mirror of
https://github.com/Rucknium/misc-research.git
synced 2025-01-19 00:34:32 +00:00
Add Banking-the-Unbanked-through-Cryptocurrency
This commit is contained in:
Rucknium
parent
d962be7a9a
commit
22ffd837d8
20 changed files with 2367 additions and 0 deletions
File diff suppressed because it is too large
Load diff
Binary file not shown.
33
Banking-the-Unbanked-through-Cryptocurrency/README.md
Normal file
33
Banking-the-Unbanked-through-Cryptocurrency/README.md
Normal file
|
|
@ -0,0 +1,33 @@
|
|||
|
||||
## Hard Data on Banking the Unbanked through Cryptocurrency
|
||||
|
||||
### Instructions
|
||||
|
||||
Install the necessary R packages:
|
||||
|
||||
```R
|
||||
install.packages(c("data.table", "readstata13", "ggplot2", "stargazer",
|
||||
"huxtable", "rvest", "ggcorrplot", "grid", "remotes"))
|
||||
|
||||
remotes::install_github("dracula/ggplot2")
|
||||
```
|
||||
|
||||
Download the survey data files and unpack them into the appropriate directories in the `raw-data` directory:
|
||||
|
||||
- [SHED 2021-2023 STATA files](https://doi.org/10.17016/datasets.002)
|
||||
- [SPACE 2022](https://web.archive.org/web/20230922180752/https://www.ecb.europa.eu/stats/ecb_surveys/space/html/index.en.html#dd)
|
||||
- [SDCPC 2015 R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-of-consumer-payment-choice/2015-survey)
|
||||
- [SDCPC 2016 R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-of-consumer-payment-choice/2016-survey)
|
||||
- [SDCPC 2017 R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-of-consumer-payment-choice/2017-survey)
|
||||
- [SDCPC 2018 R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-of-consumer-payment-choice/2018-survey#Tab3)
|
||||
- [SDCPC 2019 R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-of-consumer-payment-choice/2019-survey#Tab3)
|
||||
- [SDCPC 2020 R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-of-consumer-payment-choice/2020-survey#Tab3)
|
||||
- [SDCPC 2021 R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-and-diary-of-consumer-payment-choice/2021-survey-and-diary#Tab3)
|
||||
- [SDCPC 2022 individual-level R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-and-diary-of-consumer-payment-choice/2022-survey-and-diary#Tab3)
|
||||
- [SDCPC 2023 individual-level R data file](https://www.atlantafed.org/banking-and-payments/consumer-payments/survey-and-diary-of-consumer-payment-choice/2023-survey-and-diary#Tab3)
|
||||
|
||||
Run `SHED-data-prep.R`, `SPACE-data-prep.R`, and `SDCPC-data-prep.R` to produce the processed data files and save them in the `processed-data` directory.
|
||||
|
||||
Then run `Banking-the-Unbanked-through-Cryptocurrency.Rmd` in RStudio to produce the PDF. You may have to install some LaTeX packages.
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,85 @@
|
|||
|
||||
|
||||
library(data.table)
|
||||
|
||||
S_DCPC.2023 <- readRDS("raw-data/S-DCPC_2023/dcpc_2023_indlevel_public_rds.rds")
|
||||
S_DCPC.2022 <- readRDS("raw-data/S-DCPC_2022/dcpc_2022_indlevel_public_rds.rds")
|
||||
S_DCPC.2021 <- readRDS("raw-data/S-DCPC_2021/dcpc_2021_indlevel_public_rds.rds")
|
||||
S_DCPC.2020 <- readRDS("raw-data/S-DCPC_2020/scpc_2020_public_rds.rds")
|
||||
S_DCPC.2019 <- readRDS("raw-data/S-DCPC_2019/scpc_2019_public_rds.rds")
|
||||
S_DCPC.2018 <- readRDS("raw-data/S-DCPC_2018/scpc_2018_rds.rds")
|
||||
S_DCPC.2017 <- readRDS("raw-data/S-DCPC_2017/scpc_2017_rds.rds")
|
||||
S_DCPC.2016 <- readRDS("raw-data/S-DCPC_2016/scpc_2016_rds.rds")
|
||||
S_DCPC.2015 <- readRDS("raw-data/S-DCPC_2015/scpc_2015_rds.rds")
|
||||
|
||||
|
||||
for (i in 2015:2023) {
|
||||
print(nrow(get(paste0("S_DCPC.", i))))
|
||||
}
|
||||
|
||||
|
||||
|
||||
reason <- do.call(rbind, list(
|
||||
data.frame(year = 2023, reason = S_DCPC.2023$pa126_a, weight = S_DCPC.2023$ind_weight_all),
|
||||
data.frame(year = 2022, reason = S_DCPC.2022$pa126_a, weight = S_DCPC.2022$ind_weight_all),
|
||||
data.frame(year = 2021, reason = S_DCPC.2021$pa126_a, weight = S_DCPC.2021$ind_weight_all),
|
||||
data.frame(year = 2020, reason = S_DCPC.2020$pa126_a, weight = S_DCPC.2020$r_weight),
|
||||
data.frame(year = 2019, reason = S_DCPC.2019$pa126_a, weight = S_DCPC.2019$r_weight),
|
||||
data.frame(year = 2018, reason = S_DCPC.2018$pa126_a, weight = S_DCPC.2018$r_weight),
|
||||
data.frame(year = 2017, reason = S_DCPC.2017$pa126_a, weight = S_DCPC.2017$r_weight),
|
||||
data.frame(year = 2016, reason = S_DCPC.2016$pa126_a, weight = S_DCPC.2016$r_weight),
|
||||
data.frame(year = 2015, reason = S_DCPC.2015$pa126_a, weight = S_DCPC.2015$r_weight)
|
||||
))
|
||||
|
||||
setDT(reason)
|
||||
|
||||
owns.crypto <- reason
|
||||
owns.crypto[, owns.crypto := ! is.na(reason)]
|
||||
|
||||
reason <- reason[ ! is.na(reason), ]
|
||||
reason[, reason := as.character(reason)]
|
||||
|
||||
reason[reason %in% c(1, 2, 4), reason := "Payments"]
|
||||
reason[reason %in% c(3), reason := "Investment"]
|
||||
reason[reason %in% c(5, 9), reason := "Other"]
|
||||
reason[reason %in% c(6), reason := "Interest in new tech"]
|
||||
reason[reason %in% c(7, 8), reason := "Don't trust banks/government/USD"]
|
||||
|
||||
reason[, reason := factor(reason, levels =
|
||||
c("Investment", "Payments", "Interest in new tech", "Don't trust banks/government/USD", "Other"))]
|
||||
|
||||
reason <- aggregate(weight ~ reason + year, data = reason, FUN = sum, drop = FALSE)
|
||||
|
||||
setDT(reason)
|
||||
|
||||
reason[is.na(weight), weight := 0]
|
||||
|
||||
reason <- reason[, .(reason = reason, share = 100 * weight / sum(weight)), by = "year"]
|
||||
|
||||
|
||||
owns.crypto <- aggregate(weight ~ owns.crypto + year, data = owns.crypto, FUN = sum, drop = FALSE)
|
||||
setDT(owns.crypto)
|
||||
owns.crypto[is.na(weight), weight := 0]
|
||||
owns.crypto <- owns.crypto[, .(owns.crypto = owns.crypto, share = 100 * weight / sum(weight)), by = "year"]
|
||||
|
||||
owns.crypto <- owns.crypto[ (owns.crypto), ]
|
||||
setnames(owns.crypto, "owns.crypto", "reason")
|
||||
owns.crypto$reason <- NULL
|
||||
owns.crypto$reason <- "Owns crypto"
|
||||
|
||||
owns.crypto[, panel := "Owns crypto"]
|
||||
|
||||
reason[, panel := "Primary reason"]
|
||||
|
||||
reason.owns.crypto <- rbind(reason, owns.crypto)
|
||||
|
||||
reason.owns.crypto[, panel := factor(panel, levels = c("Owns crypto", "Primary reason"))]
|
||||
|
||||
|
||||
reason.owns.crypto[, year := factor(year)]
|
||||
|
||||
|
||||
saveRDS(reason.owns.crypto, file = "processed-data/reason-owns-crypto.rds")
|
||||
|
||||
|
||||
|
||||
413
Banking-the-Unbanked-through-Cryptocurrency/SHED-data-prep.R
Normal file
413
Banking-the-Unbanked-through-Cryptocurrency/SHED-data-prep.R
Normal file
|
|
@ -0,0 +1,413 @@
|
|||
|
||||
|
||||
library(data.table)
|
||||
library(readstata13)
|
||||
library(survey)
|
||||
|
||||
|
||||
SHED <- list()
|
||||
|
||||
SHED[["2021"]] <- readstata13::read.dta13("raw-data/SHED_2021/public2021.dta", generate.factors = TRUE, nonint.factors = TRUE)
|
||||
SHED[["2022"]] <- readstata13::read.dta13("raw-data/SHED_2022/public2022.dta", generate.factors = TRUE, nonint.factors = TRUE)
|
||||
SHED[["2023"]] <- readstata13::read.dta13("raw-data/SHED_2023/public2023.dta", generate.factors = TRUE, nonint.factors = TRUE)
|
||||
|
||||
crypto.used.as.payment_annual.trend <- c()
|
||||
|
||||
for (i in names(SHED)) {
|
||||
SHED[[i]]$crypto.used.as.payment <- SHED[[i]]$S16_b == "Yes"
|
||||
SHED[[i]] <- svydesign(ids = ~0, data = SHED[[i]], weights = SHED[[i]]$weight)
|
||||
crypto.used.as.payment_annual.trend[[i]] <-
|
||||
round(100 * as.data.frame(svymean(~ crypto.used.as.payment, design = SHED[[i]], na.rm = TRUE))[2, 1], 1)
|
||||
}
|
||||
|
||||
saveRDS(crypto.used.as.payment_annual.trend, file = "processed-data/SHED-annual-trend.rds")
|
||||
|
||||
|
||||
# Then re-do it for the pooled dataset
|
||||
|
||||
|
||||
SHED <- list()
|
||||
|
||||
SHED[["2021"]] <- readstata13::read.dta13("raw-data/SHED_2021/public2021.dta", generate.factors = TRUE, nonint.factors = TRUE)
|
||||
SHED[["2022"]] <- readstata13::read.dta13("raw-data/SHED_2022/public2022.dta", generate.factors = TRUE, nonint.factors = TRUE)
|
||||
SHED[["2023"]] <- readstata13::read.dta13("raw-data/SHED_2023/public2023.dta", generate.factors = TRUE, nonint.factors = TRUE)
|
||||
|
||||
|
||||
colnames(SHED[["2021"]]) <- paste0(colnames(SHED[["2021"]]), ".2021")
|
||||
colnames(SHED[["2022"]]) <- paste0(colnames(SHED[["2022"]]), ".2022")
|
||||
colnames(SHED[["2023"]]) <- paste0(colnames(SHED[["2023"]]), ".2023")
|
||||
|
||||
SHED.panel <- merge(SHED[["2021"]], SHED[["2022"]], by.x = "CaseID.2021", by.y = "caseid2021.2022",
|
||||
all = TRUE)
|
||||
|
||||
SHED.panel <- merge(SHED.panel, SHED[["2023"]], by.x = "CaseID.2022", by.y = "caseid2022.2023",
|
||||
all = TRUE, incomparables = NA)
|
||||
# NOTE: merge.data.frame() and merge.data.table() have different behaviors with incomparables = NA
|
||||
|
||||
|
||||
|
||||
|
||||
pooled.vars <- c(
|
||||
"S16_a",
|
||||
"S16_b",
|
||||
"S16_c",
|
||||
"S18", "S19_a", "S19_b", "S19_c", "S20_a", "S20_b", "S20_c", "S20_d",
|
||||
"BK1",
|
||||
"C2A",
|
||||
"ppgender",
|
||||
"race_5cat",
|
||||
"ED0",
|
||||
"ED1",
|
||||
"pppa_lgb",
|
||||
"ppp20197",
|
||||
"I40",
|
||||
"B2",
|
||||
"I41_b",
|
||||
"FL0",
|
||||
"B10",
|
||||
"ppage",
|
||||
"ppcmdate",
|
||||
"ind1",
|
||||
"ppcm0160",
|
||||
"ppcm1301",
|
||||
"ppmsacat",
|
||||
"ppfs0596",
|
||||
"A1_a",
|
||||
"BK2_a",
|
||||
"BK2_b",
|
||||
"BK2_c",
|
||||
"BK2_d",
|
||||
"BK2_e",
|
||||
"BNPL1",
|
||||
"ppfs1482",
|
||||
"GE2A",
|
||||
"GE1A",
|
||||
"E7",
|
||||
"E8_b",
|
||||
"xlaptop",
|
||||
"devicetype2",
|
||||
"S21"
|
||||
)
|
||||
|
||||
for (pooled.var in pooled.vars) {
|
||||
|
||||
# if (pooled.var == "S19_b") {stop()}
|
||||
|
||||
SHED.panel[, paste0(pooled.var, ".pooled")] <- NA
|
||||
|
||||
valid.var.col.name <- intersect(colnames(SHED.panel), paste0(pooled.var, ".", 2021:2023))[1]
|
||||
|
||||
var.transform <- ifelse(is.factor(SHED.panel[, valid.var.col.name]), as.character, identity)
|
||||
|
||||
for (i in as.character(2021:2023)) {
|
||||
|
||||
if ( ! (paste0(pooled.var, ".", i) %in% colnames(SHED.panel) ) ) {
|
||||
next
|
||||
}
|
||||
|
||||
SHED.panel[is.na(SHED.panel[, paste0(pooled.var, ".pooled")]), paste0(pooled.var, ".pooled")] <-
|
||||
var.transform(SHED.panel[is.na(SHED.panel[, paste0(pooled.var, ".pooled")]), paste0(pooled.var, ".", i)])
|
||||
}
|
||||
|
||||
if (is.factor(SHED.panel[, valid.var.col.name])) {
|
||||
SHED.panel[, paste0(pooled.var, ".pooled")] <- factor(SHED.panel[, paste0(pooled.var, ".pooled")])
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
SHED.panel$panel_weight.common <- apply(
|
||||
SHED.panel[, c("panel_weight.2021", "panel_weight.2022", "panel_weight.2023")], MARGIN = 1,
|
||||
FUN = function(x) {
|
||||
y <- unique(na.omit(x))
|
||||
if (length(y) == 0) { return(0) }
|
||||
return(mean(y))
|
||||
})
|
||||
|
||||
SHED.panel$panel_weight.common[SHED.panel$panel_weight.common == 0 & !is.na(SHED.panel$weight.2021)] <-
|
||||
SHED.panel$weight.2021[SHED.panel$panel_weight.common == 0 & !is.na(SHED.panel$weight.2021)]
|
||||
|
||||
SHED.panel$panel_weight.common[SHED.panel$panel_weight.common == 0 & !is.na(SHED.panel$weight.2022)] <-
|
||||
SHED.panel$weight.2022[SHED.panel$panel_weight.common == 0 & !is.na(SHED.panel$weight.2022)]
|
||||
|
||||
SHED.panel$panel_weight.common[SHED.panel$panel_weight.common == 0 & !is.na(SHED.panel$weight.2023)] <-
|
||||
SHED.panel$weight.2023[SHED.panel$panel_weight.common == 0 & !is.na(SHED.panel$weight.2023)]
|
||||
# Weighting is a little improvised
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# S16_a
|
||||
# Bought cryptocurrency or held as an
|
||||
# investment - In the past year, have you done
|
||||
# the following with cryptocurrency, such as
|
||||
# Bitcoin or Ethereum?
|
||||
SHED.panel$crypto.used.as.investment <- SHED.panel$S16_a.pooled == "Yes"
|
||||
|
||||
|
||||
# S16_b
|
||||
# In the past year, have you done the following
|
||||
# with cryptocurrency, such as Bitcoin or Ethereum?
|
||||
# - Used to buy something or make a payment
|
||||
SHED.panel$crypto.used.as.payment <- SHED.panel$S16_b.pooled == "Yes"
|
||||
|
||||
# S16_c
|
||||
# Used cryptocurrency to send money to friends
|
||||
# or family - In the past year, have you done
|
||||
# the following with cryptocurrency, such as
|
||||
# Bitcoin or Ethereum?
|
||||
SHED.panel$crypto.used.to.send.money <- SHED.panel$S16_c.pooled == "Yes"
|
||||
|
||||
# S18
|
||||
# Were any of the family or friends you sent
|
||||
# cryptocurrency to living outside of the
|
||||
# United States?
|
||||
SHED.panel$crypto.used.to.send.money.outside.us <- SHED.panel$S18.pooled == "Yes"
|
||||
|
||||
# S19_a
|
||||
# Buy something in-person - Have you used
|
||||
# cryptocurrency to do each of the following?
|
||||
SHED.panel$crypto.used.as.payment.in.person <- SHED.panel$S19_a.pooled == "Yes"
|
||||
|
||||
|
||||
# S19_b
|
||||
# Buy something online - Have you used
|
||||
# cryptocurrency to do each of the following?
|
||||
SHED.panel$crypto.used.as.payment.online <- SHED.panel$S19_b.pooled == "Yes"
|
||||
|
||||
# S19_c
|
||||
# Pay a bill online - Have you used
|
||||
# cryptocurrency to do each of the following?
|
||||
SHED.panel$crypto.used.as.payment.online.bill.pay <- SHED.panel$S19_c.pooled == "Yes"
|
||||
|
||||
|
||||
# S20_a
|
||||
# Convert cash into cryptocurrency - Have you
|
||||
# used a cryptocurrency ATM/kiosk to do each of
|
||||
# the following?
|
||||
SHED.panel$crypto.atm.convert.cash.to.crypto <- SHED.panel$S20_a.pooled == "Yes"
|
||||
|
||||
# S20_b
|
||||
# Withdraw cash - Have you used a cryptocurrency
|
||||
# ATM/kiosk to do each of the following?
|
||||
SHED.panel$crypto.atm.withdraw.cash <- SHED.panel$S20_b.pooled == "Yes"
|
||||
|
||||
# S20_c
|
||||
# Make a payment - Have you used a
|
||||
# cryptocurrency ATM/kiosk to do each of the
|
||||
# following?
|
||||
SHED.panel$crypto.atm.make.payment <- SHED.panel$S20_c.pooled == "Yes"
|
||||
|
||||
# S20_d
|
||||
# Send money to family or friends - Have you
|
||||
# used a cryptocurrency ATM/kiosk to do each of
|
||||
# the following?
|
||||
SHED.panel$crypto.atm.send.money <- SHED.panel$S20_d.pooled == "Yes"
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# BK1
|
||||
# Do you and/or your spouse or partner
|
||||
# currently have a checking, savings or money
|
||||
# market account?
|
||||
SHED.panel$lacks.bank.account <- SHED.panel$BK1.pooled == "No"
|
||||
|
||||
# C2A
|
||||
# Do you currently have at least one credit card?
|
||||
SHED.panel$lacks.credit.card <- SHED.panel$C2A.pooled == "No"
|
||||
|
||||
# ppgender
|
||||
# Gender [Ipsos source]
|
||||
SHED.panel$is.male <- SHED.panel$ppgender.pooled == "Male"
|
||||
|
||||
# race_5cat Race 5 categories
|
||||
SHED.panel$race <- SHED.panel$race_5cat.pooled
|
||||
|
||||
# ED0
|
||||
# What is the highest level of school you have
|
||||
# completed or the highest degree you have
|
||||
# received?
|
||||
SHED.panel$education.level <- relevel(SHED.panel$ED0.pooled, "High school degree or GED")
|
||||
|
||||
# ED1
|
||||
# Which one of the following broad categories
|
||||
# best describes your (current/most recent)
|
||||
# educational program?
|
||||
SHED.panel$education.subject <- relevel(SHED.panel$ED1.pooled, "Business/management")
|
||||
|
||||
# pppa_lgb [Ipsos source]
|
||||
# Q230: Which of the following best describes how you think of yourself?
|
||||
SHED.panel$lgbtq <- relevel(SHED.panel$pppa_lgb.pooled, "Straight, that is, not gay")
|
||||
|
||||
# ppp20197 [Ipsos source]
|
||||
# QEG22: Are you a citizen of the United States?
|
||||
SHED.panel$is.noncitizen <- SHED.panel$ppp20197.pooled == "No"
|
||||
|
||||
# I40
|
||||
# Which of the following categories best
|
||||
# describes the total income that you and/or
|
||||
# your spouse or partner received from all
|
||||
# sources, before taxes and deductions, in the
|
||||
# past 12 months?
|
||||
SHED.panel$income.category <- SHED.panel$I40.pooled
|
||||
|
||||
# B2
|
||||
# Overall, which one of the following best
|
||||
# describes how well you are managing
|
||||
# financially these days?
|
||||
SHED.panel$overall.financial.wellbeing <- SHED.panel$B2.pooled
|
||||
|
||||
# I41_b
|
||||
# Supplemental Nutrition Assistance Program
|
||||
# (SNAP or food stamps) - In the past 12
|
||||
# months, have you received any of the
|
||||
# following?
|
||||
SHED.panel$received.food.stamps <- SHED.panel$I41_b.pooled
|
||||
|
||||
# FL0
|
||||
# On a scale from zero to ten, where zero is
|
||||
# not at all willing to take risks and ten is
|
||||
# very willing to take risks, what number would
|
||||
# you be on the scale?
|
||||
|
||||
SHED.panel$risk.tolerance <- as.numeric(SHED.panel$FL0.pooled) - 1
|
||||
|
||||
# B10
|
||||
# Overall, on a scale from zero to ten, where
|
||||
# zero is not at all satisfied and ten is
|
||||
# completely satisfied, how satisfied are you
|
||||
# with life as a whole these days?
|
||||
SHED.panel$life.satisfaction <- as.numeric(SHED.panel$B10.pooled) - 1
|
||||
|
||||
# ppage
|
||||
# Age [Ipsos source]
|
||||
# ppcmdate
|
||||
# Date member completed Core survey
|
||||
# Must correct age variable for time of initial Ipsos survey
|
||||
SHED.panel$age <- SHED.panel$ppage.pooled + (2021 - as.numeric(substr(SHED.panel$ppcmdate.pooled, 1, 4)))
|
||||
|
||||
# ind1
|
||||
# IND1: Industry (tight scale) in current or main job
|
||||
SHED.panel$job.industry <- relevel(SHED.panel$ind1.pooled, "Retail/Stores/Shopping (including Online Retail)")
|
||||
|
||||
# ppcm0160 [Ipsos source]
|
||||
# Q26: Occupation (detailed) in current or main job
|
||||
SHED.panel$job.occupation <- relevel(SHED.panel$ppcm0160.pooled, "Food Preparation and Serving")
|
||||
|
||||
# ppcm1301 [Ipsos source]
|
||||
# GOVEMP1: Employer type
|
||||
SHED.panel$employer.type <- relevel(SHED.panel$ppcm1301.pooled, "Private-for-profit company")
|
||||
|
||||
# ppmsacat
|
||||
# MSA Status [Ipsos source]
|
||||
SHED.panel$resides.in.metro.statistical.area <- SHED.panel$ppmsacat.pooled == "Metro"
|
||||
|
||||
# ppfs0596 [Ipsos source]
|
||||
# Q22: What is the approximate total amount of
|
||||
# your household's savings and investments?
|
||||
SHED.panel$total.household.savings <- relevel(SHED.panel$ppfs0596.pooled, "$100,000 - $249,999")
|
||||
|
||||
# A1_a
|
||||
# In the past 12 months, has each of the following happened to you:
|
||||
# - Turned down for credit
|
||||
SHED.panel$rejected.for.credit <- SHED.panel$A1_a.pooled == "Yes"
|
||||
|
||||
# BK2_a
|
||||
# In the past 12 months, did you and/or spouse or partner:
|
||||
# - Purchase a money order from a place other than a bank
|
||||
SHED.panel$purchase.non.bank.money.order <- SHED.panel$BK2_a.pooled == "Yes"
|
||||
|
||||
# BK2_b
|
||||
# In the past 12 months, did you and/or spouse or partner:
|
||||
# - Cash a check at a place other than a bank
|
||||
SHED.panel$cash.check.non.bank <- SHED.panel$BK2_b.pooled == "Yes"
|
||||
|
||||
# BK2_c
|
||||
# In the past 12 months, did you and/or spouse or partner:
|
||||
# - Take out a payday loan or payday advance
|
||||
SHED.panel$take.payday.loan <- SHED.panel$BK2_c.pooled == "Yes"
|
||||
|
||||
# BK2_d
|
||||
# In the past 12 months, did you and/or spouse or partner:
|
||||
# - Take out a pawn shop loan or an auto title loan
|
||||
SHED.panel$take.auto.or.pawn.shop.loan <- SHED.panel$BK2_d.pooled == "Yes"
|
||||
|
||||
# BK2_e
|
||||
# In the past 12 months, did you and/or spouse or partner:
|
||||
# - Obtain a tax refund advance to receive your refund faster
|
||||
SHED.panel$take.tax.refund.advance <- SHED.panel$BK2_e.pooled == "Yes"
|
||||
|
||||
# BNPL1
|
||||
# In the past year, have you used a “Buy Now
|
||||
# Pay Later” service to buy something?
|
||||
SHED.panel$used.buy.now.pay.later <- SHED.panel$BNPL1.pooled == "Yes"
|
||||
|
||||
# ppfs1482 [Ipsos source]
|
||||
# Q108: Where do you think your credit score falls
|
||||
SHED.panel$perceived.credit.score <- factor(SHED.panel$ppfs1482.pooled, levels = c("Fair", "Excellent", "Good", "Poor", "Very poor", "Don’t know"))
|
||||
# Note "Don’t know" has a curved apostrophe ’
|
||||
|
||||
# GE2A
|
||||
# Some people earn money by selling items at
|
||||
# places like flea markets and garage sales or
|
||||
# through online marketplaces like eBay or
|
||||
# Etsy. In the past month, have you made money
|
||||
# by selling items in any of these ways?
|
||||
|
||||
SHED.panel$informal.selling.of.goods <- SHED.panel$GE2A.pooled == "Yes"
|
||||
|
||||
# GE1A
|
||||
# In the past month, have you done any
|
||||
# freelance or gig-work, either to supplement
|
||||
# your income or as your main job?
|
||||
|
||||
SHED.panel$freelance.or.gig.work <- SHED.panel$GE1A.pooled == "Yes"
|
||||
|
||||
# E7
|
||||
# During the past 12 months, have you
|
||||
# personally experienced discrimination or
|
||||
# unfair treatment because of your race,
|
||||
# ethnicity, age, religion, disability status,
|
||||
# sexual orientation, gender, or gender
|
||||
# identity?
|
||||
SHED.panel$experienced.discrimination <- SHED.panel$E7.pooled == "Yes"
|
||||
|
||||
# E8_b
|
||||
# In the past 12 months, did you personally experience
|
||||
# discrimination or unfair treatment while
|
||||
# doing any of the following?
|
||||
# - Banking or applying for a loan
|
||||
SHED.panel$experienced.discrimination.in.banking <- SHED.panel$E8_b.pooled == "Yes"
|
||||
|
||||
# xlaptop
|
||||
# Is R a KP laptop user?
|
||||
SHED.panel$is.kp.laptop.user <- SHED.panel$xlaptop.pooled == "Yes"
|
||||
|
||||
# devicetype2
|
||||
# DOV: Device Type - at the end of survey
|
||||
SHED.panel$respondent.device.type <- relevel(SHED.panel$devicetype2.pooled, "WinPC")
|
||||
|
||||
# S21
|
||||
# What was the main reason you used
|
||||
# cryptocurrency to buy something, make a
|
||||
# payment, or send money?
|
||||
SHED.panel$why.used.crypto.as.payment <- SHED.panel$S21.pooled
|
||||
|
||||
|
||||
|
||||
SHED.panel.survey <- svydesign(ids = ~0, data = SHED.panel, weights = SHED.panel$panel_weight.common)
|
||||
SHED.survey <- SHED.panel.survey
|
||||
|
||||
|
||||
saveRDS(SHED.survey, file = "processed-data/SHED.rds")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
197
Banking-the-Unbanked-through-Cryptocurrency/SPACE-data-prep.R
Normal file
197
Banking-the-Unbanked-through-Cryptocurrency/SPACE-data-prep.R
Normal file
|
|
@ -0,0 +1,197 @@
|
|||
|
||||
|
||||
library(data.table)
|
||||
library(survey)
|
||||
library(stargazer)
|
||||
library(huxtable)
|
||||
library(rvest)
|
||||
|
||||
|
||||
SPACE <- read.csv("raw-data/SPACE_2022/SPACE_wide_2022.csv", stringsAsFactors = FALSE)
|
||||
|
||||
country.names <- matrix(c(
|
||||
"CY", "Cyprus",
|
||||
"MT", "Malta",
|
||||
"BE", "Belgium",
|
||||
"IT", "Italy",
|
||||
"ES", "Spain",
|
||||
"GR", "Greece",
|
||||
"AT", "Austria",
|
||||
"EE", "Estonia",
|
||||
"FI", "Finland",
|
||||
"IE", "Ireland",
|
||||
"LT", "Lithuania",
|
||||
"LU", "Luxembourg",
|
||||
"LV", "Latvia",
|
||||
"PT", "Portugal",
|
||||
"SI", "Slovenia",
|
||||
"SK", "Slovakia",
|
||||
"FR", "France"
|
||||
), ncol = 2, byrow = TRUE)
|
||||
|
||||
colnames(country.names) <- c("COUNTRY", "COUNTRY.name")
|
||||
country.names <- as.data.frame(country.names)
|
||||
|
||||
SPACE <- merge(SPACE, country.names)
|
||||
|
||||
continuous.age <- matrix(c(
|
||||
1, median(c(18, 24)),
|
||||
2, median(c(25, 29)),
|
||||
3, median(c(30, 34)),
|
||||
4, median(c(35, 39)),
|
||||
5, median(c(40, 44)),
|
||||
6, median(c(45, 49)),
|
||||
7, median(c(50, 54)),
|
||||
8, median(c(55, 59)),
|
||||
9, median(c(60, 64)),
|
||||
10, median(c(64, 69)),
|
||||
11, median(c(70, 74)),
|
||||
12, 85),
|
||||
ncol = 2, byrow = TRUE)
|
||||
|
||||
colnames(continuous.age) <- c("AGE", "Age")
|
||||
continuous.age <- as.data.frame(continuous.age)
|
||||
|
||||
SPACE <- merge(SPACE, continuous.age)
|
||||
|
||||
colnames(continuous.age) <- c("AGE", "Age")
|
||||
continuous.age <- as.data.frame(continuous.age)
|
||||
|
||||
SPACE <- merge(SPACE, continuous.age)
|
||||
|
||||
SPACE$Gender <- factor(SPACE$D1, level = 1:3, labels = c("Male", "Female", "Other, non-binary"))
|
||||
SPACE$Gender <- relevel(SPACE$Gender, "Female")
|
||||
|
||||
|
||||
cash.reserves.amount <- c(
|
||||
"Less than €100",
|
||||
"€100 - €250",
|
||||
"€250 - €500",
|
||||
"€500 - €1,000",
|
||||
"€1,000 - €5,000",
|
||||
"€5,000 - €10,000",
|
||||
"More than €10,000"
|
||||
)
|
||||
|
||||
SPACE$cash.reserves.amount <- factor(SPACE$QQ10, level = 1:7, labels = cash.reserves.amount)
|
||||
|
||||
SPACE$cash.reserves.any <- factor(SPACE$QQ9, level = 0:1, labels = c("No", "Yes"))
|
||||
|
||||
SPACE$cash.reserves <- ifelse(SPACE$cash.reserves.any == "Yes",
|
||||
as.character(SPACE$cash.reserves.amount), "€0")
|
||||
|
||||
SPACE$cash.reserves <- as.factor(SPACE$cash.reserves)
|
||||
|
||||
setDT(SPACE)
|
||||
|
||||
SPACE[, has.crypto := factor(QQ1A_3, levels = 0:1, labels = c("No", "Yes"))]
|
||||
|
||||
SPACE[, crypto.use := factor(QQ1B, levels = 0:3, labels = c("None", "Investment", "Payment", "Both"))]
|
||||
SPACE[is.na(crypto.use), crypto.use := "None"]
|
||||
|
||||
table(SPACE$crypto.use)
|
||||
table(SPACE$has.crypto)
|
||||
|
||||
|
||||
SPACE[, has.payment.account := factor(QQ1A_1, labels = c("No", "Yes"))]
|
||||
SPACE[, has.card := factor(QQ1A_2, labels = c("No", "Yes"))]
|
||||
|
||||
SPACE[, has.financial.investments := factor(D10_6, labels = c("No", "Yes"))]
|
||||
|
||||
SPACE[, has.savings.account := factor(D10_3, labels = c("No", "Yes"))]
|
||||
|
||||
SPACE[, PaymentPreference := factor(QQ3, levels = c(3, 1:2), labels = c("No preference", "Cash", "Cashless"))]
|
||||
# Put no preference first so it is the contrast level
|
||||
|
||||
SPACE[, "cash.wide.acceptance" := factor(QQ13A_1, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.faster" := factor(QQ13A_2, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.privacy" := factor(QQ13A_3, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.easier" := factor(QQ13A_4, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.safer" := factor(QQ13A_5, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.immediately.settled" := factor(QQ13A_6, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.spending.awareness" := factor(QQ13A_7, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.other" := factor(QQ13A_8, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.no.use" := factor(QQ13A_9, labels = c("No", "Yes"))]
|
||||
SPACE[, "cash.none" := factor(QQ13A_10, labels = c("No", "Yes"))]
|
||||
|
||||
|
||||
|
||||
SPACE.survey <- svydesign(ids = ~ID, data = SPACE, weights = SPACE$Gross_weight)
|
||||
|
||||
saveRDS(SPACE.survey, file = "processed-data/SPACE.rds")
|
||||
|
||||
|
||||
# Load the data again to get the diary data
|
||||
|
||||
space <- read.csv("raw-data/SPACE_2022/SPACE_wide_2022.csv", stringsAsFactors = FALSE)
|
||||
|
||||
|
||||
setDT(space)
|
||||
|
||||
space.diary <- melt(space[, c("ID", "D1", "AGE", "WEEKDAY", "COUNTRY", "Gross_weight", colnames(space)[grepl("^QB", colnames(space))]), with = FALSE],
|
||||
measure.vars = patterns(purpose = "^QB1", value = "^QB3", instrument = "^QB4"))
|
||||
|
||||
|
||||
|
||||
SPACE.diary <- melt(SPACE[, c("ID", "D1", "AGE", "WEEKDAY", "COUNTRY", "Gross_weight", colnames(SPACE)[grepl("^QB", colnames(SPACE))]), with = FALSE],
|
||||
measure.vars = patterns(purpose = "^QB1", value = "^QB3", instrument = "^QB4"))
|
||||
|
||||
|
||||
purpose.label <- c("Clothes/sportswear",
|
||||
"Electronic goods/household appliances",
|
||||
"Food/daily supplies",
|
||||
"Medicine/cosmetics/drugstore products",
|
||||
"Media/games/entertainment",
|
||||
"Charitable donations",
|
||||
"Travel/accommodation",
|
||||
"Furniture/other household items",
|
||||
"Tickets for events/attractions",
|
||||
"Luxury goods",
|
||||
"Financial: insurance, investment, crypto-assets",
|
||||
"Household related services",
|
||||
"Other")
|
||||
|
||||
|
||||
|
||||
SPACE.diary <- SPACE.diary[complete.cases(SPACE.diary), ]
|
||||
SPACE.diary[purpose == 999999, purpose := NA]
|
||||
SPACE.diary[value == 999999, value := NA]
|
||||
SPACE.diary[instrument == 999999, instrument := NA]
|
||||
|
||||
SPACE.diary[, D1 := factor(D1)]
|
||||
SPACE.diary[, AGE := factor(AGE)]
|
||||
SPACE.diary[, WEEKDAY := factor(WEEKDAY)]
|
||||
SPACE.diary[, COUNTRY := factor(COUNTRY)]
|
||||
SPACE.diary[, purpose := factor(purpose, levels = seq_along(purpose.label), labels = purpose.label)]
|
||||
SPACE.diary[, instrument := factor(instrument)]
|
||||
|
||||
SPACE.diary[, `Paid with crypto` := instrument == 10]
|
||||
|
||||
|
||||
SPACE.diary.survey <- svydesign(ids = ~ID, data = SPACE.diary, weights = SPACE.diary$Gross_weight)
|
||||
|
||||
|
||||
saveRDS(SPACE.diary.survey, file = "processed-data/SPACE_diary.rds")
|
||||
|
||||
|
||||
# This computation takes a while
|
||||
|
||||
aggregate.crypto.spending.clustered <- as.data.frame(svyby(~I(365*value/1e+09), ~`Paid with crypto`,
|
||||
design = as.svrepdesign(subset(SPACE.diary.survey,
|
||||
purpose != "Financial: insurance, investment, crypto-assets")), svytotal))
|
||||
|
||||
aggregate.crypto.spending.clustered.CI <- aggregate.crypto.spending.clustered[2, 3] * 1.645
|
||||
aggregate.crypto.spending.clustered[2, 2]
|
||||
aggregate.crypto.spending.clustered[2, 2] + c(-1 * aggregate.crypto.spending.clustered.CI, aggregate.crypto.spending.clustered.CI)
|
||||
|
||||
aggregate.crypto.spending.clustered <- list(
|
||||
point.estimate = aggregate.crypto.spending.clustered[2, 2],
|
||||
CI.90.percent = aggregate.crypto.spending.clustered[2, 2] +
|
||||
c(-1 * aggregate.crypto.spending.clustered.CI, aggregate.crypto.spending.clustered.CI)
|
||||
)
|
||||
|
||||
saveRDS(aggregate.crypto.spending.clustered, file = "processed-data/EU-aggregate-crypto-spending.rds")
|
||||
|
||||
|
||||
|
||||
|
||||
Loading…
Reference in a new issue