library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.3.2
## Warning: package 'ggplot2' was built under R version 4.3.1
## Warning: package 'tibble' was built under R version 4.3.1
## Warning: package 'tidyr' was built under R version 4.3.1
## Warning: package 'readr' was built under R version 4.3.2
## Warning: package 'purrr' was built under R version 4.3.1
## Warning: package 'dplyr' was built under R version 4.3.1
## Warning: package 'stringr' was built under R version 4.3.1
## Warning: package 'forcats' was built under R version 4.3.2
## Warning: package 'lubridate' was built under R version 4.3.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ltm)
## Warning: package 'ltm' was built under R version 4.3.3
## Loading required package: MASS
##
## Attaching package: 'MASS'
##
## The following object is masked from 'package:dplyr':
##
## select
##
## Loading required package: msm
## Warning: package 'msm' was built under R version 4.3.3
## Loading required package: polycor
## Warning: package 'polycor' was built under R version 4.3.3
library(dplyr)
library(stats)
library(fastDummies)
## Warning: package 'fastDummies' was built under R version 4.3.3
## Thank you for using fastDummies!
## To acknowledge our work, please cite the package:
## Kaplan, J. & Schlegel, B. (2023). fastDummies: Fast Creation of Dummy (Binary) Columns and Rows from Categorical Variables. Version 1.7.1. URL: https://github.com/jacobkap/fastDummies, https://jacobkap.github.io/fastDummies/.
df <- read.csv2("basak_sayisal_veriler.csv")
#glimpse(df)
extract_factors <- function (df,what,howmany,reduce=0,rotat="promax"){
cat("________________ START --> ", what, "_____________________")
cat("\n")
center <- function(x) { return (x - mean(x))}
df_sub <- df %>% dplyr::select(starts_with(what)) %>% mutate(across(everything(), center))
CA <- round(cronbach.alpha(df_sub) $ alpha,2)
cat("\n")
cat("cronbach_alpa =", CA)
cat("\n")
if (reduce != 0) df_sub=df_sub[,-reduce]
FA<- df_sub%>%factanal(.,howmany, scores ="regression",rotation=rotat)
print(FA $ loadings)
explained <- 1-FA $ uniquenesses
barplot(explained,cex.names=0.7, col=1:length(explained),
main="faktor analizining acikladigi oranlar", cex.main=0.8)
cat("\n")
cat("faktor analizining acikladigi oranlar:");cat("\n")
explained_props <- as.data.frame(1-FA $ uniquenesses)
colnames(explained_props) ="explained_variances"
print(explained_props);cat("\n")
cat("likelihood ratio test | p-value:", FA $ PVAL); cat("\n")
if(FA $ PVAL<0.05) print("factors are not sufficient")
else cat("\n", "factors are sufficient")
cat("\n")
cat("________________ END _____________________")
outcome <-list(FA,df_sub)
return(outcome)
}
dummy_func <- function (df,this) {
dummy <- df %>%
dplyr::select(starts_with("isletmenin")) %>%
dplyr::select(c(this)) %>%
dummy_cols %>%
dplyr::select(where(is.numeric))
return(dummy)
}
show_model_details <- function(model_now){
cat("\n")
model_now %>%
cooks.distance %>%
plot(.,type="h",col="black",
main=paste(model_now $call[2],"cooks distances (verilerin modele etkileri)"), cex.main = 0.6);abline(h=1,lty=2,col="red")
cat(rep("##",3),sep="")
paste("Y =", model_now $call[2]) %>% print
cat(rep("##",3),sep="")
cat("\n")
model_now %>% summary %>% print
}
df %>%
dplyr::select(starts_with("isletmenin")) %>% names
## [1] "isletmenin.sektor.grubu."
## [2] "isletmenin.unvani..adi..."
## [3] "isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir."
## [4] "isletmenin.faaliyette.bulundugu.sure."
## [5] "isletmenin.olcegi."
## [6] "isletmenin.calisan.sayisi."
df %>%
dplyr::select(starts_with("isletmenin")) %>%
dplyr::select(c(3)) %>% table
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir.
## Evet Hayir
## 51 71
df %>%
dplyr::select(starts_with("isletmenin")) %>%
dplyr::select(c(5,6)) %>% table
## isletmenin.calisan.sayisi.
## isletmenin.olcegi. 10 - 49 kisi 250 kisi ve uzeri 50 - 249 kisi
## Buyuk 1 36 11
## Kucuk 9 0 7
## Orta 9 9 40
df %>%
dplyr::select(starts_with("isletmenin")) %>%
dplyr::select(c(4)) %>% table
## isletmenin.faaliyette.bulundugu.sure.
## 1 - 10 yil 11 - 30 yil 30 yildan fazla
## 15 51 56
make_model <- function(df,which_X){
dummies<- dummy_func(df,which_X)
df_pilot <- cbind(see_sur_scores,dummies)
model_sosyal_cevresel_boyut <- lm(df_pilot $sosyal_cevresel_donusum~.,data = df_pilot[,-c(2,3)])
model_sosyal_cevresel_boyut%>%show_model_details
model_verimlilik_boyutu <- lm(df_pilot $ verimlilik_boyutu~.,data = df_pilot [,-c(1,3)])
model_verimlilik_boyutu%>%show_model_details}
see_sur <- extract_factors(df,"far_sur",2)
## ________________ START --> far_sur _____________________
##
## cronbach_alpa = 0.92
##
## Loadings:
## Factor1 Factor2
## far_sur_kaynak 1.044
## far_sur_gelecek 0.542 0.365
## far_sur_adil_is 0.791
## far_sur_toplum 0.906 -0.110
## far_sur_cevre_koruma 0.888
## far_sur_paydas 0.608 0.216
## far_sur_eko_performans 0.160 0.506
## far_sur_calisan_hak 0.808
## far_sur_tarim 0.678 -0.119
##
## Factor1 Factor2
## SS loadings 4.040 1.562
## Proportion Var 0.449 0.174
## Cumulative Var 0.449 0.622
##
## faktor analizining acikladigi oranlar:
## explained_variances
## far_sur_kaynak 0.9950000
## far_sur_gelecek 0.7264461
## far_sur_adil_is 0.7079855
## far_sur_toplum 0.6819977
## far_sur_cevre_koruma 0.7664654
## far_sur_paydas 0.6143465
## far_sur_eko_performans 0.4042705
## far_sur_calisan_hak 0.7504223
## far_sur_tarim 0.3518575
##
## likelihood ratio test | p-value: 0.1037971
##
## factors are sufficient
## ________________ END _____________________
see_sur_scores <- see_sur[[1]] $ scores
colnames(see_sur_scores) <- c("sosyal_cevresel_donusum","verimlilik_boyutu")
see_sur_scores %>% boxplot(.,horizontal=TRUE,cex.axis=0.7,
col=1:dim(see_sur_scores)[2],
main = "Faktor analizinden gelen bagimli degiskenler", cex.main=0.7)
make_model(df,3)
## Warning: Using an external vector in selections was deprecated in tidyselect 1.1.0.
## ℹ Please use `all_of()` or `any_of()` instead.
## # Was:
## data %>% select(this)
##
## # Now:
## data %>% select(all_of(this))
##
## See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## ######[1] "Y = df_pilot$sosyal_cevresel_donusum ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$sosyal_cevresel_donusum ~ ., data = df_pilot[,
## -c(2, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.6723 -0.8867 0.4300 0.7770 3.6786
##
## Coefficients:
## Estimate
## (Intercept) -0.2661
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir 0.4572
## Std. Error
## (Intercept) 0.1965
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir 0.2576
## t value
## (Intercept) -1.354
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir 1.775
## Pr(>|t|)
## (Intercept) 0.1783
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir 0.0784 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.403 on 120 degrees of freedom
## Multiple R-squared: 0.02558, Adjusted R-squared: 0.01746
## F-statistic: 3.151 on 1 and 120 DF, p-value: 0.07844
## ######[1] "Y = df_pilot$verimlilik_boyutu ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$verimlilik_boyutu ~ ., data = df_pilot[,
## -c(1, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9027 -0.3443 0.1096 0.8542 5.4104
##
## Coefficients:
## Estimate
## (Intercept) 0.2063
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir -0.3545
## Std. Error
## (Intercept) 0.2043
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir 0.2678
## t value
## (Intercept) 1.010
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir -1.324
## Pr(>|t|)
## (Intercept) 0.315
## isletmenin.yabanci.firmalarla.3kligi..isbirligi.var.midir._Hayir 0.188
##
## Residual standard error: 1.459 on 120 degrees of freedom
## Multiple R-squared: 0.01439, Adjusted R-squared: 0.00618
## F-statistic: 1.752 on 1 and 120 DF, p-value: 0.1881
make_model(df,4)
## ######[1] "Y = df_pilot$sosyal_cevresel_donusum ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$sosyal_cevresel_donusum ~ ., data = df_pilot[,
## -c(2, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.5543 -0.8952 0.4718 0.8949 4.0530
##
## Coefficients:
## Estimate Std. Error
## (Intercept) 0.3496 0.3657
## `isletmenin.faaliyette.bulundugu.sure._11 - 30 yil` -0.5328 0.4160
## `isletmenin.faaliyette.bulundugu.sure._30 yildan fazla` -0.2764 0.4118
## t value Pr(>|t|)
## (Intercept) 0.956 0.341
## `isletmenin.faaliyette.bulundugu.sure._11 - 30 yil` -1.281 0.203
## `isletmenin.faaliyette.bulundugu.sure._30 yildan fazla` -0.671 0.503
##
## Residual standard error: 1.416 on 119 degrees of freedom
## Multiple R-squared: 0.01585, Adjusted R-squared: -0.0006874
## F-statistic: 0.9584 on 2 and 119 DF, p-value: 0.3864
## ######[1] "Y = df_pilot$verimlilik_boyutu ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$verimlilik_boyutu ~ ., data = df_pilot[,
## -c(1, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.1693 -0.2564 -0.0556 0.9551 5.1520
##
## Coefficients:
## Estimate Std. Error
## (Intercept) -0.8140 0.3726
## `isletmenin.faaliyette.bulundugu.sure._11 - 30 yil` 0.9324 0.4238
## `isletmenin.faaliyette.bulundugu.sure._30 yildan fazla` 0.9242 0.4195
## t value Pr(>|t|)
## (Intercept) -2.185 0.0309 *
## `isletmenin.faaliyette.bulundugu.sure._11 - 30 yil` 2.200 0.0298 *
## `isletmenin.faaliyette.bulundugu.sure._30 yildan fazla` 2.203 0.0295 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.443 on 119 degrees of freedom
## Multiple R-squared: 0.04374, Adjusted R-squared: 0.02767
## F-statistic: 2.721 on 2 and 119 DF, p-value: 0.06988
make_model(df,5)
## ######[1] "Y = df_pilot$sosyal_cevresel_donusum ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$sosyal_cevresel_donusum ~ ., data = df_pilot[,
## -c(2, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.3985 -0.8574 0.4428 0.9172 3.8892
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.05096 0.20596 0.247 0.805
## isletmenin.olcegi._Kucuk -0.13362 0.41192 -0.324 0.746
## isletmenin.olcegi._Orta -0.07033 0.27844 -0.253 0.801
##
## Residual standard error: 1.427 on 119 degrees of freedom
## Multiple R-squared: 0.001054, Adjusted R-squared: -0.01573
## F-statistic: 0.0628 on 2 and 119 DF, p-value: 0.9392
## ######[1] "Y = df_pilot$verimlilik_boyutu ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$verimlilik_boyutu ~ ., data = df_pilot[,
## -c(1, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.8541 -0.3437 0.0588 0.8463 5.1661
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.2057 0.2112 0.974 0.332
## isletmenin.olcegi._Kucuk -0.1096 0.4223 -0.259 0.796
## isletmenin.olcegi._Orta -0.4024 0.2855 -1.410 0.161
##
## Residual standard error: 1.463 on 119 degrees of freedom
## Multiple R-squared: 0.01707, Adjusted R-squared: 0.0005541
## F-statistic: 1.034 on 2 and 119 DF, p-value: 0.3589
make_model(df,6)
## ######[1] "Y = df_pilot$sosyal_cevresel_donusum ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$sosyal_cevresel_donusum ~ ., data = df_pilot[,
## -c(2, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.3963 -0.8559 0.4490 0.9585 3.9546
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) 0.2363 0.3265 0.724
## `isletmenin.calisan.sayisi._50 - 249 kisi` -0.3212 0.3762 -0.854
## `isletmenin.calisan.sayisi._250 kisi ve uzeri` -0.2267 0.3894 -0.582
## Pr(>|t|)
## (Intercept) 0.471
## `isletmenin.calisan.sayisi._50 - 249 kisi` 0.395
## `isletmenin.calisan.sayisi._250 kisi ve uzeri` 0.562
##
## Residual standard error: 1.423 on 119 degrees of freedom
## Multiple R-squared: 0.006114, Adjusted R-squared: -0.01059
## F-statistic: 0.366 on 2 and 119 DF, p-value: 0.6943
## ######[1] "Y = df_pilot$verimlilik_boyutu ~ ."
## ######
##
## Call:
## lm(formula = df_pilot$verimlilik_boyutu ~ ., data = df_pilot[,
## -c(1, 3)])
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.9980 -0.2589 -0.0041 0.9329 5.3152
##
## Coefficients:
## Estimate Std. Error t value
## (Intercept) -0.12475 0.33780 -0.369
## `isletmenin.calisan.sayisi._50 - 249 kisi` 0.07181 0.38922 0.184
## `isletmenin.calisan.sayisi._250 kisi ve uzeri` 0.24565 0.40285 0.610
## Pr(>|t|)
## (Intercept) 0.713
## `isletmenin.calisan.sayisi._50 - 249 kisi` 0.854
## `isletmenin.calisan.sayisi._250 kisi ve uzeri` 0.543
##
## Residual standard error: 1.472 on 119 degrees of freedom
## Multiple R-squared: 0.004307, Adjusted R-squared: -0.01243
## F-statistic: 0.2574 on 2 and 119 DF, p-value: 0.7735