dmarcelinobr

UnTag <- function(x){  gsub("<[^>]*>", " ", x)  }

dmarcelinobr

 if(!require('SciencePo')) install.packages('SciencePo')
data(griliches76, package="SciencePo")
detail(griliches76)

summary(lm(lw~s+age, data=griliches76))

dmarcelinobr

Call:
lm(formula = lw ~ s + iq, data = griliches76)

Residuals:
    Min      1Q  Median      3Q     Max 
-1.2817 -0.2436  0.0009  0.2424  1.1050 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)
(Intercept)  4.15573    0.10810   38.44  < 2e-16

dmarcelinobr

myboot<-function(data, stat, nreps, hist = TRUE) {
# Where 'data' is the original data set to be paste into 'myboot' program.
# 'stat' is the function that will generate the desired statistic such as "standard errors", "confidence intervals" etc.  
# 'nreps' is the number of repetitions we want in the simulation.
estimates<-get(stat)(data)# Compute the number of estimates needed:
len<-length(estimates) 
# Make a container object matrix for store the bootstrap results:
container<-matrix(NA, ncol = len , nrow = nreps) 
# The length of "estimates" is the number of coefficients we will estimate standard errors for.
nobs<-nrow(data)#Compute the number of observations to resample

dmarcelinobr

mod1 <- function(griliches76)lm(lw~s+iq, data=griliches76)[[1]]

mod1.sds <- myboot(griliches76, "mod1", 10000, hist=TRUE)

         (Intercept)      s       iq
estimates      4.1557 0.084696 0.003810
sds            0.1123 0.007351 0.001159

dmarcelinobr

# rm(list = ls())  # clear objects
# graphics.off()   # close graphics windows
 plot.new() # call new plot window 
x = seq(-5,5, length=250)
y = dnorm(x)
plot(x,y, las=1, ylab='dnorm', type='n', yaxs='i', ylim=c(0, 0.5))
x2 = seq(qnorm(0.95), 5, length=50)
y2 = dnorm(x2)
polygon(c(x2[1], x2, x2[length(x2)]),  c(0, y2, 0), border=NA, col='grey')
lines(x, y)

dmarcelinobr

myboot<-function(data, stat, nreps, hist = TRUE) {
estimates<-get(stat)(data)
len<-length(estimates) 
container<-matrix(NA, ncol = len , nrow = nreps) 
nobs<-nrow(data)
for(i in 1:nreps) { 
posdraws<-ceiling(runif(nobs)*nobs)
resample<-data[posdraws,] 
container[i,]<-get(stat)(resample)
}

dmarcelinobr

path = "~/Documents/My Data/BRAZIL/Elections/"
out.file<-""
file.names <- dir(path, pattern =".txt")
for(i in 1:length(file.names)){
  file <- read.table(file.names[i],header=TRUE, sep=";", stringsAsFactors=FALSE)
  out.file <- rbind(out.file, file)
}
 write.table(out.file, file = "cand_Brazil.txt",sep=";", 
             row.names = FALSE, qmethod = "double",fileEncoding="windows-1252")
             

dmarcelinobr

. timer on 1
. import delimited "/Users/dmarcelino/Documents/My Data/BRAZIL/Eleicoes_new/cand_Brazil.txt", delimite r(";") varnames(1) case(preserve) 
(39 vars, 1248456 obs)
. timer off 1
. timer list 1
   1:    134.37 /        1 =     134.3660

dmarcelinobr

R> system.time(cand_Brazil<-read.csv2(file="cand_Brazil.txt", header=TRUE))
   user  system elapsed 
 98.540   1.752 102.490