NLB segmentation
Ana Marija Dimitrova
2025-02-03
library(readr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union# Load the CSV file
NLB_data <- read.csv("nlb_data.csv", sep = ";")
# Remove columns 2 to 8
NLB_data <- NLB_data %>% select(-c(2:8, 101:116))
# Display the first few rows of the modified dataset
head(NLB_data)## status Q1 Q3a
## 1 Status Koliko ste stari? Gotovina
## 2 6 7 3
## 3 6 9 2
## 4 6 9 2
## 5 6 7 3
## 6 6 7 2
## Q3b
## 1 Plačilo z debetno ali kreditno kartico (uporaba fizične kartice)
## 2 2
## 3 5
## 4 4
## 5 5
## 6 5
## Q3c Q3d Q4a Q4b
## 1 Plačilo s telefonom Drugo (PayPal, Stripe,..) Nakupi do 10€ Nakupi med 11-99€
## 2 5 2 4 3
## 3 1 1 2 1
## 4 4 1 2 2
## 5 5 1 2 2
## 6 5 1 2 1
## Q4c Q4d
## 1 Nakupi med 100-1000€ Nakupi nad 1000€
## 2 2 1
## 3 1 1
## 4 1 1
## 5 1 1
## 6 1 1
## Q5
## 1 Kako se običajno odzovete, če prodajalec ne sprejema digitalnih plačil?
## 2 2
## 3 1
## 4 2
## 5 1
## 6 1
## Q5_4_text Q6a
## 1 Drugo (prosim navedite): Plača ali zaslužek iz študentskega dela
## 2 -2 3
## 3 -2 4
## 4 -2 3
## 5 -2 3
## 6 -2 4
## Q6b Q6c
## 1 Žepnina (od družinskih članov) Darila (ob rojstnih dnevih, praznikih...)
## 2 2 1
## 3 2 1
## 4 3 1
## 5 3 2
## 6 3 3
## Q6d
## 1 Delo na črno ali priložnostno delo (varstvo otrok, tutorstvo...)
## 2 1
## 3 4
## 4 4
## 5 4
## 6 4
## Q6e
## 1 Državne in/ali socialne pomoči
## 2 3
## 3 4
## 4 4
## 5 4
## 6 4
## Q6f
## 1 Državne in druge oblike štipendij (Zoisova, kadrovska...)
## 2 3
## 3 4
## 4 4
## 5 3
## 6 4
## Q6g
## 1 Donosi iz naložb (delnice, obveznice, kripto itd.)
## 2 3
## 3 3
## 4 2
## 5 4
## 6 4
## Q7
## 1 Ali vi varčujete denar? (Vprašanje NE zajema morebitnih privarčevanih sredstev, ki so jih za vas varčevali oziroma jih varčujejo starši ali drugi družinski člani)
## 2 1
## 3 1
## 4 1
## 5 1
## 6 2
## Q8a
## 1 NA
## 2 5
## 3 7
## 4 7
## 5 7
## 6 -2
## Q9a
## 1 Običajno denar porabim v obliki, v kateri sem ga prejel_a (ne spreminjam oblike prejetega denarja npr. polaganje gotovine na banko ali dvigovanje denarja iz kartice).
## 2 6
## 3 7
## 4 6
## 5 6
## 6 7
## Q9b
## 1 Zaradi varnosti svojih osebnih podatkov se počutim zaskrbljenega_o, ko uporabljam digitalne načine plačevanja (npr. spletno bančništvo, mobilne denarnice).
## 2 3
## 3 6
## 4 2
## 5 5
## 6 4
## Q9c
## 1 Digitalno plačevanje se mi zdi manj varno kakor gotovinsko plačevanje.
## 2 5
## 3 3
## 4 3
## 5 6
## 6 7
## Q9d
## 1 Več zaupanja imam v digitalne načine plačevanja, če ponujajo funkcije, kot so dvofaktorska avtentikacija ali biometrična preverjanja.
## 2 6
## 3 6
## 4 6
## 5 7
## 6 4
## Q9e
## 1 Počutim se varno, ko s seboj nosim gotovino.
## 2 4
## 3 3
## 4 3
## 5 4
## 6 4
## Q9f
## 1 Raje uporabljam digitalna plačila, ker so bolj priročna in prihranijo čas.
## 2 7
## 3 7
## 4 7
## 5 7
## 6 7
## Q9g
## 1 Raje uporabljam gotovino, da bi se izognil_a pretirani porabi, (ob porabljanju gotovine se bolj zavedam svojega zapravljanja in je le-to bolj zavestno).
## 2 6
## 3 1
## 4 1
## 5 1
## 6 4
## Q9h
## 1 Gotovino najpogosteje uporabim tam, kjer digitalna plačila niso mogoča, v nasprotnem primeru pa se raje poslužujem digitalnega plačevanja.
## 2 7
## 3 6
## 4 7
## 5 7
## 6 7
## Q31_2a Q31_2b Q31_2c
## 1 Enostavnost uporabe Hitrost transakcije Možnost uporabe v trgovinah
## 2 7 7 6
## 3 6 7 5
## 4 7 6 6
## 5 7 7 7
## 6 7 7 7
## Q31_2d Q31_2e
## 1 Varnost plačilnega sredstva Funkcije za sledenje in načrtovanje proračuna
## 2 6 3
## 3 7 7
## 4 6 4
## 5 7 7
## 6 7 7
## Q31_2f Q10a Q10b
## 1 Zasebnost uporabe Gotovina (Fizična) Debetna kartica
## 2 6 6 6
## 3 6 3 7
## 4 5 6 6
## 5 7 6 5
## 6 7 7 4
## Q10c Q10d
## 1 (Fizična) kreditna kartica Plačevanje s telefonom (Flik, Apple pay...)
## 2 6 7
## 3 7 3
## 4 4 6
## 5 4 6
## 6 4 4
## Q10e Q11a Q11b
## 1 Neobanke (Revolut, N26...) Gotovina (Fizična) debetna kartica
## 2 6 5 6
## 3 6 7 7
## 4 6 4 7
## 5 6 3 6
## 6 4 7 7
## Q11c Q11d Q11e
## 1 (Fizična) kreditna kartica Plačevanje s telefonom Neobanke (Revolut, N26...)
## 2 6 7 6
## 3 7 6 6
## 4 7 7 7
## 5 6 7 7
## 6 7 7 7
## Q12a Q12b Q12c
## 1 Gotovina (Fizična) debetna kartica (Fizična) kreditna kartica
## 2 6 7 7
## 3 6 6 6
## 4 7 7 7
## 5 6 7 7
## 6 7 7 7
## Q12d Q12e Q13a
## 1 Plačevanje s telefonom Neobanke (Revolut, N26...) Gotovina
## 2 7 6 5
## 3 6 6 5
## 4 7 7 4
## 5 6 6 1
## 6 7 4 7
## Q13b Q13c Q13d
## 1 (Fizična) debetna kartica (Fizična) kreditna kartica Plačevanje s telefonom
## 2 6 6 7
## 3 7 7 7
## 4 7 7 7
## 5 6 6 7
## 6 7 7 7
## Q13e Q14a Q14b
## 1 Neobanke (Revolut, N26...) Gotovina (Fizična) debetna kartica
## 2 7 7 6
## 3 7 7 1
## 4 7 6 5
## 5 7 7 4
## 6 7 4 7
## Q14c Q14d Q14e
## 1 (Fizična) kreditna kartica Plačevanje s telefonom Neobanke (Revolut, N26...)
## 2 5 5 6
## 3 1 1 1
## 4 5 5 5
## 5 4 4 4
## 6 7 7 7
## Q15a Q15b Q15c
## 1 Gotovina (Fizična) debetna kartica (Fizična) kreditna kartica
## 2 7 5 5
## 3 2 7 4
## 4 5 7 7
## 5 6 5 1
## 6 4 7 7
## Q15d Q15e
## 1 Plačevanje s telefonom Neobanke (Revolut, N26...)
## 2 3 3
## 3 1 6
## 4 7 7
## 5 5 5
## 6 7 7
## Q16a
## 1 Izbiram načine plačevanja, kot jih izbirajo moji prijatelji.
## 2 5
## 3 4
## 4 4
## 5 7
## 6 4
## Q16b
## 1 Izbiram načine plačevanja, kot jih izbirajo moji družinski člani.
## 2 2
## 3 4
## 4 4
## 5 7
## 6 4
## Q17 Q17_5_text
## 1 Kako si najpogosteje delite stroške med prijatelji? Drugo (prosim navedite):
## 2 2 -2
## 3 2 -2
## 4 2 -2
## 5 2 -2
## 6 2 -2
## Q18a Q18b
## 1 Lahko nakažem točno vsoto Da se izognem plačevanju z gotovino
## 2 1 0
## 3 1 1
## 4 1 1
## 5 1 1
## 6 1 1
## Q18c
## 1 Ker je proces hiter in priročen
## 2 1
## 3 1
## 4 1
## 5 1
## 6 1
## Q18d
## 1 Ker imam zabeležene svoje transakcije in tako lažje vodim svoje finance
## 2 0
## 3 0
## 4 1
## 5 1
## 6 1
## Q18e Q18e_text
## 1 Drugo (prosim navedite): Drugo (prosim navedite):
## 2 0 -2
## 3 0 -2
## 4 0 -2
## 5 0 -2
## 6 0 -2
## Q19a Q19b Q19c
## 1 Goljufije (npr. kraja denarja) Razkritje osebnih podatkov Kraja identitete
## 2 3 5 3
## 3 5 5 6
## 4 3 3 3
## 5 5 5 5
## 6 7 7 7
## Q19d
## 1 Izguba dostopa zaradi hekerskega napada
## 2 3
## 3 7
## 4 3
## 5 6
## 6 7
## Q20
## 1 Ali ste bili vi (oz. kdo od vaših bližnjih) žrtev spletne goljufije?
## 2 2
## 3 3
## 4 4
## 5 4
## 6 1
## Q21a
## 1 Pogosteje uporabljam gotovino v neznanih ali sumljivih situacijah (npr. med potovanji).
## 2 0
## 3 0
## 4 -2
## 5 -2
## 6 -1
## Q21b
## 1 Pogosteje uporabljam digitalna plačilna sredstva, kot so virtualne ali enkratne kartice, ki jih omogočajo neobanke, v neznanih ali sumljivih situacijah (npr. med potovanji).
## 2 0
## 3 0
## 4 -2
## 5 -2
## 6 -1
## Q21c
## 1 Postal_a sem bolj previden_na pri spletnih plačilih.
## 2 1
## 3 1
## 4 -2
## 5 -2
## 6 -1
## Q21d
## 1 Preklopil_a sem na varnejše plačilne možnosti (npr. mobilne denarnice z avtentikacijo).
## 2 0
## 3 0
## 4 -2
## 5 -2
## 6 -1
## Q21e
## 1 Moje vedenje se ni spremenilo.
## 2 0
## 3 0
## 4 -2
## 5 -2
## 6 -1
## Q22
## 1 Če bi imeli možnost, ali bi popolnoma preklopili na digitalna plačila?
## 2 2
## 3 2
## 4 2
## 5 1
## 6 1
## Q23
## 1 Katerega spola ste?
## 2 1
## 3 2
## 4 2
## 5 2
## 6 2
## Q24
## 1 Katera je vaša najvišja dosežena stopnja dosežene izobrazbe?
## 2 6
## 3 5
## 4 4
## 5 4
## 6 4
## Q25 Q25_5_text
## 1 Kakšen je vaš trenutni status? Drugo:
## 2 1 -2
## 3 1 -2
## 4 1 -2
## 5 1 -2
## 6 1 -2
## Q26
## 1 Kakšna je višina vaših trenutnih neto mesečnih prihodkov?
## 2 2
## 3 2
## 4 3
## 5 2
## 6 4
## Q27
## 1 Katero banko trenutno uporabljate kot primarno banko?
## 2 2
## 3 2
## 4 7
## 5 1
## 6 1
## Q27_7_text
## 1 Drugo (prosim navedite):
## 2 -2
## 3 -2
## 4 Unicredit
## 5 -2
## 6 -2Dataset overview
- Unit of observation: Each row represents a single respondent from the questionnaire, which was completed by young people aged 18 to 27.
- Sample size: The dataset includes responses from a total of 441 young individuals.
Variables description
Q1a - Age
Q3 - How many times a month do you use the following payment methods on average?
- Q3a - Cash
- Q3b - Debit or Credit (physical) cards
- Q3c - Phone
- Q3d - Other (PayPal, Stripe..)
Q4 - How often do you use cash payment for the following purchases?
- Q4a - Purchases up to €10
- Q4b - Purchases between €11 and €99
- Q4c - Purchases between €100 and €1000
- Q4d - Purchases over €1000
Q5 - How do you usually respond if a merchant does not accept digital payments?
- Q5a - I prefer to go elsewhere and pay with a digital payment method.
- Q5b - I pay in the form available, even if it means withdrawing cash from an ATM.
- Q5c - I have not encountered such a situation yet.
- Q5d - Other (please specify).
Q6 - Which of the following income sources do you have, and how do you receive them?
- Q6a - Salary or earnings from student work
- Q6b - Pocket Money (from family members)
- Q6c - Gifts (for birthdays, holidays, etc.)
- Q6d - Unreported or occasional work (childcare, tutoring, etc.)
- Q6e - Government and/or social benefits
- Q6f - Government and other forms of scholarships (e.g., Zois, corporate)
- Q6g - Returns from investments (stocks, bonds, cryptocurrencies, etc.)
Q7 - Do you save money? (This question does NOT include savings from parents or family members.)
- Q7a - Yes
- Q7b - No
Q8a - In what form do you save money? (Digital vs. cash savings)
Q9 - Various attitudes towards digital and cash payments.
- Q9a - I usually spend money in the form in which I received it.
- Q9b - I feel concerned about the security of my personal information when using digital payment methods.
- Q9c - I find digital payments less secure than cash payments.
- Q9d - I have more confidence in digital payment methods if they offer features like two-factor authentication.
- Q9e - I feel safe when I carry cash with me.
- Q9f - I prefer to use digital payments because they are more convenient and save time.
- Q9g - I prefer to use cash to avoid overspending.
- Q9h - I use cash only when digital payments are not possible.
Q10 - How safe do you think the following payment methods are?
- Q10a - Cash
- Q10b - (Physical) Debit Card
- Q10c - (Physical) Credit Card
- Q10d - Paying with your phone (Flik, Apple Pay…)
- Q10e - Neobanks (Revolut, N26…)
Q11 - How easy do you find the following payment methods to use?
- Q11a - Cash
- Q11b - (Physical) Debit Card
- Q11c - (Physical) Credit Card
- Q11d - Paying with your phone (Flik, Apple Pay…)
- Q11e - Neobanks (Revolut, N26…)
Q12 - How accepted do you think the following payment methods are in stores in your environment?
- Q12a - Cash
- Q12b - (Physical) Debit Card
- Q12c - (Physical) Credit Card
- Q12d - Paying with your phone (Flik, Apple Pay…)
- Q12e - Neobanks (Revolut, N26…)
Q13 - What do you consider the fastest payment method?
- Q13a - Cash
- Q13b - (Physical) Debit Card
- Q13c - (Physical) Credit Card
- Q13d - Paying with your phone (Flik, Apple Pay…)
- Q13e - Neobanks (Revolut, N26…)
Q14 - Which payment method do you consider the most private?
- Q14a - Cash
- Q14b - (Physical) Debit Card
- Q14c - (Physical) Credit Card
- Q14d - Paying with your phone (Flik, Apple Pay…)
- Q14e - Neobanks (Revolut, N26…)
Q15 - Which payment method helps you control spending the most?
- Q15a - Cash
- Q15b - (Physical) Debit Card
- Q15c - (Physical) Credit Card
- Q15d - Paying with your phone (Flik, Apple Pay…)
- Q15e - Neobanks (Revolut, N26…)
Q16 - Social influence on payment method choice.
- Q16a - I choose the payment methods my friends choose.
- Q16b - I choose the payment methods my family members choose.
Q17 - How do you most often share expenses among friends?
- Q17a - With cash
- Q17b - Through mobile applications (Flik, Revolut, PayPal…)
- Q17c - By bank transfer
- Q17d - I don’t share expenses among friends
- Q17e - Other (please specify)
Q18 - Reasons for preferring digital payments.
- Q18a - I can quote the exact sum.
- Q18b - To avoid paying with cash.
- Q18c - Because the process is quick and convenient.
- Q18d - Because I have my transactions recorded and it is easier to manage finances.
- Q18e - Other (please specify).
Q19 - Concerns about digital payment security.
- Q19a - Fraud (e.g., stealing money)
- Q19b - Disclosure of Personal Information
- Q19c - Identity theft
- Q19d - Loss of access due to a hacker attack
Q20 - Experience with online fraud.
- Q20a - Yes, it happened to me.
- Q20b - Yes, I know people who have had this happen.
- Q20c - Yes, it has happened to me and others I know.
- Q20d - I’ve never encountered such a situation.
Q21 - How did this affect your behavior in further payment habits?
- Q21a - I use cash more often in unfamiliar or suspicious situations (e.g., when traveling).
- Q21b - I use digital payment methods (e.g., virtual or disposable cards facilitated by neobanks) more often in unfamiliar or suspicious situations.
- Q21c - I am more cautious with online payments.
- Q21d - I switched to more secure payment options (e.g., mobile wallets with authentication).
- Q21e - My behavior hasn’t changed.
Q22 - If we had the opportunity, would you switch to digital payments entirely?
- Q22a - Yes, immediately.
- Q22b - I would consider it, but I wouldn’t want to give up cash completely.
- Q22c - No, I prefer to use cash.
- Q22d - I don’t know.
Q23 - What is your gender?
- Q23a - Man.
- Q23b - Woman.
- Q23c - Another.
- Q23d - I don’t want to answer.
Q24 - What is your highest level of educational attainment?
- Q24a - Unfinished primary school.
- Q24b - Completed primary school.
- Q24c - Completed lower or secondary vocational education.
- Q24d - Completed secondary professional or general education.
- Q24e - Completed tertiary professional or tertiary professional education (including 1st Bologna level).
Q25 - What is your current status?
- Q25a - Student.
- Q25b - Employed.
- Q25c - Self-employed.
- Q25d - Unemployed.
- Q25e - Other (please specify).
Q26 - What is your current net monthly income?
- Q26a - 0-200 EUR.
- Q26b - 201-500 EUR.
- Q26c - 501-800 EUR.
- Q26d - 801-1300 EUR.
- Q26e - More than 1300 EUR.
Q27 - Which bank do you currently use as your primary bank?
- Q27a - NLB.
- Q27b - OTP.
- Q27c - Intesa Sanpaolo.
- Q27d - Sparkasse.
- Q27e - Addiko Bank.
- Q27f - Workers’ Savings Bank.
- Q27g - Other (please specify).
Data manipulation
#Remove first row
NLB_data <- NLB_data[-1, ]
#Remove all questionnaires with non valid status
library(dplyr)
NLB_data <- NLB_data %>%
filter(!status == 5)
#Remove status column
NLB_data <- NLB_data[ , -1]
#Remove all under 18/over 27
library(dplyr)
NLB_data <- NLB_data %>%
filter(!Q1 %in% c(1, 12))# Factoring
# Age (Q1)
NLB_data$Q1F <- factor(NLB_data$Q1,
levels = c(2:11),
labels = c(18:27))
# Q5
NLB_data$Q5F <- factor(NLB_data$Q5,
levels = c(1, 2, 3, 4),
labels = c("Pay digital elsewhere", "Pay as available", "Never occurred", "Other"))
# Q7
NLB_data$Q7F <- factor(NLB_data$Q7,
levels = c(1, 2),
labels = c("Yes", "No"))
# Q17
NLB_data$Q17F <- factor(NLB_data$Q17,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash", "Mobile apps", "Bank transfer", "Don't share", "Other"))
# Q20
NLB_data$Q20F <- factor(NLB_data$Q20,
levels = c(1, 2, 3, 4),
labels = c("Yes - me", "Yes - others", "Yes - both", "No"))
# Q22
NLB_data$Q22F <- factor(NLB_data$Q22,
levels = c(1, 2, 3, 4),
labels = c("Fully digital", "Balance digital-cash", "Cash", "Don't know"))
# Q23
NLB_data$Q23F <- factor(NLB_data$Q23,
levels = c(1, 2, 3, 4),
labels = c("Man", "Woman", "Other", "Don't want to answer"))
# Q24
NLB_data$Q24F <- factor(NLB_data$Q24,
levels = c(1, 2, 3, 4, 5, 6, 7),
labels = c("Unfinished primary", "Primary school", "Vocational education", "High School", "Bachelor Degree", "Master Degree", "PhD" ))
# Q25
NLB_data$Q25F <- factor(NLB_data$Q25,
levels = c(1, 2, 3, 4, 5),
labels = c("Student", "Employed", "Self-employed", "Unemployed", "Other"))
# Q26
NLB_data$Q26F <- factor(NLB_data$Q26,
levels = c(1, 2, 3, 4, 5),
labels = c("0-200 EUR", "201-500 EUR", "501-800 EUR", "801-1300 EUR", "Above 1300 EUR"))
# Q27
NLB_data$Q27F <- factor(NLB_data$Q27,
levels = c(1, 2, 3, 4, 5, 6, 7),
labels = c("NLB", "OTP", "Intesa Sanpaolo", "Sparkasse", "Addiko Bank", "Delovska Hranilnica", "Other"))#Q3
NLB_data$Q3a <- factor(NLB_data$Q3a,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "1-3 monthly", "1 per week", "Several times a week", "Daily"))NLB_data$Q3b <- factor(NLB_data$Q3b,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "1-3 monthly", "1 per week", "Several times a week", "Daily"))NLB_data$Q3c <- factor(NLB_data$Q3c,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "1-3 monthly", "1 per week", "Several times a week", "Daily"))NLB_data$Q3d <- factor(NLB_data$Q3d,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "1-3 monthly", "1 per week", "Several times a week", "Daily"))#Q4
NLB_data$Q4a <- factor(NLB_data$Q4a,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "Less than half", "Half", "More than half", "Always"))NLB_data$Q4b <- factor(NLB_data$Q4b,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "Less than half", "Half", "More than half", "Always"))NLB_data$Q4c <- factor(NLB_data$Q4c,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "Less than half", "Half", "More than half", "Always"))NLB_data$Q4d <- factor(NLB_data$Q4d,
levels = c(1, 2, 3, 4, 5),
labels = c("Never", "Less than half", "Half", "More than half", "Always"))#Q6
NLB_data$Q6a <- factor(NLB_data$Q6a,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash", "Cash&Digitally", "Digitally", "Not using", "Don't want to answer"))#Q6
NLB_data$Q6b <- factor(NLB_data$Q6b,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash", "Cash&Digitally", "Digitally", "Not using", "Don't want to answer"))#Q6
NLB_data$Q6c <- factor(NLB_data$Q6c,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash", "Cash&Digitally", "Digitally", "Not using", "Don't want to answer"))#Q6
NLB_data$Q6d <- factor(NLB_data$Q6d,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash", "Cash&Digitally", "Digitally", "Not using", "Don't want to answer"))#Q6
NLB_data$Q6e <- factor(NLB_data$Q6e,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash", "Cash&Digitally", "Digitally", "Not using", "Don't want to answer"))#Q6
NLB_data$Q6f <- factor(NLB_data$Q6f,
levels = c(1, 2, 3, 4, 5),
labels = c("Cash", "Cash&Digitally", "Digitally", "Not using", "Don't want to answer"))head(NLB_data)## Q1 Q3a Q3b Q3c Q3d
## 1 7 1 per week 1-3 monthly Daily 1-3 monthly
## 2 9 1-3 monthly Daily Never Never
## 3 9 1-3 monthly Several times a week Several times a week Never
## 4 7 1 per week Daily Daily Never
## 5 7 1-3 monthly Daily Daily Never
## 6 9 1 per week 1 per week Never 1-3 monthly
## Q4a Q4b Q4c Q4d Q5 Q5_4_text Q6a
## 1 More than half Half Less than half Never 2 -2 Digitally
## 2 Less than half Never Never Never 1 -2 Not using
## 3 Less than half Less than half Never Never 2 -2 Digitally
## 4 Less than half Less than half Never Never 1 -2 Digitally
## 5 Less than half Never Never Never 1 -2 Not using
## 6 More than half Half Less than half Never 2 -2 Digitally
## Q6b Q6c Q6d Q6e Q6f Q6g Q7 Q8a Q9a
## 1 Cash&Digitally Cash Cash Digitally Digitally 3 1 5 6
## 2 Cash&Digitally Cash Not using Not using Not using 3 1 7 7
## 3 Digitally Cash Not using Not using Not using 2 1 7 6
## 4 Digitally Cash&Digitally Not using Not using Digitally 4 1 7 6
## 5 Digitally Digitally Not using Not using Not using 4 2 -2 7
## 6 Not using Cash Cash Digitally Digitally 4 2 -2 7
## Q9b Q9c Q9d Q9e Q9f Q9g Q9h Q31_2a Q31_2b Q31_2c Q31_2d Q31_2e Q31_2f Q10a
## 1 3 5 6 4 7 6 7 7 7 6 6 3 6 6
## 2 6 3 6 3 7 1 6 6 7 5 7 7 6 3
## 3 2 3 6 3 7 1 7 7 6 6 6 4 5 6
## 4 5 6 7 4 7 1 7 7 7 7 7 7 7 6
## 5 4 7 4 4 7 4 7 7 7 7 7 7 7 7
## 6 3 5 7 7 5 6 5 5 3 7 7 4 4 7
## Q10b Q10c Q10d Q10e Q11a Q11b Q11c Q11d Q11e Q12a Q12b Q12c Q12d Q12e Q13a
## 1 6 6 7 6 5 6 6 7 6 6 7 7 7 6 5
## 2 7 7 3 6 7 7 7 6 6 6 6 6 6 6 5
## 3 6 4 6 6 4 7 7 7 7 7 7 7 7 7 4
## 4 5 4 6 6 3 6 6 7 7 6 7 7 6 6 1
## 5 4 4 4 4 7 7 7 7 7 7 7 7 7 4 7
## 6 6 6 5 5 6 7 7 6 6 6 7 7 6 6 2
## Q13b Q13c Q13d Q13e Q14a Q14b Q14c Q14d Q14e Q15a Q15b Q15c Q15d Q15e Q16a
## 1 6 6 7 7 7 6 5 5 6 7 5 5 3 3 5
## 2 7 7 7 7 7 1 1 1 1 2 7 4 1 6 4
## 3 7 7 7 7 6 5 5 5 5 5 7 7 7 7 4
## 4 6 6 7 7 7 4 4 4 4 6 5 1 5 5 7
## 5 7 7 7 7 4 7 7 7 7 4 7 7 7 7 4
## 6 7 7 6 6 5 7 7 7 7 7 6 5 3 5 3
## Q16b Q17 Q17_5_text Q18a Q18b Q18c Q18d Q18e Q18e_text Q19a Q19b Q19c Q19d
## 1 2 2 -2 1 0 1 0 0 -2 3 5 3 3
## 2 4 2 -2 1 1 1 0 0 -2 5 5 6 7
## 3 4 2 -2 1 1 1 1 0 -2 3 3 3 3
## 4 7 2 -2 1 1 1 1 0 -2 5 5 5 6
## 5 4 2 -2 1 1 1 1 0 -2 7 7 7 7
## 6 5 2 -2 1 0 0 0 0 -2 5 4 6 6
## Q20 Q21a Q21b Q21c Q21d Q21e Q22 Q23 Q24 Q25 Q25_5_text Q26 Q27 Q27_7_text
## 1 2 0 0 1 0 0 2 1 6 1 -2 2 2 -2
## 2 3 0 0 1 0 0 2 2 5 1 -2 2 2 -2
## 3 4 -2 -2 -2 -2 -2 2 2 4 1 -2 3 7 Unicredit
## 4 4 -2 -2 -2 -2 -2 1 2 4 1 -2 2 1 -2
## 5 1 -1 -1 -1 -1 -1 1 2 4 1 -2 4 1 -2
## 6 2 1 0 0 0 0 4 2 6 1 -2 2 1 -2
## Q1F Q5F Q7F Q17F Q20F Q22F
## 1 23 Pay as available Yes Mobile apps Yes - others Balance digital-cash
## 2 25 Pay digital elsewhere Yes Mobile apps Yes - both Balance digital-cash
## 3 25 Pay as available Yes Mobile apps No Balance digital-cash
## 4 23 Pay digital elsewhere Yes Mobile apps No Fully digital
## 5 23 Pay digital elsewhere No Mobile apps Yes - me Fully digital
## 6 25 Pay as available No Mobile apps Yes - others Don't know
## Q23F Q24F Q25F Q26F Q27F
## 1 Man Master Degree Student 201-500 EUR OTP
## 2 Woman Bachelor Degree Student 201-500 EUR OTP
## 3 Woman High School Student 501-800 EUR Other
## 4 Woman High School Student 201-500 EUR NLB
## 5 Woman High School Student 801-1300 EUR NLB
## 6 Woman Master Degree Student 201-500 EUR NLBDescriptive statistics
library(dplyr)
# Convert character columns in specified ranges to numeric
NLB_data <- NLB_data %>%
mutate(across(c(2:9, 11:18, 21:66, 68:78, 80:84, 89, 92),
~ ifelse(!is.na(.), as.numeric(.), .)))## Warning: There were 5 warnings in `mutate()`.
## The first warning was:
## ℹ In argument: `across(...)`.
## Caused by warning in `ifelse()`:
## ! NAs introduced by coercion
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 4 remaining warnings.summary(NLB_data)## Q1 Q3a Q3b Q3c
## Length:304 Min. :1.000 Min. :1.00 Min. :1.000
## Class :character 1st Qu.:2.000 1st Qu.:2.00 1st Qu.:1.000
## Mode :character Median :2.000 Median :4.00 Median :4.000
## Mean :2.737 Mean :3.51 Mean :3.332
## 3rd Qu.:4.000 3rd Qu.:4.00 3rd Qu.:5.000
## Max. :5.000 Max. :5.00 Max. :5.000
##
## Q3d Q4a Q4b Q4c Q4d
## Min. :1.000 Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000
## 1st Qu.:1.000 1st Qu.:2.000 1st Qu.:1.00 1st Qu.:1.000 1st Qu.:1.000
## Median :1.000 Median :2.000 Median :2.00 Median :1.000 Median :1.000
## Mean :1.546 Mean :2.421 Mean :2.03 Mean :1.576 Mean :1.398
## 3rd Qu.:2.000 3rd Qu.:3.000 3rd Qu.:2.00 3rd Qu.:2.000 3rd Qu.:1.000
## Max. :5.000 Max. :5.000 Max. :5.00 Max. :5.000 Max. :5.000
##
## Q5 Q5_4_text Q6a Q6b Q6c
## Length:304 Min. :-2 Min. :1.000 Min. :1.000 Min. :1.00
## Class :character 1st Qu.:-2 1st Qu.:3.000 1st Qu.:1.750 1st Qu.:1.00
## Mode :character Median :-2 Median :3.000 Median :3.000 Median :1.00
## Mean :-2 Mean :2.905 Mean :2.651 Mean :1.28
## 3rd Qu.:-2 3rd Qu.:3.000 3rd Qu.:4.000 3rd Qu.:1.00
## Max. :-2 Max. :4.000 Max. :5.000 Max. :5.00
## NA's :15
## Q6d Q6e Q6f Q6g
## Min. :1.000 Min. :1.000 Min. :2.000 Min. :1.000
## 1st Qu.:1.000 1st Qu.:4.000 1st Qu.:3.000 1st Qu.:3.000
## Median :4.000 Median :4.000 Median :4.000 Median :4.000
## Mean :3.039 Mean :3.796 Mean :3.539 Mean :3.674
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
##
## Q7 Q8a Q9a Q9b
## Length:304 Min. :-2.000 Min. :1.000 Min. :1.000
## Class :character 1st Qu.: 1.000 1st Qu.:4.000 1st Qu.:1.000
## Mode :character Median : 4.000 Median :6.000 Median :3.000
## Mean : 3.395 Mean :5.316 Mean :3.115
## 3rd Qu.: 7.000 3rd Qu.:7.000 3rd Qu.:4.000
## Max. : 7.000 Max. :7.000 Max. :7.000
##
## Q9c Q9d Q9e Q9f
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.000 1st Qu.:4.000 1st Qu.:3.000 1st Qu.:6.000
## Median :4.000 Median :6.000 Median :4.000 Median :7.000
## Mean :3.655 Mean :5.359 Mean :4.135 Mean :6.046
## 3rd Qu.:5.000 3rd Qu.:7.000 3rd Qu.:5.000 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## Q9g Q9h Q31_2a Q31_2b Q31_2c
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1 Min. :1.000
## 1st Qu.:1.000 1st Qu.:5.000 1st Qu.:6.000 1st Qu.:6 1st Qu.:6.000
## Median :4.000 Median :6.000 Median :7.000 Median :7 Median :7.000
## Mean :3.441 Mean :5.704 Mean :6.105 Mean :6 Mean :6.168
## 3rd Qu.:5.000 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7 Max. :7.000
##
## Q31_2d Q31_2e Q31_2f Q10a
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:5.000 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.000
## Median :7.000 Median :5.000 Median :6.000 Median :6.000
## Mean :6.076 Mean :5.201 Mean :5.658 Mean :5.503
## 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## Q10b Q10c Q10d Q10e
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.000
## Median :5.000 Median :5.000 Median :5.000 Median :5.000
## Mean :5.138 Mean :4.947 Mean :5.174 Mean :4.826
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:7.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## Q11a Q11b Q11c Q11d Q11e
## Min. :1.000 Min. :3.000 Min. :3.00 Min. :1.00 Min. :1.000
## 1st Qu.:4.000 1st Qu.:5.000 1st Qu.:5.00 1st Qu.:7.00 1st Qu.:4.000
## Median :5.000 Median :7.000 Median :7.00 Median :7.00 Median :6.000
## Mean :5.102 Mean :6.148 Mean :6.02 Mean :6.48 Mean :5.592
## 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7.00 3rd Qu.:7.00 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.00 Max. :7.00 Max. :7.000
##
## Q12a Q12b Q12c Q12d Q12e
## Min. :1.000 Min. :3.000 Min. :2.000 Min. :1.00 Min. :1.000
## 1st Qu.:6.000 1st Qu.:6.000 1st Qu.:6.000 1st Qu.:5.00 1st Qu.:4.000
## Median :7.000 Median :7.000 Median :7.000 Median :7.00 Median :5.000
## Mean :6.227 Mean :6.484 Mean :6.336 Mean :6.03 Mean :5.076
## 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7.00 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.00 Max. :7.000
##
## Q13a Q13b Q13c Q13d
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:2.750 1st Qu.:5.000 1st Qu.:5.000 1st Qu.:7.000
## Median :4.000 Median :7.000 Median :7.000 Median :7.000
## Mean :4.076 Mean :6.174 Mean :6.122 Mean :6.526
## 3rd Qu.:6.000 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## Q13e Q14a Q14b Q14c
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.000
## Median :6.000 Median :7.000 Median :4.000 Median :4.000
## Mean :5.684 Mean :5.681 Mean :4.457 Mean :4.457
## 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## Q14d Q14e Q15a Q15b
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:4.000 1st Qu.:3.000 1st Qu.:4.000
## Median :4.000 Median :4.000 Median :5.000 Median :5.000
## Mean :4.395 Mean :4.484 Mean :4.852 Mean :5.155
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:7.000 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## Q15c Q15d Q15e Q16a
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:1.000
## Median :5.000 Median :5.000 Median :5.000 Median :3.000
## Mean :5.007 Mean :5.161 Mean :5.115 Mean :3.125
## 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:7.000 3rd Qu.:4.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## Q16b Q17 Q17_5_text Q18a
## Min. :1.000 Length:304 Min. :-2 Min. :-2.0000
## 1st Qu.:1.000 Class :character 1st Qu.:-2 1st Qu.: 1.0000
## Median :4.000 Mode :character Median :-2 Median : 1.0000
## Mean :3.339 Mean :-2 Mean : 0.5132
## 3rd Qu.:5.000 3rd Qu.:-2 3rd Qu.: 1.0000
## Max. :7.000 Max. :-2 Max. : 1.0000
## NA's :4
## Q18b Q18c Q18d Q18e
## Min. :-2.0000 Min. :-2.0000 Min. :-2.0000 Min. :-2.0000
## 1st Qu.: 0.0000 1st Qu.: 1.0000 1st Qu.: 0.0000 1st Qu.: 0.0000
## Median : 0.0000 Median : 1.0000 Median : 0.0000 Median : 0.0000
## Mean : 0.1579 Mean : 0.5164 Mean : 0.1349 Mean :-0.2368
## 3rd Qu.: 1.0000 3rd Qu.: 1.0000 3rd Qu.: 1.0000 3rd Qu.: 0.0000
## Max. : 1.0000 Max. : 1.0000 Max. : 1.0000 Max. : 1.0000
##
## Q18e_text Q19a Q19b Q19c
## Min. :-2.000 Min. :-1.000 Min. :-1.000 Min. :-1.000
## 1st Qu.:-2.000 1st Qu.: 4.000 1st Qu.: 4.000 1st Qu.: 3.000
## Median :-2.000 Median : 5.000 Median : 4.000 Median : 4.000
## Mean :-1.997 Mean : 4.507 Mean : 4.457 Mean : 4.273
## 3rd Qu.:-2.000 3rd Qu.: 6.000 3rd Qu.: 6.000 3rd Qu.: 6.000
## Max. :-1.000 Max. : 7.000 Max. : 7.000 Max. : 7.000
## NA's :7
## Q19d Q20 Q21a Q21b
## Min. :-1.000 Length:304 Min. :-2.000 Min. :-2.000
## 1st Qu.: 4.000 Class :character 1st Qu.:-2.000 1st Qu.:-2.000
## Median : 5.000 Mode :character Median :-2.000 Median :-2.000
## Mean : 4.849 Mean :-1.039 Mean :-1.072
## 3rd Qu.: 6.000 3rd Qu.: 0.000 3rd Qu.: 0.000
## Max. : 7.000 Max. : 1.000 Max. : 1.000
##
## Q21c Q21d Q21e Q22
## Min. :-2.0000 Min. :-2.000 Min. :-2.000 Length:304
## 1st Qu.:-2.0000 1st Qu.:-2.000 1st Qu.:-2.000 Class :character
## Median :-2.0000 Median :-2.000 Median :-2.000 Mode :character
## Mean :-0.8651 Mean :-1.033 Mean :-1.079
## 3rd Qu.: 1.0000 3rd Qu.: 0.000 3rd Qu.: 0.000
## Max. : 1.0000 Max. : 1.000 Max. : 1.000
##
## Q23 Q24 Q25 Q25_5_text
## Length:304 Length:304 Length:304 Min. :-2
## Class :character Class :character Class :character 1st Qu.:-2
## Mode :character Mode :character Mode :character Median :-2
## Mean :-2
## 3rd Qu.:-2
## Max. :-2
## NA's :9
## Q26 Q27 Q27_7_text Q1F
## Length:304 Length:304 Min. :-2 23 :64
## Class :character Class :character 1st Qu.:-2 22 :44
## Mode :character Mode :character Median :-2 25 :43
## Mean :-2 20 :40
## 3rd Qu.:-2 24 :30
## Max. :-2 21 :23
## NA's :23 (Other):60
## Q5F Q7F Q17F Q20F
## Pay digital elsewhere: 52 Yes:233 Cash : 28 Yes - me : 22
## Pay as available :195 No : 71 Mobile apps :250 Yes - others: 96
## Never occurred : 42 Bank transfer: 14 Yes - both : 11
## Other : 15 Don't share : 8 No :172
## Other : 4 NA's : 3
##
##
## Q22F Q23F
## Fully digital : 78 Man :120
## Balance digital-cash:171 Woman :182
## Cash : 44 Other : 1
## Don't know : 10 Don't want to answer: 1
## NA's : 1
##
##
## Q24F Q25F Q26F
## Unfinished primary : 0 Student :236 0-200 EUR :48
## Primary school : 8 Employed : 49 201-500 EUR :91
## Vocational education: 2 Self-employed: 7 501-800 EUR :58
## High School :132 Unemployed : 3 801-1300 EUR :48
## Bachelor Degree : 99 Other : 9 Above 1300 EUR:57
## Master Degree : 61 NA's : 2
## PhD : 2
## Q27F
## NLB :121
## OTP :109
## Intesa Sanpaolo : 17
## Sparkasse : 7
## Addiko Bank : 8
## Delovska Hranilnica: 19
## Other : 23Categorical variables
- Q17 – Preferred Payment Method for Expense Sharing When it comes to sharing expenses, the majority of respondents (250) prefer using mobile apps. A smaller group (28) opts for cash, while 14 respondents use bank transfers. Eight respondents do not share expenses with others, and four selected “Other” as their method of choice. This highlights the dominance of mobile apps as the most convenient and preferred option for managing shared expenses.
- Q22 – Savings Preference Respondents show varied saving preferences. A majority (171) save their money in a balanced form, splitting between digital and cash. Fully digital savings are preferred by 78 respondents, while 44 save entirely in cash. A smaller group (10 respondents) is unsure of their savings method.
- Q23 – Gender The gender distribution indicates that the majority of respondents (182) are women, while 120 are men. Additionally, 1 respondent identified as “Other,” and another preferred not to disclose their gender.
- Q24 – Education Level The most common level of education is high school completion, with 132 respondents. Following this, 99 have a bachelor’s degree, 61 hold a master’s degree, and 2 have a PhD. Vocational education was reported by 2 respondents, and 8 completed only primary school, while none reported having incomplete primary education.
- Q25 – Employment Status The majority of respondents (236) are students. Employed individuals account for 49 responses, followed by 7 self-employed, 3 unemployed, and 9 selecting “other” as their employment status.
- Q26 – Monthly Income Regarding income, the largest group of respondents (91) earns between 201-500 EUR per month. Others reported the following income ranges: 0-200 EUR (48), 501-800 EUR (58), 801-1300 EUR (48), and above 1300 EUR (57).
- Q27 – Bank Association Respondents are primarily associated with two major banks: NLB (121 respondents) and OTP (109 respondents). Smaller numbers of respondents use other banks such as Intesa Sanpaolo (17), Sparkasse (7), and Addiko Bank (8).
Numerical variables
Respondents show varying frequencies of cash usage based on the purchase amount. For small purchases (up to €10), the average usage is moderate, with a mean of 2.421 and a median of 2, indicating that cash is used occasionally but not regularly. Medium-small purchases (€11 to €99) have a slightly higher mean of 2.737 but still lean towards occasional use, with a median of 2. In contrast, for medium-large purchases (€100 to €1000), cash usage drops significantly, reflected by a mean of 1.576 and a median of 1, suggesting infrequent or rare use. This trend continues for large purchases (over €1000), where cash is almost never used, with a mean of 1.398 and a median of 1. Overall, cash usage declines as the purchase value increases, indicating a preference for alternative payment methods for higher-value transactions.
Respondents show a stronger tendency to be influenced by their family than by their friends when choosing payment methods. For Q16a (friends’ influence), the mean is 3.125 and the median is 3, indicating a neutral to slightly agreeing stance, with many respondents either disagreeing or moderately agreeing. In contrast, Q16b (family’s influence) has a higher mean of 3.339 and a median of 4, suggesting a more significant agreement with the statement. While both questions have a 1st quartile of 1, indicating strong disagreement from a subset of respondents, the 3rd quartile for family influence is 5, compared to 4 for friends, confirming that family has a stronger impact on respondents’ payment choices.
Creating PCA for clustering
NLB_PCA10 <- NLB_data[ , c("Q10b", "Q10c", "Q10d", "Q10e")]
NLB_PCA11 <- NLB_data[ , c("Q11b", "Q11c", "Q11d", "Q11e")]
NLB_PCA12 <- NLB_data[ , c("Q12b", "Q12c", "Q12d", "Q12e")]
NLB_PCA13 <- NLB_data[ , c("Q13b", "Q13c", "Q13d", "Q13e")]
NLB_PCA14 <- NLB_data[ , c("Q14b", "Q14c", "Q14d", "Q14e")]
NLB_PCA15 <- NLB_data[ , c("Q15b", "Q15c", "Q15d", "Q15e")]
library(pastecs)##
## Attaching package: 'pastecs'## The following objects are masked from 'package:dplyr':
##
## first, lastround(stat.desc(NLB_PCA10, basic = FALSE), 2)## Q10b Q10c Q10d Q10e
## median 5.00 5.00 5.00 5.00
## mean 5.14 4.95 5.17 4.83
## SE.mean 0.07 0.08 0.09 0.09
## CI.mean.0.95 0.14 0.15 0.17 0.17
## var 1.58 1.85 2.28 2.30
## std.dev 1.26 1.36 1.51 1.52
## coef.var 0.25 0.28 0.29 0.31round(stat.desc(NLB_PCA11, basic = FALSE), 2)## Q11b Q11c Q11d Q11e
## median 7.00 7.00 7.00 6.00
## mean 6.15 6.02 6.48 5.59
## SE.mean 0.06 0.07 0.06 0.09
## CI.mean.0.95 0.13 0.14 0.12 0.17
## var 1.26 1.45 1.22 2.31
## std.dev 1.12 1.20 1.10 1.52
## coef.var 0.18 0.20 0.17 0.27round(stat.desc(NLB_PCA12, basic = FALSE), 2)## Q12b Q12c Q12d Q12e
## median 7.00 7.00 7.00 5.00
## mean 6.48 6.34 6.03 5.08
## SE.mean 0.05 0.06 0.07 0.10
## CI.mean.0.95 0.11 0.13 0.14 0.19
## var 0.88 1.24 1.51 2.81
## std.dev 0.94 1.11 1.23 1.68
## coef.var 0.14 0.18 0.20 0.33round(stat.desc(NLB_PCA13, basic = FALSE), 2)## Q13b Q13c Q13d Q13e
## median 7.00 7.00 7.00 6.00
## mean 6.17 6.12 6.53 5.68
## SE.mean 0.07 0.07 0.06 0.08
## CI.mean.0.95 0.13 0.14 0.12 0.17
## var 1.34 1.47 1.08 2.18
## std.dev 1.16 1.21 1.04 1.48
## coef.var 0.19 0.20 0.16 0.26round(stat.desc(NLB_PCA14, basic = FALSE), 2)## Q14b Q14c Q14d Q14e
## median 4.00 4.00 4.00 4.00
## mean 4.46 4.46 4.39 4.48
## SE.mean 0.10 0.10 0.10 0.09
## CI.mean.0.95 0.20 0.20 0.20 0.19
## var 3.01 2.99 3.22 2.71
## std.dev 1.73 1.73 1.80 1.64
## coef.var 0.39 0.39 0.41 0.37round(stat.desc(NLB_PCA15, basic = FALSE), 2)## Q15b Q15c Q15d Q15e
## median 5.00 5.00 5.00 5.00
## mean 5.15 5.01 5.16 5.12
## SE.mean 0.10 0.10 0.11 0.10
## CI.mean.0.95 0.19 0.20 0.21 0.19
## var 2.92 3.03 3.38 2.84
## std.dev 1.71 1.74 1.84 1.69
## coef.var 0.33 0.35 0.36 0.33library(FactoMineR)
components10 <- PCA(NLB_PCA10,
scale.unit = TRUE,
graph = FALSE,
ncp = 1)library(FactoMineR)
components11 <- PCA(NLB_PCA11,
scale.unit = TRUE,
graph = FALSE,
ncp = 1)library(FactoMineR)
components12 <- PCA(NLB_PCA12,
scale.unit = TRUE,
graph = FALSE,
ncp = 1)library(FactoMineR)
components13 <- PCA(NLB_PCA13,
scale.unit = TRUE,
graph = FALSE,
ncp = 1)library(FactoMineR)
components14 <- PCA(NLB_PCA14,
scale.unit = TRUE,
graph = FALSE,
ncp = 1)library(FactoMineR)
components15 <- PCA(NLB_PCA15,
scale.unit = TRUE,
graph = FALSE,
ncp = 1)NLB_data$PC10 <- components10$ind$coord[ , 1]
NLB_data$PC11 <- components11$ind$coord[ , 1]
NLB_data$PC12 <- components12$ind$coord[ , 1]
NLB_data$PC13 <- components13$ind$coord[ , 1]
NLB_data$PC14 <- components14$ind$coord[ , 1]
NLB_data$PC15 <- components15$ind$coord[ , 1]
head(NLB_data)## Q1 Q3a Q3b Q3c Q3d Q4a Q4b Q4c Q4d Q5 Q5_4_text Q6a Q6b Q6c Q6d Q6e Q6f Q6g
## 1 7 3 2 5 2 4 3 2 1 2 -2 3 2 1 1 3 3 3
## 2 9 2 5 1 1 2 1 1 1 1 -2 4 2 1 4 4 4 3
## 3 9 2 4 4 1 2 2 1 1 2 -2 3 3 1 4 4 4 2
## 4 7 3 5 5 1 2 2 1 1 1 -2 3 3 2 4 4 3 4
## 5 7 2 5 5 1 2 1 1 1 1 -2 4 3 3 4 4 4 4
## 6 9 3 3 1 2 4 3 2 1 2 -2 3 4 1 1 3 3 4
## Q7 Q8a Q9a Q9b Q9c Q9d Q9e Q9f Q9g Q9h Q31_2a Q31_2b Q31_2c Q31_2d Q31_2e
## 1 1 5 6 3 5 6 4 7 6 7 7 7 6 6 3
## 2 1 7 7 6 3 6 3 7 1 6 6 7 5 7 7
## 3 1 7 6 2 3 6 3 7 1 7 7 6 6 6 4
## 4 1 7 6 5 6 7 4 7 1 7 7 7 7 7 7
## 5 2 -2 7 4 7 4 4 7 4 7 7 7 7 7 7
## 6 2 -2 7 3 5 7 7 5 6 5 5 3 7 7 4
## Q31_2f Q10a Q10b Q10c Q10d Q10e Q11a Q11b Q11c Q11d Q11e Q12a Q12b Q12c Q12d
## 1 6 6 6 6 7 6 5 6 6 7 6 6 7 7 7
## 2 6 3 7 7 3 6 7 7 7 6 6 6 6 6 6
## 3 5 6 6 4 6 6 4 7 7 7 7 7 7 7 7
## 4 7 6 5 4 6 6 3 6 6 7 7 6 7 7 6
## 5 7 7 4 4 4 4 7 7 7 7 7 7 7 7 7
## 6 4 7 6 6 5 5 6 7 7 6 6 6 7 7 6
## Q12e Q13a Q13b Q13c Q13d Q13e Q14a Q14b Q14c Q14d Q14e Q15a Q15b Q15c Q15d
## 1 6 5 6 6 7 7 7 6 5 5 6 7 5 5 3
## 2 6 5 7 7 7 7 7 1 1 1 1 2 7 4 1
## 3 7 4 7 7 7 7 6 5 5 5 5 5 7 7 7
## 4 6 1 6 6 7 7 7 4 4 4 4 6 5 1 5
## 5 4 7 7 7 7 7 4 7 7 7 7 4 7 7 7
## 6 6 2 7 7 6 6 5 7 7 7 7 7 6 5 3
## Q15e Q16a Q16b Q17 Q17_5_text Q18a Q18b Q18c Q18d Q18e Q18e_text Q19a Q19b
## 1 3 5 2 2 -2 1 0 1 0 0 -2 3 5
## 2 6 4 4 2 -2 1 1 1 0 0 -2 5 5
## 3 7 4 4 2 -2 1 1 1 1 0 -2 3 3
## 4 5 7 7 2 -2 1 1 1 1 0 -2 5 5
## 5 7 4 4 2 -2 1 1 1 1 0 -2 7 7
## 6 5 3 5 2 -2 1 0 0 0 0 -2 5 4
## Q19c Q19d Q20 Q21a Q21b Q21c Q21d Q21e Q22 Q23 Q24 Q25 Q25_5_text Q26 Q27
## 1 3 3 2 0 0 1 0 0 2 1 6 1 -2 2 2
## 2 6 7 3 0 0 1 0 0 2 2 5 1 -2 2 2
## 3 3 3 4 -2 -2 -2 -2 -2 2 2 4 1 -2 3 7
## 4 5 6 4 -2 -2 -2 -2 -2 1 2 4 1 -2 2 1
## 5 7 7 1 -1 -1 -1 -1 -1 1 2 4 1 -2 4 1
## 6 6 6 2 1 0 0 0 0 4 2 6 1 -2 2 1
## Q27_7_text Q1F Q5F Q7F Q17F Q20F
## 1 -2 23 Pay as available Yes Mobile apps Yes - others
## 2 -2 25 Pay digital elsewhere Yes Mobile apps Yes - both
## 3 NA 25 Pay as available Yes Mobile apps No
## 4 -2 23 Pay digital elsewhere Yes Mobile apps No
## 5 -2 23 Pay digital elsewhere No Mobile apps Yes - me
## 6 -2 25 Pay as available No Mobile apps Yes - others
## Q22F Q23F Q24F Q25F Q26F Q27F
## 1 Balance digital-cash Man Master Degree Student 201-500 EUR OTP
## 2 Balance digital-cash Woman Bachelor Degree Student 201-500 EUR OTP
## 3 Balance digital-cash Woman High School Student 501-800 EUR Other
## 4 Fully digital Woman High School Student 201-500 EUR NLB
## 5 Fully digital Woman High School Student 801-1300 EUR NLB
## 6 Don't know Woman Master Degree Student 201-500 EUR NLB
## PC10 PC11 PC12 PC13 PC14 PC15
## 1 -1.7204789 0.1593095 -1.2385549 0.3545114 -1.2168529 -1.2370388
## 2 -1.1689414 0.9246044 0.2539360 1.3676446 3.9978412 -0.6158432
## 3 -0.6604604 1.4565407 -1.4619345 1.3676446 -0.6395533 2.1738887
## 4 -0.2295463 0.3880241 -0.8265122 0.3545114 0.5197953 -1.2939568
## 5 1.4772851 1.4565407 -0.7917959 1.3676446 -2.9582505 2.1738887
## 6 -0.7464178 0.9246044 -0.8265122 0.7468479 -2.9582505 -0.3666127Clustering
NLB_CluStd <- as.data.frame(scale(NLB_data[c("PC10", "PC11", "PC12", "PC13", "PC14", "PC15")]))NLB_CluStd$Dissimilarity <- sqrt(NLB_CluStd$PC10^2 + NLB_CluStd$PC11^2 + NLB_CluStd$PC12^2 + NLB_CluStd$PC13^2 +NLB_CluStd$PC14^2 + NLB_CluStd$PC15^2)library(factoextra)## Loading required package: ggplot2## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBaDistances <- get_dist(NLB_CluStd,
method = "euclidian")
fviz_dist(Distances,
gradient = list(low = "blue",
mid = "grey",
high = "white"))
NLB_CluStd <- NLB_CluStd %>% rename(Security = PC10,
`Ease of use` = PC11,
Availability = PC12,
Speed = PC13,
Privacy = PC14,
`Controlling of spending` = PC15)library(factoextra)
get_clust_tendency(NLB_CluStd,
n = nrow(NLB_CluStd) -1,
graph = FALSE)## $hopkins_stat
## [1] 0.6785538
##
## $plot
## NULLlibrary(dplyr)
library(factoextra)
WARD <- NLB_CluStd %>%
get_dist(method = "euclidean") %>%
hclust(method = "ward.D2")
WARD##
## Call:
## hclust(d = ., method = "ward.D2")
##
## Cluster method : ward.D2
## Distance : euclidean
## Number of objects: 304library(factoextra)
fviz_dend(WARD)## Warning: The `<scale>` argument of `guides()` cannot be `FALSE`. Use "none" instead as
## of ggplot2 3.3.4.
## ℹ The deprecated feature was likely used in the factoextra package.
## Please report the issue at <https://github.com/kassambara/factoextra/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
library(factoextra)
library(NbClust)
fviz_nbclust(NLB_CluStd, kmeans, method = "wss") +
labs(subtitle = "Elbow Method")
fviz_nbclust(NLB_CluStd, kmeans, method = "silhouette") +
labs(subtitle = "Silhouette analysis")
Clustering <- kmeans(NLB_CluStd,
centers = 4,
nstart = 25)
Clustering## K-means clustering with 4 clusters of sizes 63, 93, 103, 45
##
## Cluster means:
## Security Ease of use Availability Speed Privacy
## 1 0.4866563 0.4709095 -0.15616090 0.24994550 0.8603929
## 2 -0.7517767 0.7902180 -0.57596893 0.69484422 -0.8043929
## 3 0.1430845 -0.5409715 0.04180835 -0.07174967 -0.0235824
## 4 0.5448485 -1.0541669 1.31326640 -1.62170805 0.5118394
## Controlling of spending Dissimilarity
## 1 -0.8773218 2.469170
## 2 0.5618051 2.324214
## 3 0.1264165 1.698921
## 4 -0.2221667 3.443997
##
## Clustering vector:
## [1] 2 1 2 3 2 2 3 3 3 3 2 3 1 3 2 2 1 3 3 2 1 2 2 4 3 3 3 2 2 4 1 4 3 3 3 2 2
## [38] 4 2 2 1 2 4 3 3 4 1 3 3 2 4 3 2 2 1 3 2 2 1 3 2 4 1 1 1 1 2 3 3 2 4 1 3 2
## [75] 2 1 2 1 3 3 1 4 3 1 1 3 3 3 2 3 4 2 1 1 2 2 3 2 4 1 1 2 2 2 3 4 1 2 2 1 3
## [112] 1 1 1 2 3 1 4 2 3 2 1 4 4 1 2 3 2 2 3 1 1 4 2 3 3 4 1 1 4 3 3 2 2 2 4 2 2
## [149] 1 3 2 3 3 1 3 3 2 3 3 2 2 3 2 4 3 3 2 1 4 4 4 2 4 1 2 4 1 1 3 2 3 3 2 3 1
## [186] 3 3 3 4 1 4 3 2 3 4 3 3 3 1 3 1 4 1 4 2 4 4 4 4 3 3 3 2 1 2 3 1 3 2 3 1 3
## [223] 3 3 3 4 2 2 4 2 2 1 2 3 3 2 2 2 2 3 2 3 1 1 3 3 2 2 2 2 2 2 2 4 2 1 3 3 1
## [260] 1 1 3 2 2 3 2 3 3 3 3 2 2 3 3 3 3 3 3 3 3 3 3 2 1 1 1 1 4 1 4 4 2 2 1 2 3
## [297] 3 4 1 4 3 4 2 4
##
## Within cluster sum of squares by cluster:
## [1] 301.0014 275.2221 329.2284 299.6181
## (between_SS / total_SS = 40.2 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"library(factoextra)
fviz_cluster(Clustering,
palette = "Set1",
repel = FALSE,
ggtheme = theme_bw(),
data = NLB_CluStd)
Averages <- Clustering$centers
Averages## Security Ease of use Availability Speed Privacy
## 1 0.4866563 0.4709095 -0.15616090 0.24994550 0.8603929
## 2 -0.7517767 0.7902180 -0.57596893 0.69484422 -0.8043929
## 3 0.1430845 -0.5409715 0.04180835 -0.07174967 -0.0235824
## 4 0.5448485 -1.0541669 1.31326640 -1.62170805 0.5118394
## Controlling of spending Dissimilarity
## 1 -0.8773218 2.469170
## 2 0.5618051 2.324214
## 3 0.1264165 1.698921
## 4 -0.2221667 3.443997Figure <- as.data.frame(Averages)
Figure$id <- 1:nrow(Figure)
library(tidyr)##
## Attaching package: 'tidyr'## The following object is masked from 'package:pastecs':
##
## extractFigure <- pivot_longer(Figure, cols = c("Security", "Ease of use", "Availability", "Speed", "Privacy", "Controlling of spending"))
Figure$Group <- factor(Figure$id,
levels = c(1, 2, 3, 4, 5),
labels = c("1", "2", "3", "4", "5"))
Figure$ImeF <- factor(Figure$name,
levels = c("Security", "Ease of use", "Availability", "Speed", "Privacy", "Controlling of spending"),
labels = c("Security", "Ease of use", "Availability", "Speed", "Privacy", "Controlling of spending"))
library(ggplot2)
ggplot(Figure, aes(x = ImeF, y = value)) +
geom_hline(yintercept = 0) +
theme_bw() +
geom_point(aes(shape = Group, col = Group), size = 3) +
geom_line(aes(group = id), linewidth = 1) +
ylab("Averages") +
xlab("Cluster variables") +
scale_color_brewer(palette="Set1") +
ylim(-3, 3) +
theme(axis.text.x = element_text(angle = 45, vjust = 0.50, size = 10))
NLB_CluStd$Group <- Clustering$cluster
fit <- aov(cbind(`Security`, `Ease of use`, `Availability`, `Speed`, `Privacy`, `Controlling of spending`) ~ as.factor(Group),
data = NLB_CluStd)
summary(fit)## Response Security :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(Group) 3 82.949 27.6495 37.695 < 2.2e-16 ***
## Residuals 300 220.051 0.7335
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Ease of use :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(Group) 3 152.19 50.731 100.92 < 2.2e-16 ***
## Residuals 300 150.81 0.503
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Availability :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(Group) 3 110.18 36.726 57.14 < 2.2e-16 ***
## Residuals 300 192.82 0.643
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Speed :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(Group) 3 167.71 55.905 123.97 < 2.2e-16 ***
## Residuals 300 135.29 0.451
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Privacy :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(Group) 3 118.66 39.553 64.37 < 2.2e-16 ***
## Residuals 300 184.34 0.614
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Response Controlling of spending :
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(Group) 3 81.711 27.2370 36.925 < 2.2e-16 ***
## Residuals 300 221.289 0.7376
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1FAILED Citerion validity
NLB_data$Group <- NLB_CluStd$GroupEducation
NLB_Education <- NLB_data %>% select(110)NLB_Education$D <- ifelse(NLB_data$Q24 == 4, "High School",
ifelse(NLB_data$Q24 == 5, "Bachelors",
ifelse(NLB_data$Q24 == 6, "Masters",
NLB_data$Q24)))NLB_Education$D <-ifelse(test = NLB_Education$D == 1,
yes = NA,
no = NLB_Education$D)
NLB_Education$D <-ifelse(test = NLB_Education$D == 2,
yes = NA,
no = NLB_Education$D)
NLB_Education$D <-ifelse(test = NLB_Education$D == 3,
yes = NA,
no = NLB_Education$D)
NLB_Education$D <-ifelse(test = NLB_Education$D == 7,
yes = NA,
no = NLB_Education$D)library(tidyr)
NLB_Education <- drop_na(NLB_Education)chi_square <- chisq.test(NLB_Education$Group, as.factor(NLB_Education$D))
chi_square##
## Pearson's Chi-squared test
##
## data: NLB_Education$Group and as.factor(NLB_Education$D)
## X-squared = 5.3794, df = 6, p-value = 0.4962Income
NLB_data$IncomeD <- ifelse(NLB_data$Q26 > 1, "above_500", "Below_500")chi_square <- chisq.test(NLB_data$IncomeD, as.factor(NLB_data$Group))
chi_square##
## Pearson's Chi-squared test
##
## data: NLB_data$IncomeD and as.factor(NLB_data$Group)
## X-squared = 4.7139, df = 3, p-value = 0.194Banks
NLB_data$BanksD <- ifelse(NLB_data$Q27 == 1, "NLB", NLB_data$Q27)
NLB_data$BanksD <- ifelse(NLB_data$Q27 == 2, "OTP", "other")chi_square <- chisq.test(NLB_data$BanksD, as.factor(NLB_data$Group))
chi_square##
## Pearson's Chi-squared test
##
## data: NLB_data$BanksD and as.factor(NLB_data$Group)
## X-squared = 0.26141, df = 3, p-value = 0.9671Q6 - Which of the following sources of income do you have and how do you receive them?
library(dplyr)
NLB_Q6 <- NLB_data %>%
filter(!(Q6a %in% c("NA", "Don't want to answer"))) %>%
select(Q6a, Group)chi_square <- chisq.test(NLB_Q6$Q6a, as.factor(NLB_Q6$Group))## Warning in chisq.test(NLB_Q6$Q6a, as.factor(NLB_Q6$Group)): Chi-squared
## approximation may be incorrectchi_square##
## Pearson's Chi-squared test
##
## data: NLB_Q6$Q6a and as.factor(NLB_Q6$Group)
## X-squared = 11.986, df = 9, p-value = 0.2141Gender
NLB_data <- NLB_data %>%
mutate(across(c(Q23), ~ as.numeric(as.character(.))))# Shapiro-Wilk Test for normality within each group
shapiro_results <- NLB_data %>%
group_by(Group) %>%
summarise(p_value = shapiro.test(Q23)$p.value)
print(shapiro_results)## # A tibble: 4 × 2
## Group p_value
## <int> <dbl>
## 1 1 7.65e-11
## 2 2 2.40e-13
## 3 3 7.43e-15
## 4 4 1.94e- 9# Levene's Test for homogeneity of variances
NLB_data$Group <- as.factor(NLB_data$Group)
library(car)## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recodelevene_test_result <- leveneTest(Q23 ~ Group, data = NLB_data)
print(levene_test_result)## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 3 0.3586 0.7829
## 300# Kruskal-Wallis test
kruskal_test_result <- kruskal.test(Q23 ~ Group, data = NLB_data)
# View the result
kruskal_test_result##
## Kruskal-Wallis rank sum test
##
## data: Q23 by Group
## Kruskal-Wallis chi-squared = 1.5054, df = 3, p-value = 0.681SUCCESFULL Criterion valdity
Q3c - How many times a month do you use mobile payments on average?
NLB_data$Q3c_merged <- ifelse(NLB_data$Q3c == 1, "never",
ifelse(NLB_data$Q3c %in% c(2, 3), "irregular basis", "regular basis"))chi_square <- chisq.test(NLB_data$Q3c_merged, as.factor(NLB_data$Group))
chi_square##
## Pearson's Chi-squared test
##
## data: NLB_data$Q3c_merged and as.factor(NLB_data$Group)
## X-squared = 19.394, df = 6, p-value = 0.003547Mobile Payment usage
# Calculate frequency by Response
Phone_freq <- NLB_data %>%
group_by(Group, Q3c_merged) %>%
summarise(Count = n(), .groups = 'drop') %>%
group_by(Group) %>%
mutate(Percentage = Count / sum(Count) * 100)
# Plot the frequency by Response
ggplot(Phone_freq, aes(x = Group, y = Percentage, fill = Q3c_merged)) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Frequency by Response",
x = "Group",
y = "Percentage(%)",
fill = "Mobile Payment Usage"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) # Rotate x-axis labels if needed
Q4 - How often do I use cash for purchases up to 10 EUR?
NLB_data$Q4a_merged <- ifelse(NLB_data$Q4a %in% c(1, 2), "less than half",
ifelse(NLB_data$Q4a %in% 3, "half", "more than half"))chi_square <- chisq.test(NLB_data$Q4a_merged, as.factor(NLB_data$Group))
chi_square##
## Pearson's Chi-squared test
##
## data: NLB_data$Q4a_merged and as.factor(NLB_data$Group)
## X-squared = 20.107, df = 6, p-value = 0.00265cash usage for purchases up to 10 EUR
# Calculate frequency by Response
Purchases_freq <- NLB_data %>%
group_by(Group, Q4a_merged) %>%
summarise(Count = n(), .groups = 'drop') %>%
group_by(Group) %>%
mutate(Percentage = Count / sum(Count) * 100)
# Plot the frequency by Response
ggplot(Purchases_freq, aes(x = Group, y = Percentage, fill = Q4a_merged)) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Frequency by Response",
x = "Group",
y = "Percentage(%)",
fill = "Cash Payment for purchases up to 10 EUR"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) # Rotate x-axis labels if needed
Age
NLB_data <- NLB_data %>%
mutate(across(c(Q1F), ~ as.numeric(as.character(.))))
class(NLB_data$Q1F)## [1] "numeric"# Shapiro-Wilk test for normality within each group
NLB_data %>%
group_by(Group) %>%
summarise(p_value = shapiro.test(Q1F)$p.value)## # A tibble: 4 × 2
## Group p_value
## <fct> <dbl>
## 1 1 0.0750
## 2 2 0.00322
## 3 3 0.00231
## 4 4 0.0190NLB_data$Group <- as.factor(NLB_data$Group)
library(car)
leveneTest(Q1F ~ Group, data = NLB_data)## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 3 2.1509 0.0939 .
## 300
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1kruskal_test <- kruskal.test(Q1F ~ Group, data = NLB_data)
print(kruskal_test)##
## Kruskal-Wallis rank sum test
##
## data: Q1F by Group
## Kruskal-Wallis chi-squared = 6.8551, df = 3, p-value = 0.07666group_count <- table(NLB_data$Q1F, NLB_data$Group)
print(group_count)##
## 1 2 3 4
## 18 3 1 5 6
## 19 2 7 10 2
## 20 9 8 13 10
## 21 6 8 8 1
## 22 8 14 14 8
## 23 15 23 16 10
## 24 9 8 11 2
## 25 6 19 14 4
## 26 4 2 5 2
## 27 1 3 7 0# Calculate percentage by Group
Bank_freq <- NLB_data %>%
group_by(Group, Q1F) %>%
summarise(Count = n(), .groups = 'drop') %>%
group_by(Group) %>%
mutate(Percentage = Count / sum(Count) * 100)
# Plot the percentage by Response
ggplot(Bank_freq, aes(x = Group, y = Percentage, fill = as.factor(Q1F))) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Percentage Distribution of Age by Group",
x = "Group",
y = "Percentage (%)",
fill = "Age"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) # Rotate x-axis labels if needed
Bank
NLB_data <- NLB_data %>%
mutate(across(c(Q27), ~ as.numeric(as.character(.))))# Shapiro-Wilk Test for normality within each group
shapiro_results <- NLB_data %>%
group_by(Group) %>%
summarise(p_value = shapiro.test(Q27)$p.value)
print(shapiro_results)## # A tibble: 4 × 2
## Group p_value
## <fct> <dbl>
## 1 1 2.23e-10
## 2 2 4.69e-11
## 3 3 4.26e-14
## 4 4 7.67e- 8# Levene's Test for homogeneity of variances
library(car)
levene_test_result <- leveneTest(Q27 ~ Group, data = NLB_data)
print(levene_test_result)## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 3 0.6694 0.5714
## 300# Kruskal-Wallis test
kruskal_test_result <- kruskal.test(Q27 ~ Group, data = NLB_data)
# View the result
kruskal_test_result##
## Kruskal-Wallis rank sum test
##
## data: Q27 by Group
## Kruskal-Wallis chi-squared = 8.1385, df = 3, p-value = 0.04323# Calculate frequency by Response
Bank_freq <- NLB_data %>%
group_by(Group, Q27F) %>%
summarise(Count = n(), .groups = 'drop') %>%
group_by(Group) %>%
mutate(Percentage = Count / sum(Count) * 100)
# Plot the frequency by Response
ggplot(Bank_freq, aes(x = Group, y = Percentage, fill = Q27F)) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Frequency by Response",
x = "Group",
y = "Percentage(%)",
fill = "Bank"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) # Rotate x-axis labels if needed
Graphs - demographics
Income
# Calculate frequency by Income (Q26F) and Group
income_freq <- NLB_data %>%
group_by(Group, Q26F) %>%
summarise(Count = n(), .groups = 'drop')
# Plot the frequency by Income
ggplot(income_freq, aes(x = Q26F, y = Count, fill = Group)) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Frequency by Income",
x = "Income",
y = "Frequency",
fill = "Group"
) +
theme_minimal()
Status
# Calculate frequency by Income (Q25F) and Group
status_freq <- NLB_data %>%
group_by(Group, Q25F) %>%
summarise(Count = n(), .groups = 'drop')
# Plot the frequency by status
ggplot(status_freq, aes(x = Q25F, y = Count, fill = Group)) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Frequency by Status",
x = "Status",
y = "Frequency",
fill = "Group"
) +
theme_minimal()
Education
# Calculate frequency by Education (Q24F) and Group
education_freq <- NLB_data %>%
group_by(Group, Q24F) %>%
summarise(Count = n(), .groups = 'drop')
# Plot the frequency by Education
ggplot(education_freq, aes(x = Q24F, y = Count, fill = Group)) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Frequency by Education",
x = "Education",
y = "Frequency",
fill = "Group"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) # Rotate x-axis labels if needed
Response
# Calculate frequency by Response
response_freq <- NLB_data %>%
group_by(Group, Q5F) %>%
summarise(Count = n(), .groups = 'drop')
# Plot the frequency by Response
ggplot(response_freq, aes(x = Q5F, y = Count, fill = Group)) +
geom_bar(stat = "identity", position = "dodge") +
labs(
title = "Frequency by Response",
x = "Response",
y = "Frequency",
fill = "Group"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) # Rotate x-axis labels if needed
PCA Analysis - creaing a perception map
NLB_PCA <- NLB_data[ , c("Q10a", "Q10b", "Q10c", "Q10d", "Q10e", "Q11a", "Q11b", "Q11c", "Q11d", "Q11e", "Q12a", "Q12b", "Q12c", "Q12d", "Q12e", "Q13a", "Q13b", "Q13c", "Q13d", "Q13e", "Q14a", "Q14b", "Q14c", "Q14d", "Q14e", "Q15a", "Q15b", "Q15c", "Q15d", "Q15e")]
library(pastecs)library(dplyr)
NLB_PCA <- NLB_PCA %>%
rename(
Cash_Security = Q10a,
Debit_Security = Q10b,
Credit_Security = Q10c,
Mobile_Security = Q10d,
NeoBanks_Security = Q10e,
Cash_Ease = Q11a,
Debit_Ease = Q11b,
Credit_Ease = Q11c,
Mobile_Ease = Q11d,
NeoBanks_Ease = Q11e,
Cash_Availability = Q12a,
Debit_Availability = Q12b,
Credit_Availability = Q12c,
Mobile_Availability = Q12d,
NeoBanks_Availability = Q12e,
Cash_Speed = Q13a,
Debit_Speed = Q13b,
Credit_Speed = Q13c,
Mobile_Speed = Q13d,
NeoBanks_Speed = Q13e,
Cash_Privacy = Q14a,
Debit_Privacy = Q14b,
Credit_Privacy = Q14c,
Mobile_Privacy = Q14d,
NeoBanks_Privacy = Q14e,
Cash_Control = Q15a,
Debit_Control = Q15b,
Credit_Control = Q15c,
Mobile_Control = Q15d,
NeoBanks_Control = Q15e)library(tibble)
perceptual <- NLB_PCA %>%
pivot_longer(everything(), names_to = "name", values_to = "score") %>%
separate(name, into = c("Payment method", "Variable"), sep = "_")%>%
pivot_wider(names_from = Variable, values_from = score, values_fn = mean) %>%
column_to_rownames(var = "Payment method")
print(perceptual)## Security Ease Availability Speed Privacy Control
## Cash 5.503289 5.101974 6.226974 4.075658 5.680921 4.851974
## Debit 5.138158 6.148026 6.483553 6.174342 4.457237 5.154605
## Credit 4.947368 6.019737 6.335526 6.121711 4.457237 5.006579
## Mobile 5.174342 6.480263 6.029605 6.526316 4.394737 5.161184
## NeoBanks 4.825658 5.592105 5.075658 5.684211 4.483553 5.115132library(FactoMineR)
pca <- PCA(perceptual,
scale.unit = TRUE,
graph = FALSE,
ncp = 2)print(pca$var$cor)## Dim.1 Dim.2
## Security -0.7563320 0.534605714
## Ease 0.8659604 0.465478553
## Availability -0.1808968 0.942766082
## Speed 0.9753947 0.204881709
## Privacy -0.9934258 0.026725632
## Control 0.9275822 -0.001610424library(factoextra)
fviz_pca_biplot(pca,
repel = TRUE)