# Abriendo librerias
library(readxl)
library(sqldf)
## Loading required package: gsubfn
## Loading required package: proto
## Loading required package: RSQLite
library(moments)
library(tseries)
library(forecast)
library(ggplot2)
library(zoo)
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
library(lmtest)
# Asignando opciones al Script
options(digits = 2)
options(OutDec= ",")
#options(OutDec= ",") # restore default value
sep.miles <- function(x){
format(x,big.mark=".")}
fmt.porcen <- function(x){
paste(format(round(x,2),decimal.mark = ","),'%')}
# Descargando la Base de Datos
BBDD <- read_excel("C:/Users/samora/OneDrive/Estudios/universidad/Desarrollo económico/Taller/BBDD.xls",
sheet = "pwt71_wo_country_names_wo_g_var")
DEF <- read_excel("C:/Users/samora/OneDrive/Estudios/universidad/Desarrollo económico/Taller/BBDD.xls",
sheet = "pwt70_vars")
COLDATA <- sqldf("SELECT * FROM BBDD WHERE isocode in ('COL')")
ARGDATA <- sqldf("SELECT * FROM BBDD WHERE isocode in ('ARG')")
BRADATA <- sqldf("SELECT * FROM BBDD WHERE isocode in ('BRA')")
# Sustrayendo inofmración necesaria de la Base de datos, lenguaje usado en SQL
COL <- sqldf("SELECT year, POP, rgdpch, rgdpwok, ki FROM COLDATA WHERE isocode in ('COL')")
sep.miles(COL) # separando valores en miles
## year POP rgdpch rgdpwok ki
## 1 1.950 11.592 2.624 8.157 20
## 2 1.951 11.965 2.583 8.107 19
## 3 1.952 12.351 2.672 8.485 19
## 4 1.953 12.750 2.770 8.885 20
## 5 1.954 13.162 2.912 9.435 23
## 6 1.955 13.588 2.944 9.646 23
## 7 1.956 14.029 2.923 9.674 23
## 8 1.957 14.486 2.854 9.555 20
## 9 1.958 14.958 2.780 9.407 17
## 10 1.959 15.447 2.864 9.803 17
## 11 1.960 15.953 2.938 10.172 19
## 12 1.961 16.476 3.026 10.533 20
## 13 1.962 17.010 3.073 10.752 18
## 14 1.963 17.546 3.075 10.816 16
## 15 1.964 18.090 3.234 11.434 17
## 16 1.965 18.646 3.148 11.189 17
## 17 1.966 19.202 3.249 11.610 17
## 18 1.967 19.764 3.257 11.702 17
## 19 1.968 20.322 3.380 12.209 19
## 20 1.969 20.869 3.512 12.757 18
## 21 1.970 21.430 3.663 13.375 19
## 22 1.971 21.993 3.801 13.764 19
## 23 1.972 22.543 3.936 14.138 17
## 24 1.973 23.069 4.086 14.555 18
## 25 1.974 23.598 4.272 15.094 20
## 26 1.975 24.125 4.211 14.760 16
## 27 1.976 24.638 4.366 15.180 17
## 28 1.977 25.119 4.497 15.514 19
## 29 1.978 25.575 4.783 16.371 18
## 30 1.979 26.072 4.905 16.658 18
## 31 1.980 26.631 5.030 16.949 19
## 32 1.981 27.215 5.090 16.885 20
## 33 1.982 27.826 5.055 16.474 21
## 34 1.983 28.455 4.985 15.996 20
## 35 1.984 29.095 4.990 15.752 19
## 36 1.985 29.748 4.959 15.450 17
## 37 1.986 30.410 5.081 15.609 17
## 38 1.987 31.085 5.223 15.841 17
## 39 1.988 31.771 5.330 15.968 18
## 40 1.989 32.461 5.344 15.787 16
## 41 1.990 33.147 5.410 15.817 15
## 42 1.991 33.832 5.354 15.515 14
## 43 1.992 34.520 5.574 16.071 19
## 44 1.993 35.206 5.797 16.592 23
## 45 1.994 35.888 5.967 16.557 25
## 46 1.995 36.532 6.167 16.566 25
## 47 1.996 37.098 6.097 15.867 22
## 48 1.997 37.620 6.164 15.549 21
## 49 1.998 38.133 6.082 14.878 20
## 50 1.999 38.564 5.673 13.464 13
## 51 2.000 38.910 5.794 13.350 14
## 52 2.001 39.312 5.833 13.056 15
## 53 2.002 39.805 5.901 12.837 16
## 54 2.003 40.351 6.055 12.826 17
## 55 2.004 40.922 6.286 13.632 18
## 56 2.005 41.488 6.491 14.076 20
## 57 2.006 42.046 6.830 15.179 22
## 58 2.007 42.597 7.206 16.119 23
## 59 2.008 43.141 7.356 16.232 24
## 60 2.009 43.677 7.387 15.627 23
## 61 2.010 44.205 7.536 15.761 25
ARG <- sqldf("SELECT year, POP, rgdpch, rgdpwok, ki FROM ARGDATA WHERE isocode in ('ARG')")
sep.miles(ARG) # separando valores en miles
## year POP rgdpch rgdpwok ki
## 1 1.950 17.150 5.258 12.120 16
## 2 1.951 17.517 5.464 12.657 22
## 3 1.952 17.877 5.021 11.692 20
## 4 1.953 18.231 5.152 12.060 20
## 5 1.954 18.581 5.231 12.308 19
## 6 1.955 18.928 5.520 13.052 20
## 7 1.956 19.272 5.516 13.113 18
## 8 1.957 19.611 5.675 13.564 19
## 9 1.958 19.947 5.969 14.339 19
## 10 1.959 20.281 5.549 13.403 19
## 11 1.960 20.616 6.043 14.673 25
## 12 1.961 20.951 6.164 14.980 26
## 13 1.962 21.284 6.111 14.866 24
## 14 1.963 21.616 5.783 14.081 20
## 15 1.964 21.949 6.171 15.040 24
## 16 1.965 22.283 6.692 16.324 23
## 17 1.966 22.612 6.607 16.133 22
## 18 1.967 22.934 6.709 16.397 22
## 19 1.968 23.261 6.928 16.949 23
## 20 1.969 23.600 7.485 18.328 26
## 21 1.970 23.962 7.617 18.669 25
## 22 1.971 24.364 7.825 19.224 27
## 23 1.972 24.780 7.824 19.269 27
## 24 1.973 25.210 7.933 19.585 25
## 25 1.974 25.646 8.206 20.308 24
## 26 1.975 26.082 8.043 19.951 24
## 27 1.976 26.531 7.936 19.735 26
## 28 1.977 26.984 8.396 20.929 29
## 29 1.978 27.440 7.926 19.805 25
## 30 1.979 27.902 8.401 21.043 26
## 31 1.980 28.370 8.496 21.333 28
## 32 1.981 28.848 7.877 19.690 24
## 33 1.982 29.330 7.601 18.935 21
## 34 1.983 29.794 7.769 19.408 20
## 35 1.984 30.231 7.647 19.119 17
## 36 1.985 30.672 6.997 17.354 15
## 37 1.986 31.145 7.611 19.011 18
## 38 1.987 31.625 7.693 19.246 21
## 39 1.988 32.099 7.539 18.786 21
## 40 1.989 32.572 6.901 17.028 18
## 41 1.990 33.036 6.928 16.995 16
## 42 1.991 33.504 7.410 18.268 17
## 43 1.992 33.967 7.835 19.362 19
## 44 1.993 34.407 8.161 20.101 21
## 45 1.994 34.847 8.509 20.893 22
## 46 1.995 35.274 8.323 20.207 20
## 47 1.996 35.683 8.642 20.939 21
## 48 1.997 36.102 9.156 22.152 23
## 49 1.998 36.518 9.413 22.705 23
## 50 1.999 36.923 9.062 21.790 20
## 51 2.000 37.336 8.909 21.344 19
## 52 2.001 37.694 8.556 20.347 17
## 53 2.002 37.999 7.916 18.677 12
## 54 2.003 38.337 8.446 19.769 15
## 55 2.004 38.742 8.977 19.705 18
## 56 2.005 39.181 9.671 21.100 19
## 57 2.006 39.614 10.322 22.425 21
## 58 2.007 40.049 11.003 23.922 22
## 59 2.008 40.482 11.483 25.031 24
## 60 2.009 40.914 11.593 25.300 22
## 61 2.010 41.343 12.340 27.149 24
BRA <- sqldf("SELECT year, POP, rgdpch, rgdpwok, ki FROM BRADATA WHERE isocode in ('BRA')")
sep.miles(BRA) # separando valores en miles
## year POP rgdpch rgdpwok ki
## 1 1.950 53.443 1.710 4.927 25
## 2 1.951 54.996 1.749 5.061 29
## 3 1.952 56.603 1.866 5.424 30
## 4 1.953 58.266 1.876 5.473 23
## 5 1.954 59.989 1.987 5.818 25
## 6 1.955 61.774 2.051 6.029 24
## 7 1.956 63.632 2.052 6.060 22
## 8 1.957 65.551 2.211 6.553 26
## 9 1.958 67.533 2.277 6.773 25
## 10 1.959 69.580 2.392 7.144 28
## 11 1.960 71.695 2.483 7.448 25
## 12 1.961 73.833 2.752 8.228 24
## 13 1.962 76.039 2.813 8.383 24
## 14 1.963 78.317 2.894 8.597 20
## 15 1.964 80.667 2.936 8.693 21
## 16 1.965 83.093 3.062 9.038 22
## 17 1.966 85.557 3.093 9.100 22
## 18 1.967 88.050 3.166 9.284 20
## 19 1.968 90.569 3.432 10.032 21
## 20 1.969 93.114 3.581 10.436 28
## 21 1.970 95.684 3.853 11.194 25
## 22 1.971 98.265 4.216 12.121 26
## 23 1.972 100.874 4.607 13.105 27
## 24 1.973 103.513 5.114 14.397 28
## 25 1.974 106.182 5.433 15.139 30
## 26 1.975 108.879 5.536 15.270 31
## 27 1.976 111.603 6.023 16.449 30
## 28 1.977 114.373 6.101 16.495 28
## 29 1.978 117.207 6.251 16.736 28
## 30 1.979 120.101 6.549 17.364 27
## 31 1.980 123.020 6.960 18.275 29
## 32 1.981 125.992 6.385 16.529 27
## 33 1.982 129.028 6.302 16.178 25
## 34 1.983 131.960 5.914 14.993 21
## 35 1.984 134.699 5.999 15.137 21
## 36 1.985 137.382 6.143 15.446 22
## 37 1.986 140.196 6.758 16.868 24
## 38 1.987 143.027 6.765 16.495 23
## 39 1.988 145.873 6.548 15.883 22
## 40 1.989 148.659 6.474 15.612 19
## 41 1.990 151.170 6.145 14.673 18
## 42 1.991 153.584 6.107 13.977 20
## 43 1.992 156.032 5.996 13.161 18
## 44 1.993 158.512 6.109 13.331 19
## 45 1.994 161.017 6.369 13.757 20
## 46 1.995 163.544 6.646 14.208 23
## 47 1.996 166.086 6.694 14.627 23
## 48 1.997 168.639 6.830 14.639 25
## 49 1.998 171.201 6.719 14.279 24
## 50 1.999 173.764 6.631 13.836 21
## 51 2.000 176.320 6.839 14.250 22
## 52 2.001 178.870 6.822 14.205 21
## 53 2.002 181.418 6.856 14.008 19
## 54 2.003 183.960 6.818 13.855 18
## 55 2.004 186.489 7.118 14.224 19
## 56 2.005 188.993 7.234 14.236 18
## 57 2.006 191.469 7.432 14.611 19
## 58 2.007 193.919 7.791 15.321 21
## 59 2.008 196.343 8.088 15.771 23
## 60 2.009 198.739 7.977 15.421 20
## 61 2.010 201.103 8.324 15.975 23
# Valores faltantes en el Data COL
COL$Y <- c(COL$POP * COL$rgdpwok)
COL$Inversión <- c(COL$Y * COL$ki)
lim <- NROW(COL$ki)
COL$mean.ki <- mean(COL$ki[2:lim])
COL$K <- c(c(COL$mean.ki * COL$Y * 0.01) / 0.1)
COL$PIBperCapita <- c(COL$Y / COL$POP)
COL$L <- c(COL$Y / c(COL$rgdpch * COL$rgdpwok))
COL$A <- c(COL$Y / c((COL$K ^ 0.36) * c(COL$L ^ c(1 - 0.36))))
# Valores faltantes en el Data ARG
ARG$Y <- c(ARG$POP * ARG$rgdpwok)
ARG$Inversión <- c(ARG$Y * ARG$ki)
lim <- NROW(ARG$ki)
ARG$mean.ki <- mean(ARG$ki[2:lim])
ARG$K <- c(c(ARG$mean.ki * ARG$Y * 0.01) / 0.1)
ARG$PIBperCapita <- c(ARG$Y / ARG$POP)
ARG$L <- c(ARG$Y / c(ARG$rgdpch * ARG$rgdpwok))
ARG$A <- c(ARG$Y / c((ARG$K ^ 0.36) * c(ARG$L ^ c(1 - 0.36))))
# Valores faltantes en el Data BRA
BRA$Y <- c(BRA$POP * BRA$rgdpwok)
BRA$Inversión <- c(BRA$Y * BRA$ki)
lim <- NROW(BRA$ki)
BRA$mean.ki <- mean(BRA$ki[2:lim])
BRA$K <- c(c(BRA$mean.ki * BRA$Y * 0.01) / 0.1)
BRA$PIBperCapita <- c(BRA$Y / BRA$POP)
BRA$L <- c(BRA$Y / c(BRA$rgdpch * BRA$rgdpwok))
BRA$A <- c(BRA$Y / c((BRA$K ^ 0.36) * c(BRA$L ^ c(1 - 0.36))))
#COMPARANDO VARIABLES ENTRE PAISES
Y.PLOT <- ggplot(data = COL,
aes(x=COL$year, y=COL$Y, colour="PIB de COL")
)+geom_point()+geom_point(
data = ARG, aes(x=ARG$year, y=ARG$Y, colour="PIB de ARG")
)+geom_point(
data = BRA, aes(x=BRA$year, y=BRA$Y, colour="PIB de BRA")
)+ggtitle("Comparación de PIB de Colombia contra Argentina y Brazil"
)+xlab("Year")+ylab("PIB")
Y.PLOT
Inversión.PLOT <- ggplot(data = COL,
aes(x=COL$year, y=COL$Inversión, colour="PIB de COL")
)+geom_point()+geom_point(
data = ARG, aes(x=ARG$year, y=ARG$Inversión, colour="PIB de ARG")
)+geom_point(
data = BRA, aes(x=BRA$year, y=BRA$Inversión, colour="PIB de BRA")
)+ggtitle("Comparación de Inversion de Colombia contra Argentina y Brazil"
)+xlab("year")+ylab("Inversión")
Inversión.PLOT
L.PLOT <- ggplot(data = COL,
aes(x=COL$year, y=COL$L, colour="PIB de COL")
)+geom_point()+geom_point(
data = ARG, aes(x=ARG$year, y=ARG$L, colour="PIB de ARG")
)+geom_point(
data = BRA, aes(x=BRA$year, y=BRA$L, colour="PIB de BRA")
)+ggtitle("Comparación de L de Colombia contra Argentina y Brazil"
)+xlab("Year")+ylab("L")
L.PLOT
K.PLOT <- ggplot(data = COL,
aes(x=COL$year, y=COL$K, colour="PIB de COL")
)+geom_point()+geom_point(
data = ARG, aes(x=ARG$year, y=ARG$K, colour="PIB de ARG")
)+geom_point(
data = BRA, aes(x=BRA$year, y=BRA$K, colour="PIB de BRA")
)+ggtitle("Comparación de K de Colombia contra Argentina y Brazil"
)+xlab("Year")+ylab("K")
K.PLOT
# Comparando Ciclos de inversión y K entre Brazil y Colombia
PrimeraDiff.col <- diff(COL$Inversión, 2)
PrimeraDiff.arg <- diff(ARG$Inversión, 2)
PrimeraDiff.bra <- diff(BRA$Inversión, 2)
PrimeraDiffK.col <- diff(COL$K, 2)
PrimeraDiffK.arg <- diff(ARG$K, 2)
PrimeraDiffK.bra <- diff(BRA$K, 2)
trend <- c(1:59)
Differencies.col <- data.frame(PrimeraDiff.col, trend)
Differencies.arg <- data.frame(PrimeraDiff.arg, trend)
Differencies.bra <- data.frame(PrimeraDiff.bra, trend)
DifferenciesK.col <- data.frame(PrimeraDiffK.col, trend)
DifferenciesK.arg <- data.frame(PrimeraDiffK.arg, trend)
DifferenciesK.bra <- data.frame(PrimeraDiffK.bra, trend)
Inversión.PLOT.diff <- ggplot(data = Differencies.col,
aes(x=Differencies.col$trend,
y=Differencies.col$PrimeraDiff.col, colour="PIB de COL")
)+geom_line()+geom_line(
data = Differencies.arg,
aes(x=Differencies.arg$trend,
y=Differencies.arg$PrimeraDiff.arg, colour="PIB de ARG")
)+geom_line(
data = Differencies.bra, aes(x=Differencies.bra$trend, y=Differencies.bra$PrimeraDiff.bra, colour="PIB de BRA")
)+ggtitle("Primeras diferencias Inversion de Colombia contra Argentina y Brazil"
)+xlab("year")+ylab("Inversión")
Inversión.PLOT.diff
K.PLOT.diff <- ggplot(data = DifferenciesK.col,
aes(x=DifferenciesK.col$trend,
y=DifferenciesK.col$PrimeraDiffK.col, colour="PIB de COL")
)+geom_line()+geom_line(
data = DifferenciesK.arg,
aes(x=DifferenciesK.arg$trend,
y=DifferenciesK.arg$PrimeraDiffK.arg, colour="PIB de ARG")
)+geom_line(
data = DifferenciesK.bra, aes(x=DifferenciesK.bra$trend, y=DifferenciesK.bra$PrimeraDiffK.bra, colour="PIB de BRA")
)+ggtitle("Primeras diferencias K de Colombia contra Argentina y Brazil"
)+xlab("year")+ylab("K")
K.PLOT.diff
# Crendo metodo para hacer vectores
Vectores <- function(x,y){
X <- data.frame(x, check.names = TRUE)
names(X)[1] <- y
return(X)
}
# Asignando nombres a los vectores
POP <- Vectores(COL$POP,"POP")
rgdpch <- Vectores(COL$rgdpch, "rgdpch")
rgdpwok <- Vectores(COL$rgdpwok, "rgdpwok")
ki <- Vectores(COL$ki, "ki")
year <- Vectores(COL$year, "Year")
Y <- Vectores(COL$Y, "Y")
Inversion <- Vectores(COL$Inversión, "Inversión")
K <- Vectores(COL$K, "K")
PIBprCapita <- Vectores(COL$PIBperCapita, "Pib per Capita")
L <- Vectores(COL$L, "L")
A <- Vectores(COL$A, "A")
#Analsis descreiptivo por variable, creando un metodo
Descriptivo <- function(x){
numeroFilas <- NROW(x)
X <- x[2:numeroFilas,]
as.numeric(X)
library(moments)
medianx <- median(X)
meanx <- mean(X)
sdx <- sd(X)
kurtosisx <- kurtosis(X)
skewnessx <- skewness(X)
minx <- min(X)
maxx <- max(X)
#quantilex <- quantile(x)
Descriptivox <- data.frame(medianx,
meanx,
sdx,
kurtosisx,
skewnessx,
minx,maxx)
return(Descriptivox)
}
# Aplicando metodo a variables
POP.Descriptivo <- Descriptivo(POP)
rgdpch.Descriptivo <- Descriptivo(rgdpch)
rgdpwok.Descriptivo <- Descriptivo(rgdpwok)
ki.Descriptivo <- Descriptivo(ki)
Y.Descriptivo <- Descriptivo(Y)
Inversion.Descriptivo <- Descriptivo(Inversion)
K.Descriptivo <- Descriptivo(K)
PIBprCapita.Descriptivo <- Descriptivo(PIBprCapita)
L.Descriptivo <- Descriptivo(L)
A.Descriptivo <- Descriptivo(A)
#Creando matriz con análisis descriptivo
matrix.desciptivo <- rbind(sep.miles(POP.Descriptivo),
sep.miles(rgdpch.Descriptivo),
sep.miles(rgdpwok.Descriptivo),
sep.miles(ki.Descriptivo),
format(Y.Descriptivo, scientific=FALSE, big.mark="."),
format(Inversion.Descriptivo, scientific=FALSE, big.mark="."),
format(K.Descriptivo, scientific=FALSE, big.mark="."),
sep.miles(PIBprCapita.Descriptivo),
sep.miles(L.Descriptivo),
sep.miles(A.Descriptivo))
variables <- c("POP", "rgdpch", "rgdpwok", "ki",
"Y", "Inversion", "K", "PIB per Capita", "L", "A")
row.names(matrix.desciptivo) <- variables
matrix.desciptivo
## medianx meanx sdx kurtosisx
## POP 26.923 27.608 9.895 1,7
## rgdpch 4.972 4.696 1.419 1,9
## rgdpwok 14.657 13.698 2.611 2
## ki 19 19 2,8 2,7
## Y 453.267.876 396.435.735 181.177.128 1,8
## Inversion 7.474.394.020 7.622.098.473 4.158.897.811 2,6
## K 859.734.929 751.938.681 343.647.351 1,8
## PIB per Capita 14.657 13.698 2.611 2
## L 5,9 5,8 0,54 3,2
## A 88.196 79.265 22.945 1,8
## skewnessx minx maxx
## POP 0,062 11.965 44.205
## rgdpch 0,14 2.583 7.536
## rgdpwok -0,62 8.107 16.949
## ki 0,38 13 25
## Y -0,18 97.005.027 700.272.290
## Inversion 0,63 1.815.566.547 17.424.074.687
## K -0,18 183.994.090 1.328.240.052
## PIB per Capita -0,62 8.107 16.949
## L -0,45 4,5 6,8
## A -0,3 38.488 117.271
# Aplicando descriptivo por Cuantiles
summary(COL)
## year POP rgdpch rgdpwok
## Min. :1950 Min. :11592 Min. :2583 Min. : 8107
## 1st Qu.:1965 1st Qu.:18646 1st Qu.:3234 1st Qu.:11434
## Median :1980 Median :26631 Median :4959 Median :14555
## Mean :1980 Mean :27345 Mean :4662 Mean :13607
## 3rd Qu.:1995 3rd Qu.:36532 3rd Qu.:5797 3rd Qu.:15817
## Max. :2010 Max. :44205 Max. :7536 Max. :16949
## ki Y Inversión mean.ki
## Min. :12,9 Min. :9,46e+07 Min. :1,82e+09 Min. :19
## 1st Qu.:17,2 1st Qu.:2,09e+08 1st Qu.:3,55e+09 1st Qu.:19
## Median :18,6 Median :4,51e+08 Median :7,34e+09 Median :19
## Mean :19,0 Mean :3,91e+08 Mean :7,53e+09 Mean :19
## 3rd Qu.:20,3 3rd Qu.:5,24e+08 3rd Qu.:9,34e+09 3rd Qu.:19
## Max. :25,0 Max. :7,00e+08 Max. :1,74e+10 Max. :19
## K PIBperCapita L A
## Min. :1,79e+08 Min. : 8107 Min. :4,4 Min. : 38488
## 1st Qu.:3,96e+08 1st Qu.:11434 1st Qu.:5,4 1st Qu.: 55382
## Median :8,56e+08 Median :14555 Median :5,9 Median : 88107
## Mean :7,43e+08 Mean :13607 Mean :5,8 Mean : 78606
## 3rd Qu.:9,94e+08 3rd Qu.:15817 3rd Qu.:6,1 3rd Qu.: 94758
## Max. :1,33e+09 Max. :16949 Max. :6,8 Max. :117271
# Creando Metodo para graficar Serie de Tiempo
grafico <- function(X){
tittle <- paste("variable", names(X))
color <- paste("",names(X),"")
plot.X <- ggplot(data = COL,
aes(y = X,
x = year,
colour=color))+geom_line(
)+geom_point(
)+ggtitle(
tittle
)+xlab(
"Year"
)+ylab(
color)
return(plot.X)
}
# Grafico de Serie de tiempo
POP.grafico <- grafico(POP)
POP.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
rgdpch.grafico <- grafico(rgdpch)
rgdpch.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
rgdpwok.grafico <- grafico(rgdpwok)
rgdpwok.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
ki.grafico <- grafico(ki)
ki.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
Y.grafico <- grafico(Y)
Y.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
Inversion.grafico <- grafico(Inversion)
Inversion.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
K.grafico <- grafico(K)
K.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
PIBprCapita.grafico <- grafico(PIBprCapita)
PIBprCapita.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
L.grafico <- grafico(L)
L.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
A.grafico <- grafico(A)
A.grafico
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
# Creando Metodo para graficar Histograma
histograma <- function(x){
tittle <- paste("variable", names(x))
color <- paste("",names(x),"")
plot.histo <- ggplot(data = COL,
aes(x),
colour=color
)+geom_freqpoly(
binwidth = 500
)+geom_histogram(
binwidth = 500
)+scale_y_sqrt(
)+ggtitle(
tittle
)+xlab(
"Year"
)+ylab(
color)
#Plot.histox <- hist(x[2:61,])
return(plot.histo)
}
# Finalmente el loop es
# for(var in seq_along(variables.list)) {
# # Graficando Histogramas
# POP$Type <- c("POP")
# names(POP)[1] <- "Variable"
# rgdpch$Type <- c("rgdpch")
# names(rgdpch)[1] <- "Variable"
# rgdpwok$Type <- c("rgdpwok")
# names(rgdpwok)[1] <- "Variable"
# ki$Type <- c("ki")
# names(ki)[1] <- "Variable"
# COLvar <- as.data.frame(rbind(POP, rgdpch, rgdpwok, ki))
# variables.list <- unique(COLvar$Type)
#
# C = 1 # Contadora dentro del loop
# var <- variables.list[C]
# histo <- subset(COLvar, Type == var)
# histogr <- histograma(histo$Variable)
# print(histogr)
# C = C + 1
#}
# Formateando valores grandes
Y <- format(Y, scientific=FALSE, big.mark=".")
K <- format(K, scientific=FALSE, big.mark=".")
Inversion <- format(Inversion, scientific=FALSE, big.mark=".")
POP.histograma <- histograma(POP)
rgdpch.histograma <- histograma(rgdpch)
rgdpwok.histograma <- histograma(rgdpwok)
ki.histograma <- histograma(ki)
Y.histograma <- histograma(Y)
Inversion.histograma <- histograma(Inversion)
K.histograma <- histograma(K)
PIBprCapita.histograma <- histograma(PIBprCapita)
L.histograma <- histograma(L)
A.histograma <- histograma(A)
# Creando metodo para graficar relaciones individuales
relacion <- function(X,Y){
tittle <- paste("Relación entre ", names(X), "-",names(Y))
colorUno <- paste("",names(X),"")
colorDos <- paste("",names(Y),"")
color <- paste(names(X),"-",names(Y))
Relacion <- ggplot(data = COL,
aes(y = X,
x = Y,
colour=color))+geom_point(
)+ggtitle(
tittle
)+xlab(
colorDos
)+ylab(
colorUno)
return(Relacion)
}
# Relaciones Globales
pairs(COL)
cov(COL)
## year POP rgdpch rgdpwok ki Y Inversión
## year 3,2e+02 1,8e+05 2,5e+04 3,6e+04 5,2e+00 3,2e+09 6,6e+10
## POP 1,8e+05 1,0e+08 1,4e+07 2,0e+07 3,2e+03 1,8e+12 3,7e+13
## rgdpch 2,5e+04 1,4e+07 2,1e+06 3,0e+06 9,5e+02 2,6e+11 5,7e+12
## rgdpwok 3,6e+04 2,0e+07 3,0e+06 7,2e+06 9,3e+02 4,2e+11 8,9e+12
## ki 5,2e+00 3,2e+03 9,5e+02 9,3e+02 7,8e+00 9,8e+07 5,8e+09
## Y 3,2e+09 1,8e+12 2,6e+11 4,2e+11 9,8e+07 3,4e+16 7,2e+17
## Inversión 6,6e+10 3,7e+13 5,7e+12 8,9e+12 5,8e+09 7,2e+17 1,8e+19
## mean.ki 0,0e+00 0,0e+00 0,0e+00 0,0e+00 0,0e+00 0,0e+00 0,0e+00
## K 6,0e+09 3,4e+12 4,9e+11 8,0e+11 1,9e+08 6,4e+16 1,4e+18
## PIBperCapita 3,6e+04 2,0e+07 3,0e+06 7,2e+06 9,3e+02 4,2e+11 8,9e+12
## L 7,9e+00 4,4e+03 5,4e+02 8,0e+02 -5,5e-01 7,3e+07 1,2e+09
## A 3,9e+05 2,2e+08 3,2e+07 5,7e+07 1,4e+04 4,2e+12 9,2e+13
## mean.ki K PIBperCapita L A
## year 0 6,0e+09 3,6e+04 7,9e+00 3,9e+05
## POP 0 3,4e+12 2,0e+07 4,4e+03 2,2e+08
## rgdpch 0 4,9e+11 3,0e+06 5,4e+02 3,2e+07
## rgdpwok 0 8,0e+11 7,2e+06 8,0e+02 5,7e+07
## ki 0 1,9e+08 9,3e+02 -5,5e-01 1,4e+04
## Y 0 6,4e+16 4,2e+11 7,3e+07 4,2e+12
## Inversión 0 1,4e+18 8,9e+12 1,2e+09 9,2e+13
## mean.ki 0 0,0e+00 0,0e+00 0,0e+00 0,0e+00
## K 0 1,2e+17 8,0e+11 1,4e+08 8,0e+12
## PIBperCapita 0 8,0e+11 7,2e+06 8,0e+02 5,7e+07
## L 0 1,4e+08 8,0e+02 3,2e-01 8,3e+03
## A 0 8,0e+12 5,7e+07 8,3e+03 5,4e+08
cor(COL)
## Warning in cor(COL): the standard deviation is zero
## year POP rgdpch rgdpwok ki Y Inversión mean.ki K
## year 1,00 1,00 0,98 0,75 0,10 0,98 0,89 NA 0,98
## POP 1,00 1,00 0,98 0,73 0,12 0,97 0,89 NA 0,97
## rgdpch 0,98 0,98 1,00 0,78 0,24 0,99 0,94 NA 0,99
## rgdpwok 0,75 0,73 0,78 1,00 0,12 0,86 0,79 NA 0,86
## ki 0,10 0,12 0,24 0,12 1,00 0,19 0,49 NA 0,19
## Y 0,98 0,97 0,99 0,86 0,19 1,00 0,94 NA 1,00
## Inversión 0,89 0,89 0,94 0,79 0,49 0,94 1,00 NA 0,94
## mean.ki NA NA NA NA NA NA NA 1 NA
## K 0,98 0,97 0,99 0,86 0,19 1,00 0,94 NA 1,00
## PIBperCapita 0,75 0,73 0,78 1,00 0,12 0,86 0,79 NA 0,86
## L 0,79 0,78 0,67 0,52 -0,35 0,70 0,51 NA 0,70
## A 0,94 0,93 0,97 0,91 0,22 0,99 0,94 NA 0,99
## PIBperCapita L A
## year 0,75 0,79 0,94
## POP 0,73 0,78 0,93
## rgdpch 0,78 0,67 0,97
## rgdpwok 1,00 0,52 0,91
## ki 0,12 -0,35 0,22
## Y 0,86 0,70 0,99
## Inversión 0,79 0,51 0,94
## mean.ki NA NA NA
## K 0,86 0,70 0,99
## PIBperCapita 1,00 0,52 0,91
## L 0,52 1,00 0,63
## A 0,91 0,63 1,00
subCOL <- sqldf("SELECT Y,Inversión,K,PIBperCapita,L,A FROM COL")
pairs(subCOL)
cov(subCOL)
## Y Inversión K PIBperCapita L A
## Y 3,4e+16 7,2e+17 6,4e+16 4,2e+11 7,3e+07 4,2e+12
## Inversión 7,2e+17 1,8e+19 1,4e+18 8,9e+12 1,2e+09 9,2e+13
## K 6,4e+16 1,4e+18 1,2e+17 8,0e+11 1,4e+08 8,0e+12
## PIBperCapita 4,2e+11 8,9e+12 8,0e+11 7,2e+06 8,0e+02 5,7e+07
## L 7,3e+07 1,2e+09 1,4e+08 8,0e+02 3,2e-01 8,3e+03
## A 4,2e+12 9,2e+13 8,0e+12 5,7e+07 8,3e+03 5,4e+08
cor(subCOL)
## Y Inversión K PIBperCapita L A
## Y 1,00 0,94 1,00 0,86 0,70 0,99
## Inversión 0,94 1,00 0,94 0,79 0,51 0,94
## K 1,00 0,94 1,00 0,86 0,70 0,99
## PIBperCapita 0,86 0,79 0,86 1,00 0,52 0,91
## L 0,70 0,51 0,70 0,52 1,00 0,63
## A 0,99 0,94 0,99 0,91 0,63 1,00
# Aplicando relaciones a POP
relacion(POP,rgdpch)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(POP,rgdpwok)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(POP,ki)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
#Aplicandorelacionesargdpch
relacion(rgdpch,POP)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(rgdpch,rgdpwok)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(rgdpch,ki)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
#Aplicandorelacionesargdwok
relacion(rgdpwok,POP)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(rgdpwok,rgdpch)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(rgdpwok,ki)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
#Aplicandorelacionesaki
relacion(ki,POP)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(ki,rgdpch)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
relacion(ki,rgdpwok)
## Don't know how to automatically pick scale for object of type data.frame. Defaulting to continuous.
# Haciendo regresión
model <- lm(COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita + COL$L + COL$A)
summary(model)
## Warning in summary.lm(model): essentially perfect fit: summary may be
## unreliable
##
## Call:
## lm(formula = COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita +
## COL$L + COL$A)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4,56e-07 -2,39e-08 1,00e-10 2,23e-08 5,97e-07
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4,65e-07 5,58e-07 8,30e-01 0,408
## COL$Inversión -2,94e-17 1,30e-17 -2,26e+00 0,028 *
## COL$K 5,27e-01 9,95e-16 5,30e+14 <2e-16 ***
## COL$PIBperCapita -3,30e-12 3,59e-11 -9,00e-02 0,927
## COL$L -3,54e-08 7,36e-08 -4,80e-01 0,633
## COL$A -5,20e-12 1,72e-11 -3,00e-01 0,764
## ---
## Signif. codes: 0 '***' 0,001 '**' 0,01 '*' 0,05 '.' 0,1 ' ' 1
##
## Residual standard error: 1,1e-07 on 55 degrees of freedom
## Multiple R-squared: 1, Adjusted R-squared: 1
## F-statistic: 3,37e+31 on 5 and 55 DF, p-value: <2e-16
hist(model$residuals)
#Aplicando test el LM
Durbin.Watson <- dwtest(COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita + COL$L + COL$A)
Durbin.Watson
##
## Durbin-Watson test
##
## data: COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita + COL$L + COL$A
## DW = 3, p-value = 0,9
## alternative hypothesis: true autocorrelation is greater than 0
Breusch.Godfrey <- bgtest(COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita + COL$L + COL$A)
Breusch.Godfrey
##
## Breusch-Godfrey test for serial correlation of order up to 1
##
## data: COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita + COL$L + COL$A
## LM test = 10, df = 1, p-value = 8e-04
Breusch.Pagan <- bptest(COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita + COL$L + COL$A)
Breusch.Pagan
##
## studentized Breusch-Pagan test
##
## data: COL$Y ~ COL$Inversión + COL$K + COL$PIBperCapita + COL$L + COL$A
## BP = 20, df = 5, p-value = 0,002
# Haciendo regresión LOG10
model.lo10 <- lm(log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) + log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A))
summary(model.lo10)
## Warning in summary.lm(model.lo10): essentially perfect fit: summary may be
## unreliable
##
## Call:
## lm(formula = log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) +
## log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3,16e-14 -8,70e-16 3,10e-16 1,12e-15 6,33e-15
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2,78e-01 3,05e-14 -9,10e+12 <2e-16 ***
## log10(COL$Inversión) 1,26e-14 1,29e-14 9,70e-01 0,334
## log10(COL$K) 1,00e+00 2,03e-14 4,92e+13 <2e-16 ***
## log10(COL$PIBperCapita) 3,32e-14 2,10e-14 1,58e+00 0,120
## log10(COL$L) 7,23e-14 3,35e-14 2,16e+00 0,035 *
## log10(COL$A) NA NA NA NA
## ---
## Signif. codes: 0 '***' 0,001 '**' 0,01 '*' 0,05 '.' 0,1 ' ' 1
##
## Residual standard error: 4,7e-15 on 56 degrees of freedom
## Multiple R-squared: 1, Adjusted R-squared: 1
## F-statistic: 4,41e+28 on 4 and 56 DF, p-value: <2e-16
hist(model$residuals)
#Aplicando test el LM
Durbin.Watson <- dwtest(log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) + log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A))
## Warning in dwtest(log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) +
## log10(COL$PIBperCapita) + : imaginary parts of eigenvalues discarded
Durbin.Watson
##
## Durbin-Watson test
##
## data: log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) + log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A)
## DW = 1, p-value = 2e-10
## alternative hypothesis: true autocorrelation is greater than 0
Breusch.Godfrey <- bgtest(log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) + log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A))
Breusch.Godfrey
##
## Breusch-Godfrey test for serial correlation of order up to 1
##
## data: log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) + log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A)
## LM test = 5e-04, df = 1, p-value = 1
Breusch.Pagan <- bptest(log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) + log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A))
Breusch.Pagan
##
## studentized Breusch-Pagan test
##
## data: log10(COL$Y) ~ log10(COL$Inversión) + log10(COL$K) + log10(COL$PIBperCapita) + log10(COL$L) + log10(COL$A)
## BP = 10, df = 4, p-value = 0,01