banks00_07 {npsf} | R Documentation |
U.S. Commercial Banks Data
Description
banks00_07
data frame contains selected variables for 500 (randomly sampled from around 5000) U.S. commercial banks from data of Koetter et al. (2012) for years 2000-2007. This data are used for illustrution purposes and are not suitable for research purposes.
Usage
data(banks00_07)
Format
This data frame contains the following variables (columns):
year
Year.
id
Entity ID.
TA
Gross total assets.
LLP
Loan loss provisions.
Y1
Total securities (in thousands of US dollars).
Y2
Total loans and leases (in thousands of US dollars).
W1
Cost of fixed assets divided by the cost of borrowed funds.
W2
Cost of labor (in thousands of US dollars) divided by the cost of borrowed funds.
ER
Gross total equity to gross total assets ratio.
TC
Total operating cost.
LA
Total loans and leases to gross total assets ratio.
Ti
Times bank is observed.
TA_ave
Mean value of TA.
TA_initial
Value of TA in the first observed year.
LLP_ave
Mean value of LLP.
LLP_initial
Value of LLP in the first observed year.
ER_ave
Mean value of ER.
ER_initial
Value of ER in the first observed year.
LA_ave
Mean value of LA.
LA_initial
Value of LA in the first observed year.
Details
The data were sampled and generated as shown in section "Examples".
Source
http://qed.econ.queensu.ca/jae/2014-v29.2/restrepo-tobon-kumbhakar/.
References
Koetter, M., Kolari, J., and Spierdijk, L. (2012), Enjoying the quiet life under deregulation? Evidence from adjusted Lerner indices for U.S. banks. Review of Economics and Statistics, 94, 2, 462–480.
Restrepo-Tobon, D. and Kumbhakar, S. (2014), Enjoying the quiet life under deregulation? Not Quite. Journal of Applied Econometrics, 29, 2, 333–343.
Examples
## Not run:
# Download data from the link in "Source"
banks00_07 <- read.delim("2b_QLH.txt")
# rename 'entity' to 'id'
colnames(banks00_07) [colnames(banks00_07) == "entity"] <- "id"
table(banks00_07$year)
# keep if 2000 -- 2007
banks00_07 <-
banks00_07[(banks00_07$year >= 2000 & banks00_07$year <= 2007),]
dim(banks00_07)
q1q3 <- quantile(banks00_07$TA, probs = c(.25,.75))
banks00_07 <-
banks00_07[(banks00_07$TA >= q1q3[1] & banks00_07$TA <= q1q3[2]),]
dim(banks00_07)
# generate required variables
banks00_07$TC <-banks00_07$TOC
banks00_07$ER <- banks00_07$Z / banks00_07$TA
banks00_07$LA <- banks00_07$Y2 / banks00_07$TA
banks00_07 <-
banks00_07[, colnames(banks00_07)
c("id", "year", "Ti", "TC", "Y1", "Y2", "W1","W2", "ER", "LA", "TA", "LLP")]
dim(banks00_07)
t0 <- as.vector( by(data = banks00_07$id,
INDICES = banks00_07$id,
FUN = function(qq) length(qq)) )
banks00_07$Ti <- rep(t0, times = t0)
banks00_07 <- banks00_07[banks00_07$Ti > 4,]
# complete observations
banks00_07 <- banks00_07[complete.cases(banks00_07),]
dim(banks00_07)
id_names <- unique(banks00_07$id)
N_total <- length(id_names)
set.seed(816376586)
ids_n2choose <- sample(1:N_total, 500)
ids2choose <- id_names[ids_n2choose]
banks00_07 <- banks00_07[banks00_07$id
dim(banks00_07)
t0 <- as.vector( by(data = banks00_07$id,
INDICES = banks00_07$id,
FUN = function(qq) length(qq)) )
length(rep(t0, times = t0))
banks00_07$Ti <- rep(t0, times = t0)
banks00_07[1:50,c("id","year","Ti")]
# keep if Ti > 4
banks00_07 <- banks00_07[banks00_07$Ti > 4,]
dim(banks00_07)
# sort
banks00_07 <- banks00_07[order(banks00_07$id, banks00_07$year),]
# TC = TOC
#
# ER = Z / TA
# Gross total equity to gross total assets ratio.
#
# LA = Y2 / TA
# Total loans and leases to gross total assets ratio.
banks00_07$TA_ave <-
rep(as.vector( by(data = banks00_07$TA,
INDICES = banks00_07$id,
FUN = function(qq) mean(qq))), times = t0)
banks00_07$TA_initial <-
rep(as.vector( by(data = banks00_07$TA,
INDICES = banks00_07$id,
FUN = function(qq) qq[1])), times = t0)
banks00_07$LLP_ave <-
rep(as.vector( by(data = banks00_07$LLP,
INDICES = banks00_07$id,
FUN = function(qq) mean(qq))), times = t0)
banks00_07$LLP_initial <-
rep(as.vector( by(data = banks00_07$LLP,
INDICES = banks00_07$id,
FUN = function(qq) qq[1])), times = t0)
banks00_07$ER_ave <-
rep(as.vector( by(data = banks00_07$ER,
INDICES = banks00_07$id,
FUN = function(qq) mean(qq))), times = t0)
banks00_07$ER_initial <-
rep(as.vector( by(data = banks00_07$ER,
INDICES = banks00_07$id,
FUN = function(qq) qq[1])), times = t0)
banks00_07$LA_ave <-
rep(as.vector( by(data = banks00_07$LA,
INDICES = banks00_07$id,
FUN = function(qq) mean(qq))), times = t0)
banks00_07$LA_initial <-
rep(as.vector( by(data = banks00_07$LA,
INDICES = banks00_07$id,
FUN = function(qq) qq[1])), times = t0)
cols2export <- c("id","year","Ti","TA","TA_ave",
"TA_initial","LLP","LLP_ave",
"LLP_initial","ER_ave","ER_initial","LA_ave","LA_initial")
write.table(x = banks00_07, file = "banks00_07.txt", row.names = FALSE)
## End(Not run)