Estas son las operaciones realizadas en el video correspondiente al tema
grupo<-c(rep("experimental",20), rep("control",20))
grupo
## [1] "experimental" "experimental" "experimental" "experimental" "experimental"
## [6] "experimental" "experimental" "experimental" "experimental" "experimental"
## [11] "experimental" "experimental" "experimental" "experimental" "experimental"
## [16] "experimental" "experimental" "experimental" "experimental" "experimental"
## [21] "control" "control" "control" "control" "control"
## [26] "control" "control" "control" "control" "control"
## [31] "control" "control" "control" "control" "control"
## [36] "control" "control" "control" "control" "control"
puntaje<-c(rnorm(20,5,5), rnorm(20, 35, 4))
puntaje
## [1] 7.0448065 -1.7635494 -0.9661607 3.3180538 -1.3788068 3.8476207
## [7] 11.6251510 10.8810384 5.0245474 9.8877433 4.4876607 3.9862112
## [13] 2.2145108 7.5186145 4.5699625 6.9373003 4.5859927 8.8651768
## [19] 3.6252316 4.1437260 34.8415443 32.9772615 37.7736161 36.4083677
## [25] 31.3998769 28.3572260 35.3174458 31.5359052 37.5778389 39.8846166
## [31] 36.7964508 30.3064774 37.7954841 35.6373317 33.3200137 37.6133593
## [37] 41.2649011 30.6844942 32.0374443 33.1825020
puntaje<-round(puntaje,2) # en el video esto está hecho más tarde
puntajes.por.grupo<-cbind(grupo, puntaje)
class(puntajes.por.grupo)
## [1] "matrix" "array"
puntajes.por.grupo<-as.data.frame(puntajes.por.grupo)
attributes(puntajes.por.grupo)
## $names
## [1] "grupo" "puntaje"
##
## $class
## [1] "data.frame"
##
## $row.names
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [26] 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
class(puntajes.por.grupo$grupo)
## [1] "character"
# en este caso la leyó como carácter
#la forzamos a ser un factor
puntajes.por.grupo$grupo<-as.factor(puntajes.por.grupo$grupo)
levels(puntajes.por.grupo$grupo)
## [1] "control" "experimental"
write.table(puntajes.por.grupo, "basenueva.csv")
write.table(puntajes.por.grupo, "basenueva.csv", sep = ";", row.names = F)
# en el video se importa la 3/2018, aquí la 4/2022
# el doble .txt es el nombre con el que baja del sitio del INDEC
eph.4.22<-read.table("usu_individual_T422.txt.txt")
eph.4.22<-read.table("usu_individual_T422.txt.txt", sep=";")
eph.4.22<-read.table("usu_individual_T422.txt.txt", sep=";", header = T)
class(eph.4.22)
## [1] "data.frame"
names(eph.4.22)
## [1] "CODUSU" "ANO4" "TRIMESTRE" "NRO_HOGAR" "COMPONENTE"
## [6] "H15" "REGION" "MAS_500" "AGLOMERADO" "PONDERA"
## [11] "CH03" "CH04" "CH05" "CH06" "CH07"
## [16] "CH08" "CH09" "CH10" "CH11" "CH12"
## [21] "CH13" "CH14" "CH15" "CH15_COD" "CH16"
## [26] "CH16_COD" "NIVEL_ED" "ESTADO" "CAT_OCUP" "CAT_INAC"
## [31] "IMPUTA" "PP02C1" "PP02C2" "PP02C3" "PP02C4"
## [36] "PP02C5" "PP02C6" "PP02C7" "PP02C8" "PP02E"
## [41] "PP02H" "PP02I" "PP03C" "PP03D" "PP3E_TOT"
## [46] "PP3F_TOT" "PP03G" "PP03H" "PP03I" "PP03J"
## [51] "INTENSI" "PP04A" "PP04B_COD" "PP04B1" "PP04B2"
## [56] "PP04B3_MES" "PP04B3_ANO" "PP04B3_DIA" "PP04C" "PP04C99"
## [61] "PP04D_COD" "PP04G" "PP05B2_MES" "PP05B2_ANO" "PP05B2_DIA"
## [66] "PP05C_1" "PP05C_2" "PP05C_3" "PP05E" "PP05F"
## [71] "PP05H" "PP06A" "PP06C" "PP06D" "PP06E"
## [76] "PP06H" "PP07A" "PP07C" "PP07D" "PP07E"
## [81] "PP07F1" "PP07F2" "PP07F3" "PP07F4" "PP07F5"
## [86] "PP07G1" "PP07G2" "PP07G3" "PP07G4" "PP07G_59"
## [91] "PP07H" "PP07I" "PP07J" "PP07K" "PP08D1"
## [96] "PP08D4" "PP08F1" "PP08F2" "PP08J1" "PP08J2"
## [101] "PP08J3" "PP09A" "PP09A_ESP" "PP09B" "PP09C"
## [106] "PP09C_ESP" "PP10A" "PP10C" "PP10D" "PP10E"
## [111] "PP11A" "PP11B_COD" "PP11B1" "PP11B2_MES" "PP11B2_ANO"
## [116] "PP11B2_DIA" "PP11C" "PP11C99" "PP11D_COD" "PP11G_ANO"
## [121] "PP11G_MES" "PP11G_DIA" "PP11L" "PP11L1" "PP11M"
## [126] "PP11N" "PP11O" "PP11P" "PP11Q" "PP11R"
## [131] "PP11S" "PP11T" "P21" "DECOCUR" "IDECOCUR"
## [136] "RDECOCUR" "GDECOCUR" "PDECOCUR" "ADECOCUR" "PONDIIO"
## [141] "TOT_P12" "P47T" "DECINDR" "IDECINDR" "RDECINDR"
## [146] "GDECINDR" "PDECINDR" "ADECINDR" "PONDII" "V2_M"
## [151] "V3_M" "V4_M" "V5_M" "V8_M" "V9_M"
## [156] "V10_M" "V11_M" "V12_M" "V18_M" "V19_AM"
## [161] "V21_M" "T_VI" "ITF" "DECIFR" "IDECIFR"
## [166] "RDECIFR" "GDECIFR" "PDECIFR" "ADECIFR" "IPCF"
## [171] "DECCFR" "IDECCFR" "RDECCFR" "GDECCFR" "PDECCFR"
## [176] "ADECCFR" "PONDIH"
eph.4.22$sexo<-as.factor(eph.4.22$CH04)
levels(eph.4.22$sexo)
## [1] "1" "2"
levels(eph.4.22$sexo)<-c("varon", "mujer")
eph.4.22$ESTADO<-as.factor(eph.4.22$ESTADO)
levels(eph.4.22$ESTADO)
## [1] "0" "1" "2" "3" "4"
levels(eph.4.22$ESTADO)<-c(NA, "ocupade", "desocupade", "inactive", NA)
levels(eph.4.22$ESTADO)
## [1] "ocupade" "desocupade" "inactive"