Differences

This shows you the differences between two versions of the page.

--- factor_analysis_examples [2019/11/20 08:52] – [Personality] hkimscil
+++ factor_analysis_examples [2019/12/06 13:45] – created hkimscil
@@ Line 1: / Line 1: @@
-====== FA e.gs ======
+====== 1 ======
-====== Personality ======
+{{:r:EFA.csv}}
 <code>
-d <- read.table("http://commres.net/wiki/_media/r/personality0.txt")
+# read the dataset into R variable using the read.csv(file) function
+data <- read.csv("http://commres.net/wiki/_media/r/efa.csv")
+head(data)
 </code>
-살펴보기 (head)
-구조및성질 (str)
-상관관계 도식화 (corrplot)
-  * require corrplot package
-<code>
-install.packages("corrplot") # if not installed
-library(corrplot)
-corrplot(cor(d), order = "hclust", tl.col='black', tl.cex=.75)
-</code>
-fa 펑션 factor analysis
 <code>
+# install the package
+# install.packages("psych")
+# install.packages("GPArotation")
+# load the package
 library(psych)
-d.fa <- fa(d, rotate="none") # fa test with no rotation
+library(GPArotation)
-names(d.fa) # to see what comes with the output d.fa
 </code>
-check out the output.
 <code>
-d.fa
+# calculate the correlation matrix
+corMat <- cor(data)
+# display the correlation matrix
+round(corMat,3)
 </code>
-compare the output to d.fa$communality
 <code>
-d.fa$communality
+# use fa() to conduct an oblique principal-axis exploratory factor analysis
+# save the solution to an R variable
+solution <- fa(r = corMat, nfactors = 2, rotate = "oblimin", fm = "pa")
+solution2 <- fa(data,  nfactors = 2, rotate = "oblimin", fm = "pa")
+# display the solution output
+solution
+solution2
 </code>
-for better output
 <code>
-data.frame(d.fa$communality)
+fa.sort(solution)
 </code>
-d.fa 아웃풋처럼 round 처리
-<code>
-round(data.frame(d.fa$communality),3)
-</code>
-check out the uniqueness too
-<WRAP info 70%>
-uniqueness check
-직접 해 보기
-</WRAP>