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_or <- read.csv2("basak_sayisal_veriler.csv")
df <- df_or[-43,]
#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("isletme")) %>%
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("isletme")) %>% names
## [1] "isletme_sektor" "isletme_isim" "isletme_yabanci_ortak"
## [4] "isletme_yas" "isletme_olcek" "isletme_calisan_sayisi"
df %>%
dplyr::select(starts_with("isletme")) %>%
dplyr::select(c(3)) %>% table
## isletme_yabanci_ortak
## Evet Hayir
## 51 70
df %>%
dplyr::select(starts_with("isletme")) %>%
dplyr::select(c(5,6)) %>% table
## isletme_calisan_sayisi
## isletme_olcek 10 - 49 kisi 250 kisi ve uzeri 50 - 249 kisi
## Buyuk 1 36 11
## Kucuk 9 0 6
## Orta 9 9 40
df %>%
dplyr::select(starts_with("isletme")) %>%
dplyr::select(c(4)) %>% table
## isletme_yas
## 1 - 10 yil 11 - 30 yil 30 yildan fazla
## 15 51 55
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 1.031
## far_sur_gelecek 0.439 0.459
## far_sur_adil_is 0.772
## far_sur_toplum 0.943 -0.143
## far_sur_cevre_koruma 0.786 0.101
## far_sur_paydas 0.444 0.378
## far_sur_eko_performans 0.139 0.533
## far_sur_calisan_hak 0.715 0.170
## far_sur_tarim 0.660 -0.105
##
## Factor1 Factor2
## SS loadings 3.467 1.779
## Proportion Var 0.385 0.198
## Cumulative Var 0.385 0.583
##
## faktor analizining acikladigi oranlar:
## explained_variances
## far_sur_kaynak 0.9435916
## far_sur_gelecek 0.7231282
## far_sur_adil_is 0.7080690
## far_sur_toplum 0.6964625
## far_sur_cevre_koruma 0.7537155
## far_sur_paydas 0.6064055
## far_sur_eko_performans 0.4214697
## far_sur_calisan_hak 0.7336435
## far_sur_tarim 0.3367582
##
## likelihood ratio test | p-value: 0.06571096
##
## 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
## -4.8050 -0.9329 0.4233 0.7697 3.9615
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.3573 0.1965 -1.819 0.0715 .
## isletme_yabanci_ortak_Hayir 0.6176 0.2583 2.391 0.0184 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.403 on 119 degrees of freedom
## Multiple R-squared: 0.04584, Adjusted R-squared: 0.03782
## F-statistic: 5.717 on 1 and 119 DF, p-value: 0.01837
## ######[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
## -5.1971 -0.4102 0.0624 0.7704 3.4458
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.2734 0.2022 1.352 0.179
## isletme_yabanci_ortak_Hayir -0.4726 0.2659 -1.778 0.078 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.444 on 119 degrees of freedom
## Multiple R-squared: 0.02587, Adjusted R-squared: 0.01768
## F-statistic: 3.16 on 1 and 119 DF, p-value: 0.07803
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
## -4.2879 -1.0077 0.5104 0.8430 4.4785
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.3873 0.3674 1.054 0.294
## `isletme_yas_11 - 30 yil` -0.6441 0.4180 -1.541 0.126
## `isletme_yas_30 yildan fazla` -0.2549 0.4145 -0.615 0.540
##
## Residual standard error: 1.423 on 118 degrees of freedom
## Multiple R-squared: 0.02679, Adjusted R-squared: 0.01029
## F-statistic: 1.624 on 2 and 118 DF, p-value: 0.2015
## ######[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
## -5.3766 -0.3086 -0.0749 0.8103 3.0748
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.8352 0.3702 -2.256 0.0259 *
## `isletme_yas_11 - 30 yil` 1.0070 0.4211 2.391 0.0184 *
## `isletme_yas_30 yildan fazla` 0.9036 0.4176 2.164 0.0325 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.434 on 118 degrees of freedom
## Multiple R-squared: 0.04799, Adjusted R-squared: 0.03185
## F-statistic: 2.974 on 2 and 118 DF, p-value: 0.05494
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
## -4.4814 -0.9939 0.4672 1.0090 4.2851
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.03352 0.20728 -0.162 0.872
## isletme_olcek_Kucuk 0.38550 0.42480 0.907 0.366
## isletme_olcek_Orta -0.02977 0.28022 -0.106 0.916
##
## Residual standard error: 1.436 on 118 degrees of freedom
## Multiple R-squared: 0.008736, Adjusted R-squared: -0.008066
## F-statistic: 0.5199 on 2 and 118 DF, p-value: 0.5959
## ######[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
## -5.0459 -0.4098 0.0221 0.7193 2.9736
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.2730 0.2095 1.303 0.195
## isletme_olcek_Kucuk -0.5322 0.4294 -1.239 0.218
## isletme_olcek_Orta -0.4319 0.2833 -1.525 0.130
##
## Residual standard error: 1.452 on 118 degrees of freedom
## Multiple R-squared: 0.02375, Adjusted R-squared: 0.007199
## F-statistic: 1.435 on 2 and 118 DF, p-value: 0.2422
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
## -4.5403 -0.9434 0.4964 0.9799 4.2262
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.2123 0.3301 0.643 0.521
## `isletme_calisan_sayisi_50 - 249 kisi` -0.2167 0.3812 -0.568 0.571
## `isletme_calisan_sayisi_250 kisi ve uzeri` -0.2964 0.3937 -0.753 0.453
##
## Residual standard error: 1.439 on 118 degrees of freedom
## Multiple R-squared: 0.004788, Adjusted R-squared: -0.01208
## F-statistic: 0.2839 on 2 and 118 DF, p-value: 0.7534
## ######[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
## -5.0807 -0.3374 -0.0095 0.9556 3.0460
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.10296 0.33517 -0.307 0.759
## `isletme_calisan_sayisi_50 - 249 kisi` -0.02114 0.38703 -0.055 0.957
## `isletme_calisan_sayisi_250 kisi ve uzeri` 0.30362 0.39972 0.760 0.449
##
## Residual standard error: 1.461 on 118 degrees of freedom
## Multiple R-squared: 0.01135, Adjusted R-squared: -0.005408
## F-statistic: 0.6772 on 2 and 118 DF, p-value: 0.51