1 “CLASE 1”

rm(list = ls())

Utilizar siempre minusculas, sin tildes ni caracteres especiales

Nombres de variables

Creacion de objetos

1.1 Escalar

escalar1 <- 3
escalar2 <- 4

1.2 Operaciones

escalar1 + escalar2
## [1] 7
escalar3 <- escalar1 + escalar2
escalar3<-escalar1+escalar2

escalar4 <- escalar3 * escalar2
escalar5 <- escalar4/escalar1
escalar5
## [1] 9.333333
summary(escalar5)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   9.333   9.333   9.333   9.333   9.333   9.333
table(escalar5)
## escalar5
## 9.33333333333333 
##                1

1.3 Vectores

vect1 <- c(2,1.5,4) #vector numerico
vect2 <- c("Juan","Pedro","Sara")
vect3 <- c(5,6,2)

prd1 <- vect1 *escalar4

1.4 Ubicacion

vect1[2]
## [1] 1.5
vect2[3]
## [1] "Sara"
objeto1 <- vect3[1]

objeto2 <- vect2[2:3]

objeto3 <- vect2[1:2]

objeto4 <- vect2[c(1,3)]
objeto4_f2 <- vect2[-2]

1.5 Matrices

vector1 <- c(1,2,3)
vector2 <- c(4,5,6)
vector3 <- c(7,8,9)

matrizA <- cbind(vector1,vector2,vector3)
matrizA
##      vector1 vector2 vector3
## [1,]       1       4       7
## [2,]       2       5       8
## [3,]       3       6       9
matrizB <- rbind(vector1,vector2,vector3)
matrizB
##         [,1] [,2] [,3]
## vector1    1    2    3
## vector2    4    5    6
## vector3    7    8    9

1.6 Bases de datos (data frames)

base1 <- as.data.frame(matrizA)
base2 <- as.data.frame(matrizB)

1.7 Ingresar a objetos en bases de datos (tomar variables con $)

base1$vector1
## [1] 1 2 3

1.8 Cambiar de nombre a variables

nombre_vectores <- c("variable1","variable2","variable3")

names(base1) <- nombre_vectores

1.9 Cargar bases de datos internas

Filtros Borramos todo

rm(list = ls())
base <- mtcars

Filtros

Vehiculos con mas de 4 cilindros

1.10 Primera forma subset

base1 <- subset(base,base$cyl > 4)

## Segunda forma (matricial)

base1_f2 <- base[base$cyl>4,]

1.11 Tercer forma (dplyr)

#install.packages('dplyr')
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.5.1
## 
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
base1_f3 <- base %>% 
  filter(cyl>4)

2 “CLASE 2”

2.1 Librerias

#install.packages('readxl')
library(readxl)
## Warning: package 'readxl' was built under R version 4.5.1
#install.packages("dplyr")
library(dplyr)
#install.packages("haven")
library(haven)
## Warning: package 'haven' was built under R version 4.5.1

2.2 Cargar bases de datos

base <- read_excel("pib_can_anual.xlsx")
## New names:
## • `` -> `...20`
pib_can_anual <- read_excel("pib_can_anual.xlsx")
## New names:
## • `` -> `...20`

2.3 Cambiar de nombre a variables

names(base)[6] <-'agricultura'

2.4 Reemplazar los NA con 0

base[is.na(base)] <- 0

2.5 Ver cuantas observaciones tengo por variable

table(base$prov)
## 
##            AZUAY          BOLÍVAR            CAÑAR           CARCHI 
##              150               70               70               60 
##       CHIMBORAZO         COTOPAXI           EL ORO       ESMERALDAS 
##              100               70              140               71 
##        GALÁPAGOS           GUAYAS         IMBABURA             LOJA 
##               30              250               60              160 
##         LOS RÍOS           MANABÍ  MORONA SANTIAGO             NAPO 
##              130              220              120               50 
##         ORELLANA          PASTAZA        PICHINCHA      SANTA ELENA 
##               40               40               80               30 
##    SANTO DOMINGO        SUCUMBÍOS       TUNGURAHUA ZAMORA CHINCHIPE 
##               19               70               90               90

2.6 Nos quedamos con una provincia

base_santo <- base %>% 
  filter(dpa_prov == "23")

base_manabi <- base %>% 
  filter(prov== "MANABÍ")

2.7 Quedarme solo con las variables necesarias

names(base_manabi)
##  [1] "year"                                     
##  [2] "prov"                                     
##  [3] "dpa_prov"                                 
##  [4] "canton"                                   
##  [5] "dpa_can"                                  
##  [6] "agricultura"                              
##  [7] "Explotacion de minas y canteras"          
##  [8] "Manufactura\r\n\r\n"                      
##  [9] "Suministro de electricidad y de agua"     
## [10] "Construccion\r\n\r\n"                     
## [11] "comercio\r\n\r\n"                         
## [12] "Alojamiento y servicios de comida"        
## [13] "Transporte, informacion y comunicaciones" 
## [14] "Actividades financieras\r\n"              
## [15] "Actividades profesionales e inmobiliarias"
## [16] "Administracion publica \r\n"              
## [17] "Enseñanza\r\n\r\n"                        
## [18] "Salud\r\n\r\n"                            
## [19] "Otros servicios\r\n\r\n"                  
## [20] "...20"
base_manabi1 <- base_manabi %>% 
  select(year,prov,dpa_prov,canton,dpa_can,agricultura,'Explotacion de minas y canteras')

2.8 Vista resumen de una variables

summary(base_manabi1$agricultura)
##      Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
##     80.46   4888.18  11260.08  29351.06  38616.46 234997.81

Valor limite 29351.06

2.9 Eliminar ultima variable

base_manabi1 <- base_manabi1[,-7]

2.10 Crear nueva variable dicotoma (mutate)

base_manabi1 <- base_manabi1 %>% 
  mutate(tipo_pib= ifelse(agricultura > 29351,"pib_alto","pib_bajo"))

base_manabi1 <- base_manabi1 %>% 
  mutate(tipo= ifelse(agricultura > 29351,1,0))

base_manabi1 <- base_manabi1 %>% 
  mutate(periodo= ifelse(year < 2016,"pre","post"))

3 “CLASE 3”

3.1 Dividamos las bases por periodo

base_manabi_pre <- base_manabi1 %>% 
  filter(periodo=="pre")
base_manabi_post <- base_manabi1 %>% 
  filter(periodo=="post")

3.2 Sumar el PIB de agricultura por Canton

b_m_pre_agg <- base_manabi_pre %>% 
  group_by(canton) %>% 
  summarise(total_agricultura_pre=sum(agricultura))

b_m_post_agg <- base_manabi_post %>% 
  group_by(canton) %>% 
  summarise(total_agricultura_post=sum(agricultura))

4 “CLASE 4”

4.1 Cargar bases de datos

rm(list = ls())

base <- read.csv('base_final - base_final (1).csv')

4.2 Librerias

library(dplyr)

4.3 Filtramos la base de datos desde 1980 hasta 2024

base <- base %>% 
  filter(anio>=1980)

4.4 Creamos una nueva variable

4.5 Primera forma

Ingreso_disponible <- base$Pib_impuestos
Ingreso_disponible <- base$pib-base$impuestos
base$ingreso_disponible <- base$pib-base$impuestos

4.6 Segunda forma

base <- base %>% 
  mutate(ingreso_disponible2 = pib - impuestos)

4.7 Modelo Econometrico

C = B1 + B2*YD +u

options(scipen = 999)

modelo <- lm(consumo ~ ingreso_disponible,data=base)
summary(modelo)
## 
## Call:
## lm(formula = consumo ~ ingreso_disponible, data = base)
## 
## Residuals:
##         Min          1Q      Median          3Q         Max 
## -4901431887 -1069569495  -195228251  1233327995  6870277166 
## 
## Coefficients:
##                             Estimate        Std. Error t value
## (Intercept)        14165415645.32893   935246532.56462   15.15
## ingreso_disponible           0.68472           0.01397   49.01
##                               Pr(>|t|)    
## (Intercept)        <0.0000000000000002 ***
## ingreso_disponible <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 2450000000 on 43 degrees of freedom
## Multiple R-squared:  0.9824, Adjusted R-squared:  0.982 
## F-statistic:  2402 on 1 and 43 DF,  p-value: < 0.00000000000000022

4.8 Creamos variables logaritmicas

base <- base %>% 
  mutate(ln_consumo = log(consumo),
         ln_ingreso_disponible = log(ingreso_disponible))

modelo2 <- lm(ln_consumo ~ ln_ingreso_disponible, data = base)

summary(modelo2)
## 
## Call:
## lm(formula = ln_consumo ~ ln_ingreso_disponible, data = base)
## 
## Residuals:
##       Min        1Q    Median        3Q       Max 
## -0.113225 -0.021156  0.005125  0.031844  0.124035 
## 
## Coefficients:
##                       Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)            6.70498    0.45862   14.62 <0.0000000000000002 ***
## ln_ingreso_disponible  0.72715    0.01852   39.26 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.05187 on 43 degrees of freedom
## Multiple R-squared:  0.9729, Adjusted R-squared:  0.9722 
## F-statistic:  1541 on 1 and 43 DF,  p-value: < 0.00000000000000022
confint(modelo)
##                                  2.5 %              97.5 %
## (Intercept)        12279311258.7509937 16051520031.9068737
## ingreso_disponible           0.6565423           0.7128939
confint(modelo2)
##                           2.5 %    97.5 %
## (Intercept)           5.7800964 7.6298736
## ln_ingreso_disponible 0.6897913 0.7645002

5 “CLASE 5”

5.1 Cargar bases de datos

rm(list = ls())

base <- read.csv("datos_ecuador - datos_ecuador.csv")

5.2 Modelo: desempleo = B1 + B2*PIB +u

names(base)
## [1] "anio"                     "trim"                    
## [3] "RiesgoPais"               "PIB_MillonesUSD"         
## [5] "TasaDesempleo_Porcentaje" "IED_MillonesUSD"
modelo_desempleo <- lm(TasaDesempleo_Porcentaje ~ PIB_MillonesUSD, data=base)
modelo_desemepleo2 <- lm(base$TasaDesempleo_Porcentaje ~base$PIB_MillonesUSD)


summary(modelo_desempleo)
## 
## Call:
## lm(formula = TasaDesempleo_Porcentaje ~ PIB_MillonesUSD, data = base)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.6369 -0.8933 -0.1452  0.4323  7.6118 
## 
## Coefficients:
##                    Estimate  Std. Error t value          Pr(>|t|)    
## (Intercept)      8.37282462  0.92082867   9.093 0.000000000000595 ***
## PIB_MillonesUSD -0.00010715  0.00003556  -3.014           0.00376 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.377 on 61 degrees of freedom
## Multiple R-squared:  0.1296, Adjusted R-squared:  0.1153 
## F-statistic: 9.081 on 1 and 61 DF,  p-value: 0.003758
summary(modelo_desemepleo2)
## 
## Call:
## lm(formula = base$TasaDesempleo_Porcentaje ~ base$PIB_MillonesUSD)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.6369 -0.8933 -0.1452  0.4323  7.6118 
## 
## Coefficients:
##                         Estimate  Std. Error t value          Pr(>|t|)    
## (Intercept)           8.37282462  0.92082867   9.093 0.000000000000595 ***
## base$PIB_MillonesUSD -0.00010715  0.00003556  -3.014           0.00376 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.377 on 61 degrees of freedom
## Multiple R-squared:  0.1296, Adjusted R-squared:  0.1153 
## F-statistic: 9.081 on 1 and 61 DF,  p-value: 0.003758

5.3 Modelo: IED = B1 + B2* RP +u

names(base)
## [1] "anio"                     "trim"                    
## [3] "RiesgoPais"               "PIB_MillonesUSD"         
## [5] "TasaDesempleo_Porcentaje" "IED_MillonesUSD"
model_ied <- lm(IED_MillonesUSD ~ RiesgoPais, data=base)
summary(model_ied)
## 
## Call:
## lm(formula = IED_MillonesUSD ~ RiesgoPais, data = base)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -317.37  -55.76  -16.82   54.14  279.09 
## 
## Coefficients:
##              Estimate Std. Error t value       Pr(>|t|)    
## (Intercept) 229.89653   29.74552   7.729 0.000000000129 ***
## RiesgoPais   -0.04321    0.02458  -1.758         0.0838 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 107.9 on 61 degrees of freedom
## Multiple R-squared:  0.04821,    Adjusted R-squared:  0.0326 
## F-statistic: 3.089 on 1 and 61 DF,  p-value: 0.08382

5.4 Creamos el Riesgo pais Rezagado

library(dplyr)
base <- base %>% 
  mutate(ied_rezagado1= lag(IED_MillonesUSD,n=1),
         rp_rezagado1 = lag(RiesgoPais,n=1),
         rp_rezagado2 = lag(RiesgoPais,n=2))

5.5 Modelo rezagado

names(base)
## [1] "anio"                     "trim"                    
## [3] "RiesgoPais"               "PIB_MillonesUSD"         
## [5] "TasaDesempleo_Porcentaje" "IED_MillonesUSD"         
## [7] "ied_rezagado1"            "rp_rezagado1"            
## [9] "rp_rezagado2"
model_ied_lag1 <- lm(IED_MillonesUSD ~ rp_rezagado1, data=base)
summary(model_ied_lag1)
## 
## Call:
## lm(formula = IED_MillonesUSD ~ rp_rezagado1, data = base)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -319.35  -55.08  -20.33   52.81  271.41 
## 
## Coefficients:
##               Estimate Std. Error t value      Pr(>|t|)    
## (Intercept)  208.40204   30.70883   6.786 0.00000000578 ***
## rp_rezagado1  -0.02284    0.02527  -0.904          0.37    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 110.7 on 60 degrees of freedom
##   (1 observation deleted due to missingness)
## Multiple R-squared:  0.01343,    Adjusted R-squared:  -0.003015 
## F-statistic: 0.8167 on 1 and 60 DF,  p-value: 0.3698
model_ied_lag2 <- lm(IED_MillonesUSD ~ rp_rezagado2, data=base)
summary(model_ied_lag2)
## 
## Call:
## lm(formula = IED_MillonesUSD ~ rp_rezagado2, data = base)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -320.59  -53.15  -14.34   49.29  266.92 
## 
## Coefficients:
##               Estimate Std. Error t value      Pr(>|t|)    
## (Intercept)  214.06880   30.81112   6.948 0.00000000332 ***
## rp_rezagado2  -0.02707    0.02533  -1.069          0.29    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 111 on 59 degrees of freedom
##   (2 observations deleted due to missingness)
## Multiple R-squared:  0.01899,    Adjusted R-squared:  0.002358 
## F-statistic: 1.142 on 1 and 59 DF,  p-value: 0.2896

5.6 Correccion prueba

Utilice la base de datos “datos_ecuador.csv”, para el periodo entre 2015 y 2023, Corra el modelo desempleo = B1 + B2*Ln(PIB) +u. Indique el valor de B2. (Ingrese su valor con 2 decimales sin redondear)

rm(list = ls())
base <- read.csv("datos_ecuador - datos_ecuador.csv")

Filtro

base1 <- base %>% 
  filter(anio> 2015 & anio < 2023) %>% 
  mutate(ln_pib=log(PIB_MillonesUSD))

Modelo

names(base1)
## [1] "anio"                     "trim"                    
## [3] "RiesgoPais"               "PIB_MillonesUSD"         
## [5] "TasaDesempleo_Porcentaje" "IED_MillonesUSD"         
## [7] "ln_pib"
modelo1 <- lm(TasaDesempleo_Porcentaje ~ ln_pib,data = base1)
summary(modelo1)
## 
## Call:
## lm(formula = TasaDesempleo_Porcentaje ~ ln_pib, data = base1)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.4957 -0.9472 -0.3826  0.3515  6.4448 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)  
## (Intercept)  105.698     42.899   2.464   0.0207 *
## ln_pib        -9.759      4.205  -2.321   0.0284 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.559 on 26 degrees of freedom
## Multiple R-squared:  0.1716, Adjusted R-squared:  0.1398 
## F-statistic: 5.387 on 1 and 26 DF,  p-value: 0.0284

B2= -9.75

Utilice la base de datos “datos_ecuador.csv”, Para el periodo deshde 2015 hasta 2023, corra el modelo desempleo = B1 + B2*PIB +u. Indique el valor de B2. (Ingrese su valor con 2 decimales sin redondear)

rm(list = ls())
base <- read.csv("datos_ecuador - datos_ecuador.csv")

base2 <- base %>% 
  filter(anio>= 2015 & anio <= 2023)
modelo2 <- lm(TasaDesempleo_Porcentaje~PIB_MillonesUSD, data = base2)
summary(modelo2)
## 
## Call:
## lm(formula = TasaDesempleo_Porcentaje ~ PIB_MillonesUSD, data = base2)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.8356 -0.8271 -0.1033  0.1037  6.8451 
## 
## Coefficients:
##                   Estimate Std. Error t value  Pr(>|t|)    
## (Intercept)     12.6811501  2.7428198   4.623 0.0000526 ***
## PIB_MillonesUSD -0.0002485  0.0001002  -2.481    0.0182 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.451 on 34 degrees of freedom
## Multiple R-squared:  0.1533, Adjusted R-squared:  0.1284 
## F-statistic: 6.155 on 1 and 34 DF,  p-value: 0.01821

6 “CLASE 6”

MANEJO DE ENCUESTAS

6.1 Cargar bases de datos

rm(list = ls())
#Librerias
library(dplyr)
#install.packages('srvyr')
library(srvyr)
## Warning: package 'srvyr' was built under R version 4.5.1
## 
## Adjuntando el paquete: 'srvyr'
## The following object is masked from 'package:stats':
## 
##     filter
#install.packages('rio')
library(rio)
## Warning: package 'rio' was built under R version 4.5.1
#install.packages('import')
library(import)
## Warning: package 'import' was built under R version 4.5.1
## The import package should not be attached.
## Use "colon syntax" instead, e.g. import::from, or import:::from.

6.2 Cargamos la base de datos

personas <- import("1_BDD_ENS2018_f1_personas (3).dta")

6.3 Identificamos la variable

table(personas$dcronica_2)
## 
##    0    1 
## 5591 2210
dci <- 2210/(5591+2210)
dci*100
## [1] 28.3297

6.4 Trabajando con muestras oficiales

dm <- personas %>% 
  as_survey_design(ids=upm,   #unidad primaria de muestreo
                   strata=estrato, #estrato
                   weights = fexp) #factor de expansion
options(survey.lonely.psu = 'certainty') #forzando a que las observaciones sean unicas e individuales


prev_nac_dci2 <- dm %>% 
  summarise(survey_mean(dcronica_2, vartype =c('se','cv'),na.rm=T),
            n_muestra=sum(!is.na(dcronica_2))) %>% 
  mutate(dominio="Nacional") %>% 
  select(dominio, porcentaje=coef, se=`_se`, cv=`_cv`, n_muestra) %>% 
  mutate(porcentaje=round((porcentaje*100),digits = 1))

6.5 ENEMDU II TRIMESTRE 2025

rm(list = ls())
library(dplyr)
library(srvyr)
library(rio)
#installed.packages('haven')
library(haven)
df <- read.csv2("enemdu_persona_2025_II_trimestre.csv")
df2 <- read.csv("enemdu_persona_2025_II_trimestre.csv",sep = ';')

6.6 Declaracion del disenio muestral

dm <- df %>% 
  as_survey_design(ids=upm,   #unidad primaria de muestreo
                   strata=estrato, #estrato
                   weights = fexp) #factor de expansion

6.7 Replicar indicadores

TASA DE DESEMPLEO NACIONAL

tasa_desempleo_nac <- dm %>% 
  filter(p03>=15) %>% 
  summarise(
    tasa_desempleo = survey_ratio(
      numerator=( condact == 7 | condact==8),
      denominator=(condact %in% 1:8),
      vartype = c('se','ci')
    ) 
  ) %>% 
  mutate(tasa_desempleo = round((tasa_desempleo*100),digits = 1))

TASA DE EMPLEO ADECUADO

tasa_empleo_adec <- dm %>% 
  filter(p03>=15) %>% 
  summarise(
    tasa_empleo_adecuado = survey_ratio(
      numerator=( condact == 1),
      denominator=(condact %in% 1:8),
      vartype = c('se','ci')
    ) 
  ) %>% 
  mutate(tasa_empleo_adecuado = round((tasa_empleo_adecuado*100),digits = 1))

TASA DE subempleo

tasa_subempleo_nac <- dm %>% 
  filter(p03>=15) %>% 
  summarise(
    tasa_subempleo = survey_ratio(
      numerator=( condact == 2 | condact==3),
      denominator=(condact %in% 1:8),
      vartype = c('se','ci')
    ) 
  ) %>% 
  mutate(tasa_subempleo = round((tasa_subempleo*100),digits = 1))

TASA DE EMPLEO no remunerado

tasa_empleo_norem <- dm %>% 
  filter(p03>=15) %>% 
  summarise(
    tasa_empleo_norem = survey_ratio(
      numerator=( condact == 5),
      denominator=(condact %in% 1:8),
      vartype = c('se','ci')
    ) 
  ) %>% 
  mutate(tasa_empleo_norem = round((tasa_empleo_norem*100),digits = 1))