Factor Analysis Comparison
Heather Perkins
2022-11-15
Prepare Data
Import surveys, combine into single data frame, delete identifying information, assign IDs, and separate out by scale for item examination.
# https://hansjoerg.me/2018/04/23/rasch-in-r-tutorial/
knitr::knit_hooks$set(
error = function(x, options) {
paste('\n\n<div class="alert alert-danger">',
gsub('##', '\n', gsub('^##\ Error', '**Error**', x)),
'</div>', sep = '\n')
},
warning = function(x, options) {
paste('\n\n<div class="alert alert-warning">',
gsub('##', '\n', gsub('^##\ Warning:', '**Warning**', x)),
'</div>', sep = '\n')
},
message = function(x, options) {
paste('\n\n<div class="alert alert-info">',
gsub('##', '\n', x),
'</div>', sep = '\n')
}
)
# load libraries ----------------------------------------------------------
library(stringi)
library(psych)
library(DT)
library(naniar)
library(UpSetR)
library(nFactors)
library(lavaan)
library(corrplot)
library(tidyr)
library(ggplot2)
library(dplyr)
library("eRm")
library("ltm")
library("difR")
library("psych")
library(readr) # For import the data
library(TAM) # For running the Rating Scale Rasch Model
# library(plyr) # For plot the Item characteristic curves
library(WrightMap)# For plot the variable map
# library(eRm) # For another example
# load data ---------------------------------------------------------------
# alt <- read.csv(file="UBelong Post-Survey Pitt OChem Spring 2022 Alternative Scales_April 28, 2022_12.34.csv", header=T)
# alt <- alt[-c(1,2),]
# alt$scale <- "alt"
#
# orig <- read.csv(file="UBelong Post-Survey Pitt OChem Spring 2022 Original Scales_April 28, 2022_12.35.csv", header=T)
# orig <- orig[-c(1,2),]
# orig$scale <- "orig"
#
# df <- rbind.data.frame(alt, orig)
# df <- subset(df, select = -c(1:19))
# names(df)
# myFun <- function(n) {
# a <- do.call(paste0, replicate(5, sample(LETTERS, n, TRUE), FALSE))
# paste0(a, sprintf("%04d", sample(9999, n, TRUE)), sample(LETTERS, n, TRUE))
# }
# df$id <- myFun(nrow(df))
# write.csv(df, file="imported_anonymized.csv", row.names = F)
df <- read.csv(file="imported_anonymized.csv", header=T)
# extract items -----------------------------------------------------------
# new items
EEochem <- subset(df, select=c(scale,grep("EEochem", colnames(df)))) # entry expectations
CCdisc <- subset(df, select=c(scale, grep("CCdisc", colnames(df)))) # classroom climate
IDochem <- cbind.data.frame(subset(df, select=c(scale,grep("IDochem", colnames(df)))), subset(df, select=grep("FASochem", colnames(df)))) # identity
CSochem <- subset(df, select=grep("CSochem", colnames(df))) # career satisfaction
# established scales
MSchem <- subset(df, select=c(scale,grep("MSchem", colnames(df)))) # discipline growth mindset (chemistry)
IPchem <- subset(df, select=c(scale, grep("IPchem", colnames(df)))) # instructor growth mindset (chemistry)
SEchem <- subset(df, select=c(scale, grep("SEchem", colnames(df)))) # disciplinary self-efficacy (chemistry)
MSochem <- subset(df, select=c(scale, grep("MSochem", colnames(df)))) # disciplinary growth mindset (organic chemistry)
IPochem <- subset(df, select=c(scale, grep("IPochem", colnames(df)))) # instructor growth mindset (organic chemistry)
SEochem <- subset(df, select=c(scale, grep("SEochem", colnames(df)))) # disciplinary self-efficacy (organic chemistry)
CNEBochem_class <- cbind.data.frame(subset(subset(df, select=grep("CNEBochem", colnames(df))), select=c(1:3))) # entity norms and beliefs
CNEBochem_self <- cbind.data.frame(subset(subset(df, select=grep("CNEBochem", colnames(df))), select=c(4:6))) # entity norms and beliefs
CNHSochem_others <- cbind.data.frame(subset(subset(df, select=grep("CNHSochem", colnames(df))), select=c(1:3))) # help seeking
CNHSochem_self <- cbind.data.frame(subset(subset(df, select=grep("CNHSochem", colnames(df))), select=c(4:6))) # help seeking
CNSWochem <- subset(df, select=c(scale, grep("CNSWochem", colnames(df)))) # help seeking
FCochem <- subset(df, select=c(scale, grep("FCochem", colnames(df)))) # faculty caring
IDochem$FASochem03_rc[IDochem$FASochem03 == 1] <- 4
IDochem$FASochem03_rc[IDochem$FASochem03 == 2] <- 3
IDochem$FASochem03_rc[IDochem$FASochem03 == 3] <- 2
IDochem$FASochem03_rc[IDochem$FASochem03 == 4] <- 1
IDochem$FASochem03 <- IDochem$FASochem03_rc
IDochem <- subset(IDochem, select=-c(FASochem03_rc))Disciplinary Mindset (OC-Alt)
d <- subset(MSochem, scale == "alt", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## MSochem01 MSochem02 MSochem03 MSochem04 MSochem05 MSochem06 MSochem07
## 0.217 0.228 0.249 0.207 0.724 0.488 0.630
##
## Loadings:
## [1] 0.885 0.878 0.866 0.891 -0.525 -0.715 -0.609
##
## Factor1
## SS loadings 4.256
## Proportion Var 0.608
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 102.43 on 14 degrees of freedom.
## The p-value is 1.62e-15EFA <- factanal(d, factors = 2, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 2, rotation = "promax")
##
## Uniquenesses:
## MSochem01 MSochem02 MSochem03 MSochem04 MSochem05 MSochem06 MSochem07
## 0.244 0.247 0.178 0.175 0.479 0.249 0.267
##
## Loadings:
## Factor1 Factor2
## MSochem01 0.789
## MSochem02 0.769
## MSochem03 0.963
## MSochem04 0.898
## MSochem05 0.752
## MSochem06 0.754
## MSochem07 0.899
##
## Factor1 Factor2
## SS loadings 2.979 1.983
## Proportion Var 0.426 0.283
## Cumulative Var 0.426 0.709
##
## Factor Correlations:
## Factor1 Factor2
## Factor1 1.000 -0.665
## Factor2 -0.665 1.000
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 33 on 8 degrees of freedom.
## The p-value is 6.15e-05Disciplinary Mindset (OC-Orig)
d <- subset(MSochem, scale == "orig", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## MSochem01 MSochem02 MSochem03 MSochem04 MSochem05 MSochem06 MSochem07
## 0.359 0.284 0.225 0.152 0.335 0.221 0.440
##
## Loadings:
## [1] 0.801 0.846 0.880 0.921 -0.815 -0.882 -0.748
##
## Factor1
## SS loadings 4.982
## Proportion Var 0.712
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 54.14 on 14 degrees of freedom.
## The p-value is 1.22e-06EFA <- factanal(d, factors = 2, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 2, rotation = "promax")
##
## Uniquenesses:
## MSochem01 MSochem02 MSochem03 MSochem04 MSochem05 MSochem06 MSochem07
## 0.295 0.278 0.166 0.109 0.333 0.237 0.086
##
## Loadings:
## Factor1 Factor2
## MSochem02 0.792
## MSochem03 1.031
## MSochem04 0.986
## MSochem06 -0.620
## MSochem01 0.316 -0.565
## MSochem07 1.099
## MSochem05 -0.460 0.400
##
## Factor1 Factor2
## SS loadings 3.393 1.806
## Proportion Var 0.485 0.258
## Cumulative Var 0.485 0.743
##
## Factor Correlations:
## Factor1 Factor2
## Factor1 1.0 -0.8
## Factor2 -0.8 1.0
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 20.19 on 8 degrees of freedom.
## The p-value is 0.00963Instructor Mindset (OC-Alt)
d <- subset(IPochem, scale == "alt", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## IPochem02 IPochem03 IPochem04 IPochem05
## 0.529 0.444 0.690 0.996
##
## Loadings:
## [1] 0.686 0.745 -0.557
##
## Factor1
## SS loadings 1.340
## Proportion Var 0.335
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 1.37 on 2 degrees of freedom.
## The p-value is 0.505Instructor Mindset (OC-Orig)
d <- subset(IPochem, scale == "orig", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## IPochem02 IPochem03 IPochem04 IPochem05
## 0.005 0.766 0.953 0.996
##
## Loadings:
## [1] 0.997 0.484
##
## Factor1
## SS loadings 1.28
## Proportion Var 0.32
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 5.01 on 2 degrees of freedom.
## The p-value is 0.0815Self-Efficacy (OC-Alt)
d <- subset(SEochem, scale == "alt", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## SEochem01 SEochem02 SEochem03 SEochem04 SEochem05
## 0.540 0.492 0.638 0.569 0.597
##
## Loadings:
## [1] 0.679 0.713 -0.602 0.656 -0.634
##
## Factor1
## SS loadings 2.164
## Proportion Var 0.433
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 3.31 on 5 degrees of freedom.
## The p-value is 0.653Self-Efficacy (OC-Orig)
d <- subset(SEochem, scale == "orig", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## SEochem01 SEochem02 SEochem03 SEochem04 SEochem05
## 0.376 0.386 0.623 0.795 0.797
##
## Loadings:
## [1] 0.790 0.783 -0.614 0.453 -0.450
##
## Factor1
## SS loadings 2.022
## Proportion Var 0.404
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 1.85 on 5 degrees of freedom.
## The p-value is 0.869Identity (OC-Alt)
d <- subset(IDochem, scale == "alt", select=-c(1,2))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 3, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 3, rotation = "promax")
##
## Uniquenesses:
## IDochem02 IDochem03 IDochem04 IDochem05 IDochem06 IDochem10 IDochem07
## 0.178 0.370 0.092 0.104 0.498 0.552 0.553
## IDochem08 IDochem09 FASochem02 FASochem03 FASochem05
## 0.440 0.346 0.203 0.362 0.315
##
## Loadings:
## Factor1 Factor2 Factor3
## IDochem02 0.916
## IDochem03 0.654
## IDochem04 0.927
## IDochem05 0.910
## IDochem06 0.753
## IDochem10 0.625
## FASochem02 0.917
## FASochem03 0.825
## FASochem05 0.702
## IDochem07 0.737
## IDochem08 0.756
## IDochem09 0.665
##
## Factor1 Factor2 Factor3
## SS loadings 3.563 2.502 1.626
## Proportion Var 0.297 0.208 0.135
## Cumulative Var 0.297 0.505 0.641
##
## Factor Correlations:
## Factor1 Factor2 Factor3
## Factor1 1.000 -0.658 0.402
## Factor2 -0.658 1.000 -0.551
## Factor3 0.402 -0.551 1.000
##
## Test of the hypothesis that 3 factors are sufficient.
## The chi square statistic is 23.89 on 33 degrees of freedom.
## The p-value is 0.877Identity (OC-Orig)
d <- subset(IDochem, scale == "orig", select=-c(1,2))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 3, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 3, rotation = "promax")
##
## Uniquenesses:
## IDochem02 IDochem03 IDochem04 IDochem05 IDochem06 IDochem10 IDochem07
## 0.458 0.585 0.194 0.120 0.558 0.493 0.888
## IDochem08 IDochem09 FASochem02 FASochem03 FASochem05
## 0.618 0.585 0.446 0.498 0.005
##
## Loadings:
## Factor1 Factor2 Factor3
## IDochem02 0.768
## IDochem04 0.885
## IDochem05 0.942
## IDochem06 0.639
## FASochem03 0.545
## FASochem05 1.123
## IDochem10 -0.404 0.904
## IDochem08 -0.337 0.621
## IDochem03 0.399 0.323
## IDochem07 0.378
## IDochem09 0.352 0.351
## FASochem02 0.406
##
## Factor1 Factor2 Factor3
## SS loadings 3.044 2.048 1.715
## Proportion Var 0.254 0.171 0.143
## Cumulative Var 0.254 0.424 0.567
##
## Factor Correlations:
## Factor1 Factor2 Factor3
## Factor1 1.000 0.553 0.734
## Factor2 0.553 1.000 0.447
## Factor3 0.734 0.447 1.000
##
## Test of the hypothesis that 3 factors are sufficient.
## The chi square statistic is 39.06 on 33 degrees of freedom.
## The p-value is 0.216Disciplinary Mindset (C-Alt)
d <- subset(MSchem, scale == "alt", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## MSchem01 MSchem02 MSchem03 MSchem04 MSchem05 MSchem06 MSchem07
## 0.582 0.420 0.410 0.295 0.658 0.351 0.411
##
## Loadings:
## [1] 0.646 0.762 0.768 0.840 -0.585 -0.805 -0.768
##
## Factor1
## SS loadings 3.872
## Proportion Var 0.553
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 87.64 on 14 degrees of freedom.
## The p-value is 1.06e-12EFA <- factanal(d, factors = 2, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 2, rotation = "promax")
##
## Uniquenesses:
## MSchem01 MSchem02 MSchem03 MSchem04 MSchem05 MSchem06 MSchem07
## 0.630 0.465 0.316 0.005 0.580 0.234 0.249
##
## Loadings:
## Factor1 Factor2
## MSchem05 0.756
## MSchem06 0.867
## MSchem07 0.899
## MSchem03 0.802
## MSchem04 1.058
## MSchem01 -0.323 0.329
## MSchem02 -0.441 0.342
##
## Factor1 Factor2
## SS loadings 2.440 2.016
## Proportion Var 0.349 0.288
## Cumulative Var 0.349 0.637
##
## Factor Correlations:
## Factor1 Factor2
## Factor1 1.00 -0.74
## Factor2 -0.74 1.00
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 28.43 on 8 degrees of freedom.
## The p-value is 0.000399Disciplinary Mindset (C-Orig)
d <- subset(MSchem, scale == "orig", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## MSchem01 MSchem02 MSchem03 MSchem04 MSchem05 MSchem06 MSchem07
## 0.436 0.281 0.154 0.112 0.706 0.528 0.642
##
## Loadings:
## [1] 0.751 0.848 0.920 0.942 -0.543 -0.687 -0.598
##
## Factor1
## SS loadings 4.141
## Proportion Var 0.592
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 158.34 on 14 degrees of freedom.
## The p-value is 1.53e-26EFA <- factanal(d, factors = 2, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 2, rotation = "promax")
##
## Uniquenesses:
## MSchem01 MSchem02 MSchem03 MSchem04 MSchem05 MSchem06 MSchem07
## 0.446 0.250 0.130 0.111 0.181 0.148 0.370
##
## Loadings:
## Factor1 Factor2
## MSchem01 0.708
## MSchem02 0.918
## MSchem03 0.936
## MSchem04 0.894
## MSchem05 0.974
## MSchem06 0.849
## MSchem07 0.737
##
## Factor1 Factor2
## SS loadings 3.056 2.229
## Proportion Var 0.437 0.318
## Cumulative Var 0.437 0.755
##
## Factor Correlations:
## Factor1 Factor2
## Factor1 1.00 -0.61
## Factor2 -0.61 1.00
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 58.7 on 8 degrees of freedom.
## The p-value is 8.36e-10Instructor Mindset (C-Alt)
d <- subset(IPchem, scale == "alt", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## IPchem02 IPchem03 IPchem04 IPchem05
## 0.547 0.339 0.798 0.992
##
## Loadings:
## [1] 0.673 0.813 -0.449
##
## Factor1
## SS loadings 1.324
## Proportion Var 0.331
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 3.3 on 2 degrees of freedom.
## The p-value is 0.192Instructor Mindset (C-Orig)
d <- subset(IPochem, scale == "orig", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## IPochem02 IPochem03 IPochem04 IPochem05
## 0.005 0.766 0.953 0.996
##
## Loadings:
## [1] 0.997 0.484
##
## Factor1
## SS loadings 1.28
## Proportion Var 0.32
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 5.01 on 2 degrees of freedom.
## The p-value is 0.0815Faculty Caring (C-Alt)
d <- subset(FCochem, scale == "alt", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## FCochem01 FCochem02 FCochem03 FCochem04
## 0.412 0.225 0.135 0.143
##
## Loadings:
## [1] 0.767 0.880 0.930 0.926
##
## Factor1
## SS loadings 3.084
## Proportion Var 0.771
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 5.72 on 2 degrees of freedom.
## The p-value is 0.0572Faculty Caring (C-Orig)
d <- subset(FCochem, scale == "orig", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## FCochem01 FCochem02 FCochem03 FCochem04
## 0.229 0.307 0.189 0.197
##
## Loadings:
## [1] 0.878 0.832 0.900 0.896
##
## Factor1
## SS loadings 3.077
## Proportion Var 0.769
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 8.92 on 2 degrees of freedom.
## The p-value is 0.0116Classroom Climate (C-Alt)
d <- subset(CCdisc, scale == "alt", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## CCdisc01 CCdisc02 CCdisc03 CCdisc04
## 0.934 0.005 0.991 0.999
##
## Loadings:
## [1] 0.997
##
## Factor1
## SS loadings 1.071
## Proportion Var 0.268
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 2.96 on 2 degrees of freedom.
## The p-value is 0.228Classroom Climate (C-Orig)
d <- subset(CCdisc, scale == "orig", select=-c(1))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 1, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 1, rotation = "promax")
##
## Uniquenesses:
## CCdisc01 CCdisc02 CCdisc03 CCdisc04
## 0.966 0.964 0.586 0.005
##
## Loadings:
## [1] 0.643 0.997
##
## Factor1
## SS loadings 1.479
## Proportion Var 0.370
##
## Test of the hypothesis that 1 factor is sufficient.
## The chi square statistic is 2.47 on 2 degrees of freedom.
## The p-value is 0.29Classroom Norms (C-Alt)
# CNEBochem_class CNHSochem_others CNSWochem
CN_cno <- cbind.data.frame(CNEBochem_class, CNHSochem_others,subset(CNSWochem, select=c(1:4)))
d <- subset(CN_cno, scale == "alt", select=-c(scale))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 3, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 3, rotation = "promax")
##
## Uniquenesses:
## CNEBochem01 CNEBochem02 CNEBochem03 CNHSochem01 CNHSochem02 CNHSochem03
## 0.608 0.759 0.881 0.631 0.327 0.172
## CNSWochem01 CNSWochem02 CNSWochem03
## 0.306 0.428 0.636
##
## Loadings:
## Factor1 Factor2 Factor3
## CNHSochem01 0.538
## CNHSochem02 0.617 0.396
## CNHSochem03 0.913
## CNSWochem01 0.769
## CNEBochem01 0.657
## CNSWochem02 0.463 -0.503
## CNEBochem02 0.473
## CNEBochem03 0.353
## CNSWochem03 0.369 -0.401
##
## Factor1 Factor2 Factor3
## SS loadings 1.643 1.267 1.135
## Proportion Var 0.183 0.141 0.126
## Cumulative Var 0.183 0.323 0.449
##
## Factor Correlations:
## Factor1 Factor2 Factor3
## Factor1 1.0000 -0.325 0.0976
## Factor2 -0.3249 1.000 -0.3079
## Factor3 0.0976 -0.308 1.0000
##
## Test of the hypothesis that 3 factors are sufficient.
## The chi square statistic is 26.94 on 12 degrees of freedom.
## The p-value is 0.00788Classroom Norms (C-Orig)
# CNEBochem_class CNHSochem_others CNSWochem
CN_cno <- cbind.data.frame(CNEBochem_class, CNHSochem_others,subset(CNSWochem, select=c(1:4)))
d <- subset(CN_cno, scale == "orig", select=-c(scale))
d <- na.omit(d)
ev <- eigen(cor(d))
ap <- parallel(subject=nrow(d),var=ncol(d),rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
EFA <- factanal(d, factors = 3, rotation = "promax")
print(EFA, digits=3, cutoff=.3, sort=TRUE)##
## Call:
## factanal(x = d, factors = 3, rotation = "promax")
##
## Uniquenesses:
## CNEBochem01 CNEBochem02 CNEBochem03 CNHSochem01 CNHSochem02 CNHSochem03
## 0.838 0.658 0.478 0.672 0.549 0.191
## CNSWochem01 CNSWochem02 CNSWochem03
## 0.578 0.141 0.395
##
## Loadings:
## Factor1 Factor2 Factor3
## CNSWochem01 0.541
## CNSWochem02 0.967
## CNSWochem03 0.804
## CNHSochem02 0.711
## CNHSochem03 0.942
## CNEBochem02 0.578
## CNEBochem03 -0.739
## CNEBochem01
## CNHSochem01 0.347 0.328
##
## Factor1 Factor2 Factor3
## SS loadings 2.081 1.518 1.069
## Proportion Var 0.231 0.169 0.119
## Cumulative Var 0.231 0.400 0.519
##
## Factor Correlations:
## Factor1 Factor2 Factor3
## Factor1 1.000 -0.504 -0.189
## Factor2 -0.504 1.000 0.192
## Factor3 -0.189 0.192 1.000
##
## Test of the hypothesis that 3 factors are sufficient.
## The chi square statistic is 12.42 on 12 degrees of freedom.
## The p-value is 0.413