PCA for oJoggle with Residual Scores

#Get rid of duplicated rows in data
#oJoggle1 = oJoggle[!duplicated(oJoggle$HNDid), ]
#save(oJoggle1,file='/Users/meganwilliams/Desktop/HANDLS/Joggle/Joggle PCA/oJoggle1.rdata')

Run PCA for oJoggle with Residual Scores

##Packages Used: “psych”, “GPArotation”, “nFactors”
load(file='/Users/meganwilliams/Desktop/HANDLS/Joggle/Joggle PCA/oJoggle1.rdata')

#install.packages("psych")
library("psych")
#install.packages("GPArotation")
library("GPArotation")
#install.packages("nFactors")
library("nFactors")

Initial Extraction of the Components

JogglePCA<-principal(oJoggle1,nfactors=8,rotate="none")
principal(r=oJoggle1,nfactors=8,rotate="none")
## Principal Components Analysis
## Call: principal(r = oJoggle1, nfactors = 8, rotate = "none")
## Standardized loadings (pattern matrix) based upon correlation matrix
##                  PC1   PC2   PC3   PC4   PC5   PC6   PC7   PC8 h2       u2
## residNBack      0.37  0.62 -0.08  0.13 -0.68 -0.01  0.00 -0.01  1  4.4e-16
## residBART       0.05 -0.20 -0.18  0.96  0.03  0.04  0.09 -0.04  1  1.2e-15
## residVOLT       0.67 -0.16  0.41 -0.08 -0.02  0.11  0.45 -0.37  1  1.0e-15
## residDSST      -0.10  0.68  0.51  0.21  0.42  0.20 -0.09  0.00  1 -6.7e-16
## residLOT        0.73 -0.01 -0.02  0.04  0.17 -0.37 -0.45 -0.30  1  7.8e-16
## residAM         0.61 -0.26  0.51  0.08 -0.09 -0.10 -0.06  0.52  1  1.2e-15
## oMPTspeed       0.64 -0.08 -0.35 -0.10  0.07  0.63 -0.20  0.05  1  2.2e-16
## oPVTefficiency  0.53  0.33 -0.49 -0.07  0.36 -0.24  0.35  0.22  1  1.9e-15
## 
##                        PC1  PC2  PC3  PC4  PC5  PC6  PC7  PC8
## SS loadings           2.20 1.10 1.09 1.00 0.81 0.66 0.59 0.54
## Proportion Var        0.28 0.14 0.14 0.13 0.10 0.08 0.07 0.07
## Cumulative Var        0.28 0.41 0.55 0.67 0.78 0.86 0.93 1.00
## Proportion Explained  0.28 0.14 0.14 0.13 0.10 0.08 0.07 0.07
## Cumulative Proportion 0.28 0.41 0.55 0.67 0.78 0.86 0.93 1.00
## 
## Test of the hypothesis that 8 components are sufficient.
## 
## The degrees of freedom for the null model are  28  and the objective function was  0.79
## The degrees of freedom for the model are -8  and the objective function was  0 
## The total number of observations was  1278  with MLE Chi Square =  0  with prob <  NA 
## 
## Fit based upon off diagonal values = 1

Eigen Values

ev <- eigen(cor(oJoggle1))
ev$values
## [1] 2.2034 1.0999 1.0930 1.0001 0.8085 0.6602 0.5915 0.5433

Scree Plot

ap <- parallel(subject=nrow(oJoggle1),var=ncol(oJoggle1), rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)

plot of chunk unnamed-chunk-5

Rotation to Final Solution - 3 Factors

JogglePCA.r<-principal(oJoggle1,nfactors=3,rotate="promax",scores=T)
principal(r=oJoggle1,nfactors=3,rotate="promax",scores=T)
## Principal Components Analysis
## Call: principal(r = oJoggle1, nfactors = 3, rotate = "promax", scores = T)
## Standardized loadings (pattern matrix) based upon correlation matrix
##                  PC1   PC3   PC2    h2   u2
## residNBack     -0.07  0.63  0.44 0.525 0.48
## residBART      -0.04  0.03 -0.28 0.076 0.92
## residVOLT       0.82 -0.03  0.08 0.643 0.36
## residDSST       0.10 -0.02  0.86 0.731 0.27
## residLOT        0.44  0.42 -0.06 0.539 0.46
## residAM         0.91 -0.19  0.06 0.705 0.29
## oMPTspeed       0.15  0.56 -0.31 0.542 0.46
## oPVTefficiency -0.20  0.85 -0.05 0.636 0.36
## 
##                        PC1  PC3  PC2
## SS loadings           1.69 1.59 1.11
## Proportion Var        0.21 0.20 0.14
## Cumulative Var        0.21 0.41 0.55
## Proportion Explained  0.39 0.36 0.25
## Cumulative Proportion 0.39 0.75 1.00
## 
##  With component correlations of 
##       PC1   PC3   PC2
## PC1  1.00  0.41 -0.15
## PC3  0.41  1.00 -0.08
## PC2 -0.15 -0.08  1.00
## 
## Test of the hypothesis that 3 components are sufficient.
## 
## The degrees of freedom for the null model are  28  and the objective function was  0.79
## The degrees of freedom for the model are 7  and the objective function was  0.79 
## The total number of observations was  1278  with MLE Chi Square =  1006  with prob <  6.2e-213 
## 
## Fit based upon off diagonal values = 0.59