NLB
Blanka
2025-02-02
library(readxl)
mydata <- read_xlsx("./dataset copy.xlsx")## New names:
## • `Q22a_1` -> `Q22a_1...26`
## • `Q22b_1` -> `Q22b_1...27`
## • `Q22c_1` -> `Q22c_1...28`
## • `Q22d_1` -> `Q22d_1...29`
## • `Q22e_1` -> `Q22e_1...30`
## • `Q22a_1` -> `Q22a_1...32`
## • `Q22b_1` -> `Q22b_1...33`
## • `Q22c_1` -> `Q22c_1...34`
## • `Q22d_1` -> `Q22d_1...72`
## • `Q22e_1` -> `Q22e_1...73`mydata <- mydata[-1, ]
head(mydata)## # A tibble: 6 × 73
## Q8 Q66 Q10 Q12 Q11 Q48 Q48_5_text Q14a Q14b Q14c Q14d Q14e
## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 1 3 3 6 2 -2 -2 0 1 0 0 0
## 2 1 2 5 6 1 1 -2 0 1 0 0 0
## 3 1 6 5 6 1 3 -2 0 1 0 1 0
## 4 1 2 5 6 2 -2 -2 1 0 1 1 0
## 5 1 2 2 6 2 -2 -2 0 1 0 0 0
## 6 1 6 7 7 2 -2 -2 0 1 0 0 0
## # ℹ 61 more variables: Q14e_text <chr>, Q15 <chr>, Q16 <chr>, Q17 <chr>,
## # Q18 <chr>, Q25a <chr>, Q25b <chr>, Q25c <chr>, Q25d <chr>, Q25e <chr>,
## # Q25f <chr>, Q25g <chr>, Q25h <chr>, Q22a_1...26 <dbl>, Q22b_1...27 <dbl>,
## # Q22c_1...28 <dbl>, Q22d_1...29 <dbl>, Q22e_1...30 <dbl>, Q24 <chr>,
## # Q22a_1...32 <dbl>, Q22b_1...33 <dbl>, Q22c_1...34 <dbl>, Q13 <chr>,
## # Q20 <chr>, Q46 <chr>, Q1a_1 <dbl>, Q1b_1 <dbl>, Q1c_1 <dbl>, Q1d_1 <dbl>,
## # Q1e_1 <dbl>, Q1f_1 <dbl>, Q2a_1 <dbl>, Q2b_1 <dbl>, Q2c_1 <dbl>, …mydata$Q39 <- factor(mydata$Q39,
levels = c(1,2),
labels = c("Male", "Female"))
mydata$Q37 <- factor(mydata$Q37,
levels = c(1, 2, 3, 4, 5, 6, 7),
labels = c("Less than 1,000", "1,001 - 1,300", "1,301 - 1,700", "1,701 - 2,500", "2,501 - 3,300", "More than 3,000", "Pension"))
mydata$Q41 <- factor(mydata$Q41,
levels = c(1, 2, 3, 4, 5, 6, 7),
labels = c("Unfinished Elementary", "Finished Elementary", "Vocational School", "General High School", "Undergraduate Degree", "Master's Degree", "PhD"))
mydata$Q42 <- factor(mydata$Q42,
levels = c(1, 2, 3, 4, 5),
labels = c("Employed", "Self-Employed", "Retired", "Unemployed", "Other"))
#Service #Creative
mydata$Q43 <- factor(mydata$Q43,
levels = c(1, 2, 3, 4, 5),
labels = c("Physical Work", "Physical Work", "Office", "Public Sector", "Physical Work"))
mydata$Q44 <- factor(mydata$Q44,
levels = c(1, 2, 3),
labels = c("Urban", "Urban", "Rural"))
mydata$Q45 <- factor(mydata$Q45,
levels = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10),
labels = c("NLB", "OTP", "Unicredit", "Raiffaisen", "Gorenjska banka", "Intesa Sanpaolo", "Delavska hranilnica", "Revolut", "N26", "Other"))
mydata$Q11 <- factor(mydata$Q11,
levels = c(1, 2),
labels = c("No", "Yes"))
mydata$Q13 <- factor(mydata$Q13,
levels = c(1, 2, 3, 4, 5, 6, 7),
labels = c("Never", "Less than once a month", "Once a month", "2-3 times a month", "Once a week", "2-3 times a week","Every day"))
mydata$Q20 <- factor(mydata$Q20,
levels = c(1, 2, 3, 4, 5),
labels = c("Less than 50", "50-100", "101-300", "301-500", "More than 500"))mydata$Q40 <- as.numeric(as.character(mydata$Q40))
mydata$Q40 <- 2025 - mydata$Q40
head(mydata)## # A tibble: 6 × 73
## Q8 Q66 Q10 Q12 Q11 Q48 Q48_5_text Q14a Q14b Q14c Q14d Q14e
## <chr> <chr> <chr> <chr> <fct> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 1 3 3 6 Yes -2 -2 0 1 0 0 0
## 2 1 2 5 6 No 1 -2 0 1 0 0 0
## 3 1 6 5 6 No 3 -2 0 1 0 1 0
## 4 1 2 5 6 Yes -2 -2 1 0 1 1 0
## 5 1 2 2 6 Yes -2 -2 0 1 0 0 0
## 6 1 6 7 7 Yes -2 -2 0 1 0 0 0
## # ℹ 61 more variables: Q14e_text <chr>, Q15 <chr>, Q16 <chr>, Q17 <chr>,
## # Q18 <chr>, Q25a <chr>, Q25b <chr>, Q25c <chr>, Q25d <chr>, Q25e <chr>,
## # Q25f <chr>, Q25g <chr>, Q25h <chr>, Q22a_1...26 <dbl>, Q22b_1...27 <dbl>,
## # Q22c_1...28 <dbl>, Q22d_1...29 <dbl>, Q22e_1...30 <dbl>, Q24 <chr>,
## # Q22a_1...32 <dbl>, Q22b_1...33 <dbl>, Q22c_1...34 <dbl>, Q13 <fct>,
## # Q20 <fct>, Q46 <chr>, Q1a_1 <dbl>, Q1b_1 <dbl>, Q1c_1 <dbl>, Q1d_1 <dbl>,
## # Q1e_1 <dbl>, Q1f_1 <dbl>, Q2a_1 <dbl>, Q2b_1 <dbl>, Q2c_1 <dbl>, …mydata$Q25a <- factor(mydata$Q25a,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))
mydata$Q25b <- factor(mydata$Q25b,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))
mydata$Q25c <- factor(mydata$Q25c,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))
mydata$Q25d <- factor(mydata$Q25d,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))
mydata$Q25e <- factor(mydata$Q25e,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))
mydata$Q25f <- factor(mydata$Q25f,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))
mydata$Q25g <- factor(mydata$Q25g,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))
mydata$Q25h <- factor(mydata$Q25h,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash only", "Mostly cash","Half-half", "Mostly digital","Digital only"))summary(mydata[c(35,36,62,63,65,66,68,69,70)])## Q13 Q20 Q39 Q40
## Never : 3 Less than 50 :88 Male :63 Min. :20.00
## Less than once a month:40 50-100 :43 Female:89 1st Qu.:26.00
## Once a month :45 101-300 :20 Median :38.00
## 2-3 times a month :39 301-500 : 0 Mean :39.02
## Once a week :11 More than 500: 1 3rd Qu.:49.00
## 2-3 times a week :11 Max. :65.00
## Every day : 3
## Q41 Q42 Q43 Q44
## Unfinished Elementary: 0 Employed :118 Physical Work:41 Urban:120
## Finished Elementary : 2 Self-Employed: 25 Office :48 Rural: 32
## Vocational School : 9 Retired : 0 Public Sector:29
## General High School :43 Unemployed : 9 NA's :34
## Undergraduate Degree :55 Other : 0
## Master's Degree :35
## PhD : 8
## Q45
## NLB :56
## OTP :40
## Intesa Sanpaolo :19
## Unicredit :11
## Delavska hranilnica:10
## Revolut : 8
## (Other) : 8Q46:Usage of digital payments relative to cash (0-100 slider)
Q1:Kako pomembni so vam naslednji dejavniki, ko se odločate, katero plačilno metodo uporabiti?
Q1a_1:Security
Ho:Importance of security when making payments does not influence the usage of digital payments.
H1:Importance of security when making payments positively influences the usage of digital payments.
We do not reject the null hypotheses. p-value > 0.05
mydata$Q46 <- as.numeric(as.character(mydata$Q46))
mydata$Q1a_1 <- as.numeric(as.character(mydata$Q1a_1))
library(car)## Loading required package: carDatascatterplotMatrix(mydata[ ,c(37,38)], smooth=FALSE)
library(Hmisc)##
## Attaching package: 'Hmisc'## The following objects are masked from 'package:base':
##
## format.pval, unitsrcorr(as.matrix(mydata[ ,c(37,38)]),
type="pearson")## Q46 Q1a_1
## Q46 1.00 0.01
## Q1a_1 0.01 1.00
##
## n= 152
##
##
## P
## Q46 Q1a_1
## Q46 0.9054
## Q1a_1 0.9054#securityQ1b_1:Speed of transaction
Ho:Importance of speed of transaction when making payments does not influence the usage of digital payments.
H1:Importance of speed of transaction when making payments positively influences the usage of digital payments.
We reject the null hypotheses. p-value < 0.011
mydata$Q46 <- as.numeric(as.character(mydata$Q46))
mydata$Q1b_1 <- as.numeric(as.character(mydata$Q1b_1))
library(car)
scatterplotMatrix(mydata[ ,c(37,39)], smooth=FALSE)
library(Hmisc)
rcorr(as.matrix(mydata[ ,c(37,39)]),
type="pearson")## Q46 Q1b_1
## Q46 1.00 0.21
## Q1b_1 0.21 1.00
##
## n= 152
##
##
## P
## Q46 Q1b_1
## Q46 0.0106
## Q1b_1 0.0106#speed of transactionsQ1c_1:Ease of use
Ho:Importance of Ease of use when making payments does not influence the usage of digital payments.
H1:Importance of Ease of use when making payments positively influences the usage of digital payments.
We reject the null hypotheses. p-value < 0.001
mydata$Q46 <- as.numeric(as.character(mydata$Q46))
mydata$Q1c_1 <- as.numeric(as.character(mydata$Q1c_1))
library(car)
scatterplotMatrix(mydata[ ,c(37,40)], smooth=FALSE)
library(Hmisc)
rcorr(as.matrix(mydata[ ,c(37,40)]),
type="pearson")## Q46 Q1c_1
## Q46 1.00 0.29
## Q1c_1 0.29 1.00
##
## n= 152
##
##
## P
## Q46 Q1c_1
## Q46 3e-04
## Q1c_1 3e-04#ease of useQ1d_1:Convenience
Ho:Importance of Ease of use when making payments does not influence the usage of digital payments.
H1:Importance of Ease of use when making payments positively influences the usage of digital payments.
We reject the null hypotheses. p-value < 0.001
mydata$Q46 <- as.numeric(as.character(mydata$Q46))
mydata$Q1d_1 <- as.numeric(as.character(mydata$Q1d_1))
library(car)
scatterplotMatrix(mydata[ ,c(37,41)], smooth=FALSE)
library(Hmisc)
rcorr(as.matrix(mydata[ ,c(37,41)]),
type="pearson")## Q46 Q1d_1
## Q46 1.00 0.27
## Q1d_1 0.27 1.00
##
## n= 152
##
##
## P
## Q46 Q1d_1
## Q46 6e-04
## Q1d_1 6e-04#convenienceQ1e_1:Privacy
Ho:Importance of Privacy when making payments does not influence the usage of digital payments.
H1:Importance of Privacy when making payments negatively influences the usage of digital payments.
We reject the null hypotheses. p-value < 0.01
mydata$Q46 <- as.numeric(as.character(mydata$Q46))
mydata$Q1e_1 <- as.numeric(as.character(mydata$Q1e_1))
library(car)
scatterplotMatrix(mydata[ ,c(37,42)], smooth=FALSE)
library(Hmisc)
rcorr(as.matrix(mydata[ ,c(37,42)]),
type="pearson")## Q46 Q1e_1
## Q46 1.00 -0.26
## Q1e_1 -0.26 1.00
##
## n= 152
##
##
## P
## Q46 Q1e_1
## Q46 0.0013
## Q1e_1 0.0013#privacyQ1f_1:Spending control
Ho:Importance of Spending control when making payments does not influence the usage of digital payments.
H1:Importance of Spending control when making payments positively influences the usage of digital payments.
We do not reject the null hypotheses. p-value > 0.05
mydata$Q46 <- as.numeric(as.character(mydata$Q46))
mydata$Q1f_1 <- as.numeric(as.character(mydata$Q1f_1))
library(car)
scatterplotMatrix(mydata[ ,c(37,43)], smooth=FALSE)
library(Hmisc)
rcorr(as.matrix(mydata[ ,c(37,43)]),
type="pearson")## Q46 Q1f_1
## Q46 1.00 -0.02
## Q1f_1 -0.02 1.00
##
## n= 152
##
##
## P
## Q46 Q1f_1
## Q46 0.7674
## Q1f_1 0.7674#spending controlQ44: Where do you reside? (0:Urban,1:Rural)
Ho:Rural and urban people use the same proportion of cash and digital payments.
H1:Rural people use more cash than urban people./Urban people use digital payments more.
We reject the null hypotheses. p-value > 0.01
wilcox.test(mydata$Q46~mydata$Q44,
correct=FALSE,
alternative = "greater",
exact=FALSE)##
## Wilcoxon rank sum test
##
## data: mydata$Q46 by mydata$Q44
## W = 2436.5, p-value = 0.009716
## alternative hypothesis: true location shift is greater than 0library(effectsize)
effectsize(wilcox.test(mydata$Q46~mydata$Q44,
correct=FALSE,
alternative = "greater",
exact=FALSE))## r (rank biserial) | 95% CI
## --------------------------------
## 0.27 | [0.09, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].interpret_rank_biserial(0.27, rules="funder2019")## [1] "medium"
## (Rules: funder2019)Q15:Pri plačilih za manjše vrednosti (do 10 €) se mi zdi gotovina hitrejši način plačila od digitalnih plačil.
Ho:Cash and digital payments are evenly popular for small-value transactions (up to €10) because of convenience.
H1:Cash is more popular for small-value transactions (up to €10) because of convenience.
We do not reject the null hypotheses.
#if faster, 10eur
mydata$Q15 <- as.numeric(as.character(mydata$Q15))
shapiro.test(mydata$Q15)##
## Shapiro-Wilk normality test
##
## data: mydata$Q15
## W = 0.86315, p-value = 1.443e-10wilcox.test(mydata$Q15,
mu=4,
alternative = "greater",
correct=FALSE)##
## Wilcoxon signed rank test
##
## data: mydata$Q15
## V = 3009, p-value = 1
## alternative hypothesis: true location is greater than 4Q17:Rad/a uporabljam mobilne plačilne platforme (kot so Apple Pay, Revolut, PayPal, Flik), ker so priročne.
Ho:Convenience does not influence the usage of mobile payment platforms such as Apple Pay, Revolut, PayPal, Flik.
H1:Convenience significantly influences the usage of mobile payment platforms such as Apple Pay, Revolut, PayPal, Flik.
We reject the null hypotheses. p-value < 0.001
#flik, convenient
mydata$Q17 <- as.numeric(as.character(mydata$Q17))
shapiro.test(mydata$Q17)##
## Shapiro-Wilk normality test
##
## data: mydata$Q17
## W = 0.78751, p-value = 1.407e-13wilcox.test(mydata$Q17,
mu=4,
alternative = "greater",
correct=FALSE)##
## Wilcoxon signed rank test
##
## data: mydata$Q17
## V = 8734, p-value = 3.884e-11
## alternative hypothesis: true location is greater than 4effectsize(wilcox.test(mydata$Q17,
mu=4,
alternative = "greater",
correct=FALSE))## r (rank biserial) | 95% CI
## --------------------------------
## 0.61 | [0.50, 1.00]
##
## - Deviation from a difference of 4.
## - One-sided CIs: upper bound fixed at [1.00].interpret_rank_biserial(0.61, rules="funder2019")## [1] "very large"
## (Rules: funder2019)Q18:Verjetno bom uporabljal/a mobilne plačilne platforme (kot so Apple Pay, Revolut, PayPal, Flik), če mi jih priporočijo prijatelji, družina ali vrstniki.
Ho:Recommendations by friends, family, or peers do not influence the usage of mobile payment platforms such as Apple Pay, Revolut, PayPal, Flik.
H1:Recommendations by friends, family, or peers significantly positively influence the usage of mobile payment platforms such as Apple Pay, Revolut, PayPal, Flik.
We reject the null hypotheses. p-value < 0.001
#flik, family
mydata$Q18 <- as.numeric(as.character(mydata$Q18))
shapiro.test(mydata$Q18)##
## Shapiro-Wilk normality test
##
## data: mydata$Q18
## W = 0.87963, p-value = 9.066e-10wilcox.test(mydata$Q18,
mu=4,
alternative = "greater",
correct=FALSE)##
## Wilcoxon signed rank test
##
## data: mydata$Q18
## V = 8163, p-value = 4.305e-09
## alternative hypothesis: true location is greater than 4library(effectsize)
effectsize(wilcox.test(mydata$Q18,
mu=4,
alternative = "greater",
correct=FALSE))## r (rank biserial) | 95% CI
## --------------------------------
## 0.54 | [0.42, 1.00]
##
## - Deviation from a difference of 4.
## - One-sided CIs: upper bound fixed at [1.00].interpret_rank_biserial(0.54, rules="funder2019")## [1] "very large"
## (Rules: funder2019)Q10:Raje imam pri sebi gotovino, ker ni vedno mogoče plačati z drugimi plačilnimi sredstvi.
Ho:Limited infrastructure for digital payments does not influence the use of cash.
H1:Limited infrastructure for digital payments increases the use of cash.
We do not reject the null hypotheses. p-value > 0.05
#infrastructure, cash
mydata$Q10 <- as.numeric(as.character(mydata$Q10))
shapiro.test(mydata$Q10)##
## Shapiro-Wilk normality test
##
## data: mydata$Q10
## W = 0.91107, p-value = 4.992e-08wilcox.test(mydata$Q10,
mu=4,
alternative = "greater",
correct=FALSE)##
## Wilcoxon signed rank test
##
## data: mydata$Q10
## V = 6179.5, p-value = 0.05264
## alternative hypothesis: true location is greater than 4