> library(psych)
> library(broom)
> library(tidyr)
> ex8_7=read.csv("/Users/y/Desktop/R/R87.csv")
> ex8_7
x1 x2 x3 x4 x5
1 75.20 0.140 1.86 0.91 5.21
2 75.15 0.160 2.11 0.74 4.93
3 72.19 0.130 1.52 0.69 4.65
4 72.35 0.130 1.37 0.83 4.87
5 72.74 0.100 1.41 0.72 4.99
6 73.29 0.033 1.07 0.17 3.15
7 73.72 0.033 0.77 0.28 2.78
> #评估数据是否适合做因子分析
> KMO(ex8_7)
Kaiser-Meyer-Olkin factor adequacy
Call: KMO(r = ex8_7)
Overall MSA = 0.35
MSA for each item =
x1 x2 x3 x4 x5
0.09 0.40 0.38 0.38 0.39
> #结果Overall MSA = 0.35,小于0.5,不太适合做因子分析
> #bartlett检验
> #H0:原始变量的相关系数矩阵是单位矩阵
> cortest.bartlett(ex8_7)
R was not square, finding R from data
$chisq
[1] 38.01037
$p.value
[1] 3.779435e-05
$df
[1] 10
> #从结果p值很小很小,显然可以拒绝原假设
>
>
> #碎石图,确定因子个数
> par(family='STKaiti')#显示中文
> scree(ex8_7,factors = FALSE)
> #因子个数取2,图在下面
>
>
> #估计因子载荷
> #principal() 主成分法估计因子载荷
>
> #不旋转
> pri_ex8_7=principal(ex8_7,nfactors = 2,rotate = "none")
> pri_ex8_7
Principal Components Analysis
Call: principal(r = ex8_7, nfactors = 2, rotate = "none")
Standardized loadings (pattern matrix) based upon correlation matrix
PC1 PC2 h2 u2 com
x1 0.35 0.93 0.98 0.016 1.3
x2 0.98 -0.10 0.96 0.038 1.0
x3 0.94 0.24 0.94 0.061 1.1
x4 0.94 -0.23 0.94 0.062 1.1
x5 0.95 -0.24 0.97 0.029 1.1
PC1 PC2
SS loadings 3.75 1.04
Proportion Var 0.75 0.21
Cumulative Var 0.75 0.96
Proportion Explained 0.78 0.22
Cumulative Proportion 0.78 1.00
Mean item complexity = 1.1
Test of the hypothesis that 2 components are sufficient.
The root mean square of the residuals (RMSR) is 0.03
with the empirical chi square 0.11 with prob < 0.74
Fit based upon off diagonal values = 1>
> #用方差最大化旋转
> pri_varimax_ex8_7=principal(ex8_7,nfactors = 2,rotate = "varimax")
> pri_varimax_ex8_7
Principal Components Analysis
Call: principal(r = ex8_7, nfactors = 2, rotate = "varimax")
Standardized loadings (pattern matrix) based upon correlation matrix
RC1 RC2 h2 u2 com
x1 0.08 0.99 0.98 0.016 1.0
x2 0.96 0.18 0.96 0.038 1.1
x3 0.84 0.49 0.94 0.061 1.6
x4 0.97 0.03 0.94 0.062 1.0
x5 0.98 0.03 0.97 0.029 1.0
RC1 RC2
SS loadings 3.55 1.25
Proportion Var 0.71 0.25
Cumulative Var 0.71 0.96
Proportion Explained 0.74 0.26
Cumulative Proportion 0.74 1.00
Mean item complexity = 1.1
Test of the hypothesis that 2 components are sufficient.
The root mean square of the residuals (RMSR) is 0.03
with the empirical chi square 0.11 with prob < 0.74
Fit based upon off diagonal values = 1
PC1 PC2 h2 u2 com
x1 0.35 0.93 0.98 0.016 1.3
x2 0.98 -0.10 0.96 0.038 1.0
x3 0.94 0.24 0.94 0.061 1.1
x4 0.94 -0.23 0.94 0.062 1.1
x5 0.95 -0.24 0.97 0.029 1.1