Portada
UNIVERSIDAD DE EL SALVADOR FACULTAD DE CIENCIAS ECONÓMICAS ESCUELA DE ECONOMÍA MÉTODOS PARA EL ANÁLISIS ECONÓMICO CICLO II-2024 GT02
TEMA A INVESTIGAR: “Importación y exportación de datos en R studio”
INTEGRANTES:
| Nombre | Cárne |
|---|---|
| Edwin Fabricio Aguirre Sarmiento | AS19011 |
| Gabriel Arturo Sánchez Henríquez | SH22002 |
| Diego Edgardo Siliezar Madrid | SM21024 |
DOCENTE: Carlos Ademir Pérez Alas
Ciudad Universitaria, San Salvador, 9 de diciembre del 2024.
Preparación de los datos
library(readxl)
library (kableExtra)
# Carga de los datos
PIB_trimestral <- read_excel("C:/Users/SANCHEZ/Desktop/GABRIEL2021/Universidad/Ciclo VI/Metodos para el analisis economico/datos_PIB_trim_CA.xlsx", skip=5)
# Se nombran las columnas
names(PIB_trimestral)[1] <- "Fechas"
names(PIB_trimestral)[2] <- "Costa Rica"
names(PIB_trimestral)[3] <- "El Salvador"
names(PIB_trimestral)[4] <- "Guatemala"
names(PIB_trimestral)[5] <- "Honduras"
names(PIB_trimestral)[6] <- "Nicaragua"
names(PIB_trimestral)[7] <- "República Dominicana"
names(PIB_trimestral)[8] <- "Panamá"
kable(head(PIB_trimestral, 10), align = "c") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = F,
position = "center") %>%
row_spec(0, bold = T, background = "#D3D3D3")%>%
footnote(general = "Elaborado con datos del Consejo Monetario Centroamericano",
general_title = "Nota: ",
footnote_as_chunk = T,
threeparttable = T)| Fechas | Costa Rica | El Salvador | Guatemala | Honduras | Nicaragua | República Dominicana | Panamá |
|---|---|---|---|---|---|---|---|
| 1990-I | – | 48.97 | – | – | – | – | – |
| 1990-II | – | 56.32 | – | – | – | – | – |
| 1990-III | – | 56.41 | – | – | – | – | – |
| 1990-IV | – | 59.88 | – | – | – | – | – |
| 1991-I | 2730297.53 | 50.54 | – | – | – | 43.2 | – |
| 1991-II | 2585732.5299999998 | 58.01 | – | – | – | 40.69 | – |
| 1991-III | 2614916.7799999998 | 56.98 | – | – | – | 37.78 | – |
| 1991-IV | 2873789.53 | 59.37 | – | – | – | 41.06 | – |
| 1992-I | 2966524.89 | 53.82 | – | – | – | 46.32 | – |
| 1992-II | 2788824.31 | 59.47 | – | – | – | 46.39 | – |
| Nota: Elaborado con datos del Consejo Monetario Centroamericano |
Costa Rica
Implementacion personalizada
library(dplyr)
library(mFilter)
library(forecast)
# Se convierte la columna de Costa Rica a numérica y se eliminan los valores faltantes
PIB_trimestral$`Costa Rica` <- as.numeric(PIB_trimestral$`Costa Rica`)
PIB_trimestral <- PIB_trimestral %>% filter(!is.na(`Costa Rica`))
TS_CR<-ts(PIB_trimestral$`Costa Rica`,start = c(1991,1),frequency = 4)
# Aplica el filtro de Hodrick-Prescott
hp_resultCR <- hpfilter(TS_CR, freq = 1600)
# Extrae la tendencia y el componente cíclico
trend <- hp_resultCR$trend
cycle <- hp_resultCR$cycle
# Visualiza los resultados
plot(TS_CR, type = "l", main = "Filtro de Hodrick-Prescott Costa Rica (1991,I - 2024,II)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2)
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)
plot(cycle, type = "l", main = "Componente Ciclico Costa Rica (1991,I - 2024,II)", ylab = "Ciclo", xlab = "Tiempo")
El Salvador
Implementacion personalizada
library(dplyr)
library(mFilter)
library(forecast)
# Se convierte la columna de El Salvador en numérica y se eliminan los valores faltantes
PIB_trimestral$`El Salvador`<- as.numeric(PIB_trimestral$`El Salvador`)
PIB_trimestral <- PIB_trimestral %>% filter(!is.na(`El Salvador`))
TS_ES<-ts(PIB_trimestral$`El Salvador`,start = c(1990,1),frequency = 4)
# Aplica el filtro de Hodrick-Prescott
hp_resultES <- hpfilter(TS_ES, freq = 1600)
# Extrae la tendencia y el componente cíclico
trend <- hp_resultES$trend
cycle <- hp_resultES$cycle
# Visualiza los resultados
plot(TS_ES, type = "l", main = "Filtro de Hodrick-Prescott para El Salvador (1990,I - 2024,II)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2)
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)
plot(cycle, type = "l", main = "Componente Ciclico El Salvador (1991,I - 2024,II)", ylab = "Ciclo", xlab = "Tiempo")
Guatemala
Implementacion personalizada
library(dplyr)
library(mFilter)
library(forecast)
# Se convierte la columna de Guatemala en numérica y se eliminan los valores faltantes
PIB_trimestral$Guatemala<- as.numeric(PIB_trimestral$Guatemala)
PIB_trimestral <- PIB_trimestral %>% filter(!is.na(Guatemala))
TS_GT<-ts(PIB_trimestral$Guatemala,start = c(2001,1),frequency = 4)
# Aplica el filtro de Hodrick-Prescott
hp_resultGT <- hpfilter(TS_GT, freq = 1600)
# Extrae la tendencia y el componente cíclico
trend <- hp_resultGT$trend
cycle <- hp_resultGT$cycle
# Visualiza los resultados
plot(TS_GT, type = "l", main = "Filtro de Hodrick-Prescott para Guatemala (2001,I - 2024,II)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2)
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)
plot(cycle, type = "l", main = "Componente Ciclico Guatemala (2001,I - 2024,II)", ylab = "Ciclo", xlab = "Tiempo")
Honduras
Implementacion personalizada
library(dplyr)
library(mFilter)
library(forecast)
# Se convierte la columna de Honduras en numérica y se eliminan los valores faltantes
PIB_trimestral$Honduras<- as.numeric(PIB_trimestral$Honduras)
PIB_trimestral <- PIB_trimestral %>% filter(!is.na(Honduras))
TS_HN<-ts(PIB_trimestral$Honduras,start = c(2000,1),frequency = 4)
# Aplica el filtro de Hodrick-Prescott
hp_resultHN <- hpfilter(TS_HN, freq = 1600)
# Extrae la tendencia y el componente cíclico
trend <- hp_resultHN$trend
cycle <- hp_resultHN$cycle
# Visualiza los resultados
plot(TS_HN, type = "l", main = "Filtro de Hodrick-Prescott para Honduras (2000,I - 2024,II)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2)
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)
plot(cycle, type = "l", main = "Componente Ciclico Honduras (2000,I - 2024,II)", ylab = "Ciclo", xlab = "Tiempo")
Nicaragua
Implementacion personalizada
library(dplyr)
library(mFilter)
library(forecast)
# Se convierte la columna de Nicaragua en numérica y se eliminan los valores faltantes
PIB_trimestral$Nicaragua<- as.numeric(PIB_trimestral$Nicaragua)
PIB_trimestral <- PIB_trimestral %>% filter(!is.na(Nicaragua))
TS_NC<-ts(PIB_trimestral$Nicaragua,start = c(2006,1),frequency = 4)
# Aplica el filtro de Hodrick-Prescott
hp_resultNC <- hpfilter(TS_NC, freq = 1600)
# Extrae la tendencia y el componente cíclico
trend <- hp_resultNC$trend
cycle <- hp_resultNC$cycle
# Visualiza los resultados
plot(TS_NC, type = "l", main = "Filtro de Hodrick-Prescott para Nicaragua (2006,I - 2024,II)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2)
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)
plot(cycle, type = "l", main = "Componente Ciclico Nicaragua (2006,I - 2024,II)", ylab = "Ciclo", xlab = "Tiempo")
República Dominicana
Implementacion personalizada
library(dplyr)
library(mFilter)
library(forecast)
# Se convierte la columna de Republica Dominicana en numérica y se eliminan los valores faltantes
PIB_trimestral$`República Dominicana`<- as.numeric(PIB_trimestral$`República Dominicana`)
PIB_trimestral <- PIB_trimestral %>% filter(!is.na(`República Dominicana`))
TS_RD<-ts(PIB_trimestral$`República Dominicana`,start = c(1991,1),frequency = 4)
# Aplica el filtro de Hodrick-Prescott
hp_resultRD <- hpfilter(TS_RD, freq = 1600)
# Extrae la tendencia y el componente cíclico
trend <- hp_resultRD$trend
cycle <- hp_resultRD$cycle
# Visualiza los resultados
plot(TS_RD, type = "l", main = "Filtro de Hodrick-Prescott para Republica Dominicana (1991,I - 2024,II)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2)
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)
plot(cycle, type = "l", main = "Componente Ciclico Republica Dominicana (1991,I - 2024,II)", ylab = "Ciclo", xlab = "Tiempo")
Panamá
Implementacion personalizada
library(dplyr)
library(mFilter)
library(forecast)
# Se convierte la columna de Panama en numérica y se eliminan los valores faltantes
PIB_trimestral$Panamá<- as.numeric(PIB_trimestral$Panamá)
PIB_trimestral <- PIB_trimestral %>% filter(!is.na(Panamá))
TS_PM<-ts(PIB_trimestral$Panamá,start = c(1996,1),frequency = 4)
# Aplica el filtro de Hodrick-Prescott
hp_resultPM <- hpfilter(TS_PM, freq = 1600)
# Extrae la tendencia y el componente cíclico
trend <- hp_resultPM$trend
cycle <- hp_resultPM$cycle
# Visualiza los resultados
plot(TS_PM, type = "l", main = "Filtro de Hodrick-Prescott para Panama (1996,I - 2022,III)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2)
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)
plot(cycle, type = "l", main = "Componente Ciclico Republica Dominicana (1996,I - 2022,III)", ylab = "Ciclo", xlab = "Tiempo")
