【文件】SPSS专用统计术语
- 1、下载文档前请自行甄别文档内容的完整性,平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益,请联系客服反馈,我们会尽快为您处理(人工客服工作时间:9:00-18:30)。
【关键字】文件
SPSS专用统计术语
1、X2/df x2(卡方检验)检验方法和分解融合(DF)方法
x2值(Chi-Square)为22.4601,自由度(chi-square df)为4,P值(Pr>Chi-Square)为0.0002
2、RMR LISREL、AMOS等结构方程模型分析软件,为什么我的Amos输出中找不到RMR和GFI这一项内容。
(1)间距参数RSm与混合参数Rmr(c)称为附加参数
(2)表示残差均方根,残差是指样本导出的方差协方差矩阵与模型隐含的方差协方差矩阵中对应元素的差值,RMR的值越小,模型拟合越好。
从你的图片看,你的模型拟合度不好。
Amos does not report GFI, PGFI, AGFI and RMR when you estimate means and intercepts. This is because it is not clear how to incorporate means and intercepts into the conventional formulas for these statistics. One possibility is to calculate these statistics based on the observed variances/covariances and the fitted (implied) variances/covariances, leaving the means and intercepts out of the fit measure. That way of computing the statistics could be useful and is certainly defensible. It would make a great deal of sense in those models where means and intercepts are estimated but not constrained. On the other hand, for models that constrain means and intercepts it is important to pay attention to how well the model reproduces the means and intercepts, as well as the variances/covariances.
Another approach would be to generalize the definitions of those statistics to somehow incorporate failure to fit means and intercepts. So far, a unique, obviously correct, way of doing this has not been proposed.
For these reasons, the design decision was made not to report GFI, PGFI, AGFI and RMR when means and intercepts are estimated.
回头去看你的“View”里的“Analysis Properties”,“Estimates means and intercepets”是被选中了的,把那个复选框去掉后,报表里就有RMR和GFI等指数啦。
3、NFI(1)神经纤维指数;(2)Normed Fit Index,正规指数,越接近于1,说明拟合越好。
本特勒―波内特规范拟合指数(NFI);(3)Normed Fit Index,正规拟合指数
4、RMSEA 近似误差均方根,root mean square error of approximation,衡量模型协方差与数据协方差阵的差异大小,RMSFA越小越好。
5、GFI 拟合优度指数goodness of fit index
6、RFI 相对拟合指数,(1)renal function index肾功能指数(2)Relative Fit Index
7、NNFI 非本特内-范内特规范拟合指数,
8、IFI Incremental Fit Index,增量拟合指数
9、AGFI adjusted GFI,调整拟合优度指数
10、TLI Tucker-Lewis Index指数,TLI 可能大于1 或者小于1,但一般在0~1 之间,越接近1 模型越理想。
11、CFI Comparative Fit Index,比较拟合指数
The confirmatory fator analysis showed that the fit indexes for
χ~2/df=3.622,GFI=0.92,AGFI=0.91,NFI=0.89,NNFI=0.90,RMSEA=0.069,CFI=0.90,IFI= for high goals had no significant correlations with SCL-90、SDS、SAS and SWLS,but with SES (r=0.241,P<0.01).
验证性因素分析显示拟合指数
χ2/df=3.622,GFI=0.92,AGFI=0.91,NFI=0.87,NNFI=0.90,RMSEA=0.069,CFI=0.90,IFI=0.90。
追求高标准与SCL-90、SDS、SAS和SWLS等效标不相关,与SES的相关为0.241(P<0.01);
信息标准指数ISI 完全标准化解(MI)
相对拟合指数(RFI)大于0.90,近似均方根残差(RMSEA)小于0.08,则模型与数据的拟合程度很好。
非范拟合指数(NNFI)为0.93,近似均方根误差(RMSEA)为0.079。
12个分测验的完全标准化解(MI)分别为
与自由度df之比、近似误差均方根(RMSEA)、拟合优度指数(goodness of fit index,GFI)
本特勒―波内特规范拟合指数(NFI)、近似误差平方根(RMSEA)和信息标准指数等。
可根据用于验证的数据特征
1.
2009年7月7日... 7 • • goodness of fit index NNFI CFI • df=[ , p(p+1)/2] .... (CFI) = 0.95 Incremental Fit Index (IFI) = 0.95 Relative Fit Index (RFI) = 0.88 ...
运行lisrel会产生一个GF文件,就是模型拟合指目标文件,内容如下(文件中是居中设置的):Degrees of Freedom = 35
Minimum Fit Function Chi-Square = 47.95 (P = 0.071)
Normal Theory Weighted Least Squares Chi-Square = 47.07 (P = 0.083)
Estimated Non-centrality Parameter (NCP) = 12.07
90 Percent Confidence Interval for NCP = (0.0 ; 34.10)
Minimum Fit Function Value = 0.048
Population Discrepancy Function Value (F0) = 0.012
90 Percent Confidence Interval for F0 = (0.0 ; 0.034)
Root Mean Square Error of Approximation (RMSEA) = 0.019
90 Percent Confidence Interval for RMSEA = (0.0 ; 0.031)
P-Value for Test of Close Fit (RMSEA < 0.05) = 1.00
Expected Cross-Validation Index (ECVI) = 0.087
90 Percent Confidence Interval for ECVI = (0.075 ; 0.11)
ECVI for Saturated Model = 0.11
ECVI for Independence Model = 1.87
Chi-Square for Independence Model with 45 Degrees of Freedom = 1843.25
Independence AIC = 1863.25
Model AIC = 87.07
Saturated AIC = 110.00
Independence CAIC = 1922.33
Model CAIC = 205.23
Saturated CAIC = 434.93
Normed Fit Index (NFI) = 0.97
Non-Normed Fit Index (NNFI) = 0.99
Parsimony Normed Fit Index (PNFI) = 0.76
Comparative Fit Index (CFI) = 0.99
Incremental Fit Index (IFI) = 0.99
Relative Fit Index (RFI) = 0.97
Critical N (CN) = 1195.65
Root Mean Square Residual (RMR) = 0.049
Standardized RMR = 0.021
Goodness of Fit Index (GFI) = 0.99
Adjusted Goodness of Fit Index (AGFI) = 0.99
Parsimony Goodness of Fit Index (PGFI) = 0.63
我现在想要做的是从多个这样的文件中抽取特定的拟合指目标值另存为一个txt文件,并于首行指明拟合指目标名称?在R在能否实现呢?该如何操作?
能。
因为这个文件的规律很明确。
用readLines()读进来,用split()拆分'=',用as.numeric()转成数值。
细节我就不说了,里面有几行和其它行的规律不完全一样。
用两行文本举个例子吧,比如我现在读了两行文本放在x中:
> x
[1] " P-Value for Test of Close Fit (RMSEA < 0.05) = 1.00"
[2] " Expected Cross-Validation Index (ECVI) = 0.087"
用'='为拆分符号把x拆掉:
> strsplit(x,'=')
[[1]]
[1] " P-Value for Test of Close Fit (RMSEA < 0.05) "
[2] " 1.00"
[[2]]
[1] " Expected Cross-Validation Index (ECVI) "
[2] " 0.087"
每个子对象的第二个就是你要的东西(用as.numeric()转换一下)。
其中不一样的那两行
再次使用strsplit命令这样就可以分开数字了
最后可以将需要的列表读出,将其中的数字分别转换为字符
不过现在遇到这么个问题
因为我有多个这样读取的数据,格式都是一样的:第一行为变量名,第二行为相应的数值
但是因为分别存在不同的txt文件中
不知道到如何能将其合并为一个文件
此文档是由网络收集并进行重新排版整理.word可编辑版本!。