podatki <- read.table("/cloud/project/Poglavje 1/Naloga 2/Anketa.csv", header=TRUE, sep=";", dec=",")
Opis spremenljivk:
#Zamenjava mankajočih vrednosti s povprečjem (mean) spremenljivke
podatki_imputacija <- sapply(X = podatki, FUN = function(x) {
x[is.na(x)] <- mean(x, na.rm = TRUE)
x
})
podatki_imputacija <- as.data.frame(podatki_imputacija)
podatki <- na.omit(podatki) #Odstranitev enot z manjkajočimi vrednostmi
podatki_MGK <- podatki[-1]
library(pastecs)
round(stat.desc(podatki_MGK, basic=FALSE), 2)
## T1 T2 T3 T4 T5 T6 T7 T8 T9 T10 T11
## median 5.00 5.00 5.00 4.00 4.00 4.00 4.00 4.00 4.00 4.00 4.00
## mean 4.46 4.53 4.45 4.28 4.17 3.93 4.08 3.78 3.77 3.61 3.81
## SE.mean 0.02 0.02 0.02 0.02 0.02 0.03 0.03 0.02 0.03 0.03 0.03
## CI.mean.0.95 0.04 0.04 0.04 0.04 0.05 0.05 0.05 0.05 0.05 0.06 0.05
## var 0.53 0.49 0.54 0.69 0.80 1.07 0.93 0.83 0.97 1.25 0.92
## std.dev 0.73 0.70 0.73 0.83 0.89 1.03 0.96 0.91 0.98 1.12 0.96
## coef.var 0.16 0.15 0.16 0.19 0.21 0.26 0.24 0.24 0.26 0.31 0.25
## T12
## median 4.00
## mean 3.67
## SE.mean 0.03
## CI.mean.0.95 0.05
## var 0.86
## std.dev 0.93
## coef.var 0.25
R <- cor(podatki_MGK)
library(psych)
cortest.bartlett(R, n=nrow(podatki_MGK))
## $chisq
## [1] 8676.712
##
## $p.value
## [1] 0
##
## $df
## [1] 66
library(psych)
KMO(R)
## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = R)
## Overall MSA = 0.93
## MSA for each item =
## T1 T2 T3 T4 T5 T6 T7 T8 T9 T10 T11 T12
## 0.92 0.92 0.94 0.94 0.95 0.93 0.92 0.96 0.96 0.96 0.91 0.91
library(FactoMineR)
mgk <- PCA(podatki_MGK,
scale.unit = TRUE,
graph = FALSE)
library(factoextra)
get_eigenvalue(mgk)
## eigenvalue variance.percent cumulative.variance.percent
## Dim.1 6.2491466 52.076222 52.07622
## Dim.2 1.2294783 10.245652 62.32187
## Dim.3 0.7189891 5.991576 68.31345
## Dim.4 0.6131295 5.109412 73.42286
## Dim.5 0.5611649 4.676374 78.09924
## Dim.6 0.5029911 4.191592 82.29083
## Dim.7 0.4712636 3.927196 86.21802
## Dim.8 0.3888152 3.240127 89.45815
## Dim.9 0.3679037 3.065864 92.52402
## Dim.10 0.3282004 2.735004 95.25902
## Dim.11 0.3173777 2.644814 97.90383
## Dim.12 0.2515399 2.096166 100.00000
library(psych)
fa.parallel(podatki_MGK,
sim = FALSE,
fa = "pc")
## Parallel analysis suggests that the number of factors = NA and the number of components = 2
library(FactoMineR)
mgk <- PCA(podatki_MGK,
scale.unit = TRUE,
graph = FALSE,
ncp = 2)
print(mgk$var$cor)
## Dim.1 Dim.2
## T1 0.7272862 -0.449186917
## T2 0.7237804 -0.407656811
## T3 0.7462246 -0.308126055
## T4 0.6851108 -0.281370367
## T5 0.8064691 -0.105254309
## T6 0.7551239 0.365934593
## T7 0.6409799 0.497003643
## T8 0.5926928 0.377917114
## T9 0.7633547 0.134538044
## T10 0.6513753 0.364483297
## T11 0.8191389 -0.040292200
## T12 0.7137101 0.004668726
print(mgk$var$contrib)
## Dim.1 Dim.2
## T1 8.464279 16.410935243
## T2 8.382874 13.516633611
## T3 8.910834 7.722109966
## T4 7.511055 6.439258329
## T5 10.407700 0.901070779
## T6 9.124640 10.891459216
## T7 6.574581 20.090848536
## T8 5.621324 11.616418635
## T9 9.324640 1.472208603
## T10 6.789563 10.805239477
## T11 10.737283 0.132044741
## T12 8.151226 0.001772866
library(factoextra)
fviz_pca_var(mgk,
repel = TRUE)
podatki$GK1 <- mgk$ind$coord[ , 1]
podatki$GK2 <- mgk$ind$coord[ , 2]
podatki[34, c(1, 14, 15)]
## ID GK1 GK2
## 34 34 0.1166287 -1.470207
podatki_std <- scale(podatki[ , 2:13])
podatki_std[34, ]
## T1 T2 T3 T4 T5
## 0.73741110 0.67816982 0.75745547 0.86774507 -0.18499331
## T6 T7 T8 T9 T10
## 0.06726110 -0.07981577 0.24583366 -0.78700936 -1.43920227
## T11 T12
## 0.19519579 -0.71913015