI2]
), ncol=5, byrow=TRUE)
params.I <- c('lam1', 'lam2', 'lam3', 'lam4', 'gam1', 'gam2',
'gam3', 'gam4', 'theta1', 'theta2', 'theta3',
'theta4', 'theta5', 'theta6', 'psi1', 'psi2')
vars.I <- c('Y1', 'Y2', 'Y3', 'Y4', 'Y5', 'Y6', 'CSI1',
'CSI2', 'CSI3', 'CSI4', 'ETA1', 'ETA2')
sem.I <- sem(ram.I, S, 250, param.names=params.I,
var.names=vars.I, fixed.x=7:10)
summaryGOF(sem.I)
# Goodness-of-Fit indexes of structural equation models for 'sem' package[善良的结构方程模型的拟合指数的“SEM”]
# ICOMP = -14.964[ICOMP = -14.964]
# Fml = 0.19582[FML = 0.19582]
# RNI = 0.97065[RNI = 0.97065]
# IFI = 0.97133[IFI = 0.97133]
# chisq.df = 1.6814[chisq.df = 1.6814]
# CN = 231.91[CN = 231.91]
# Gamma.hat = 0.98438[Gamma.hat = 0.98438]
# BL86 = 0.89465[BL86 = 0.89465]
# W = 1.6814[W = 1.6814]
# d = 0.079042[D = 0.079042]
# Mc = 0.96125[MC = 0.96125]
# CAK = 0.27582[CAK = 0.27582]
# CSK = 0.41668[CSK = 0.41668]
# ECVI = 0.40466 [ECVI = 0.40466]
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 00:33:30
