Qué necesitamos para cargar datos de diversas fuentes? En principio algunas librerias de R
#install.packages("tidyverse")library(haven)
eph <- read_sav("REG02_EPHC_T4_2023.SAV")Verificar algunas de las variables
names(eph)## [1] "UPM" "NVIVI" "NHOGA" "TRIMESTRE" "RONDA"
## [6] "ANIO" "AREA" "ESTGEO" "L02" "P02"
## [11] "P03" "P06" "P09" "A01" "A01A"
## [16] "A02" "A03" "A04" "A04B" "A04A"
## [21] "A05" "A06" "A06E" "A07" "A08"
## [26] "A09" "A09E" "A10" "A11A" "A11M"
## [31] "A11S" "A12" "A13REC" "A14REC" "A15"
## [36] "A16" "A17A" "A17M" "A17S" "A18"
## [41] "B01REC" "B02REC" "B03LU" "B03MA" "B03MI"
## [46] "B03JU" "B03VI" "B03SA" "B03DO" "B04"
## [51] "B05" "B06" "B07A" "B07M" "B07S"
## [56] "B08" "B09A" "B09M" "B09S" "B10"
## [61] "B11" "B12" "B13" "B14" "B15"
## [66] "B16G" "B16U" "B16D" "B16T" "B17"
## [71] "B18AG" "B18AU" "B18BG" "B18BU" "B19"
## [76] "B20G" "B20U" "B20D" "B20T" "B21"
## [81] "B22" "B23" "B24" "B25" "B26"
## [86] "B271" "B272" "B28" "B29" "B30"
## [91] "B31" "C01REC" "C02REC" "C03" "C04"
## [96] "C05" "C06" "C07" "C08" "C09"
## [101] "C101" "C102" "C11G" "C11U" "C11D"
## [106] "C11T" "C12" "C13AG" "C13AU" "C13BG"
## [111] "C13BU" "C14" "C14A" "C14B" "C14C"
## [116] "C15" "C16REC" "C17REC" "C18" "C18A"
## [121] "C18B" "C19" "D01" "D02" "D03"
## [126] "D04" "D05" "CATE_PEA" "TAMA_PEA" "OCUP_PEA"
## [131] "RAMA_PEA" "HORAB" "HORABC" "HORABCO" "PEAD"
## [136] "PEAD_1" "PEAA" "FEX.2022" "añoest" "Informalidad"
## [141] "E01AIMDE" "E01BIMDE" "E01CIMDE" "E01DDE" "E01EDE"
## [146] "E01FDE" "E01GDE" "E01HDE" "E01IDE" "E01JDE"
## [151] "E01KDE" "E01LDE" "E01MDE" "E01KJDE"Sexo (P06)
table(eph$P06)##
## 1 6
## 8287 8488*Etiquetamos las categorias para la variable sexo (p06)
eph$P06=factor(eph$P06, levels = c(1,6),labels = c("Hombres","Mujeres"))
table(eph$P06)##
## Hombres Mujeres
## 8287 8488cantidad de población
tabla1=aggregate(FEX.2022 ~ P06,data=eph,sum)
tabla1## P06 FEX.2022
## 1 Hombres 2900086
## 2 Mujeres 3002988los salarios de las mujeres en promedio son mas bajos o altos que el de los hombres?
La variable ingreso se llama e01aimde
tabla2=aggregate(as.numeric(E01AIMDE) ~ P06, data=eph, mean)
tabla2## P06 as.numeric(E01AIMDE)
## 1 Hombres 1815106.2
## 2 Mujeres 845322.7Explorar otras variables como: Area de residencia (AREA)
Edad (P02)
Categoria de ocupacion (PEAA)