Correlaciones entre variables del Censo de Viviendas, Hogares y Personas e ingresos promedios comunales de la CASEN 2017.
VE-CC-AJ
DataIntelligenceViernes 02-07-2021
Abstract
Calculamos correlaciones entre el ingreso promedio comunal multiplicado por la población comunal que llamaremos ipcmp extraído de la Casen 2017 y las frecuencias de categorías de respuesta para todas las variables del Censo de viviendas, hogares y personas al 2017, también extraídas a nivel comunal.
Importante es aplicar la libreria dplyr para evitar que en los filtros se desplieguen series de tiempo.
Area: urbano = 1 rural = 2
URBANO
1 Pregunta P03A: Material de los muros exteriores
Ésta pregunta posee 6 categorías de respuesta:
1 Hormigón armado
2 Albañilería: bloque de cemento, piedra o ladrillo
3 Tabique forrado por ambas caras (madera o acero)
4 Tabique sin forro interior (madera u otro)
5 Adobe, barro, quincha, pirca u otro artesanal tradicional
6 Materiales precarios (lata, cartón, plástico, etc.)
98 No aplica
99 Missing
1.1 Cálculo de frecuencias
Leemos las respuestas a la pregunta P03A del censo de viviendas 2017 y obtenemos la tabla de frecuencias por categoría de respuesta:
tabla_con_clave <- readRDS("../censo_viviendas_con_clave_17.rds")
tabla_con_clave <- filter(tabla_con_clave, tabla_con_clave$AREA == 1)
b <- tabla_con_clave$COMUNA
c <- tabla_con_clave$P03A
cross_tab = xtabs( ~ unlist(b) + unlist(c))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2017"
d_t <- filter(d,d$unlist.c. == 1)
for(i in 2:6){
d_i <- filter(d,d$unlist.c. == i)
d_t = merge( x = d_t, y = d_i, by = "unlist.b.", all.x = TRUE)
}
codigos <- d_t$unlist.b.
rango <- seq(1:nrow(d_t))
cadena <- paste("0",codigos[rango], sep = "")
cadena <- substr(cadena,(nchar(cadena)[rango])-(4),6)
codigos <- as.data.frame(codigos)
cadena <- as.data.frame(cadena)
comuna_corr <- cbind(d_t,cadena)
comuna_corr <- comuna_corr[,-c(1),drop=FALSE]
names(comuna_corr)[19] <- "código"
ingresos_expandidos_2017 <- readRDS("ingresos_expandidos_17_urbano_nacional.rds")
df_2017_2 = merge( x = comuna_corr, y = ingresos_expandidos_2017, by = "código", all.x = TRUE)
tablamadre <- head(df_2017_2,50)
kbl(tablamadre) %>%
kable_styling(bootstrap_options = c("striped", "hover")) %>%
kable_paper() %>%
scroll_box(width = "100%", height = "300px")| código | unlist.c..x | Freq.x | anio.x | unlist.c..y | Freq.y | anio.y | unlist.c..x.1 | Freq.x.1 | anio.x.1 | unlist.c..y.1 | Freq.y.1 | anio.y.1 | unlist.c..x.2 | Freq.x.2 | anio.x.2 | unlist.c..y.2 | Freq.y.2 | anio.y.2 | comuna.x | promedio_i | año | comuna.y | personas | Ingresos_expandidos | tipo |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 01101 | 1 | 20661 | 2017 | 2 | 24209 | 2017 | 3 | 6980 | 2017 | 4 | 2524 | 2017 | 5 | 77 | 2017 | 6 | 306 | 2017 | Iquique | 356487.6 | 2017 | 1101 | 191468 | 68255976664 | Urbano |
| 01107 | 1 | 6109 | 2017 | 2 | 15902 | 2017 | 3 | 2921 | 2017 | 4 | 2791 | 2017 | 5 | 47 | 2017 | 6 | 488 | 2017 | Alto Hospicio | 301933.4 | 2017 | 1107 | 108375 | 32722034397 | Urbano |
| 01401 | 1 | 184 | 2017 | 2 | 1912 | 2017 | 3 | 405 | 2017 | 4 | 194 | 2017 | 5 | 13 | 2017 | 6 | 23 | 2017 | Pozo Almonte | 299998.6 | 2017 | 1401 | 15711 | 4713278189 | Urbano |
| 01404 | 1 | 45 | 2017 | 2 | 84 | 2017 | 3 | 136 | 2017 | 4 | 71 | 2017 | 5 | 13 | 2017 | 6 | 3 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 01405 | 1 | 129 | 2017 | 2 | 582 | 2017 | 3 | 290 | 2017 | 4 | 136 | 2017 | 5 | 121 | 2017 | 6 | 15 | 2017 | Pica | 330061.1 | 2017 | 1405 | 9296 | 3068247619 | Urbano |
| 02101 | 1 | 38428 | 2017 | 2 | 49260 | 2017 | 3 | 5428 | 2017 | 4 | 3921 | 2017 | 5 | 227 | 2017 | 6 | 415 | 2017 | Antofagasta | 347580.2 | 2017 | 2101 | 361873 | 125779893517 | Urbano |
| 02102 | 1 | 747 | 2017 | 2 | 1576 | 2017 | 3 | 354 | 2017 | 4 | 191 | 2017 | 5 | 1 | 2017 | 6 | 32 | 2017 | Mejillones | 369770.7 | 2017 | 2102 | 13467 | 4979702302 | Urbano |
| 02104 | 1 | 380 | 2017 | 2 | 1584 | 2017 | 3 | 822 | 2017 | 4 | 364 | 2017 | 5 | 3 | 2017 | 6 | 30 | 2017 | Taltal | 376328.9 | 2017 | 2104 | 13317 | 5011572025 | Urbano |
| 02201 | 1 | 12795 | 2017 | 2 | 25957 | 2017 | 3 | 2756 | 2017 | 4 | 1063 | 2017 | 5 | 2031 | 2017 | 6 | 372 | 2017 | Calama | 416281.1 | 2017 | 2201 | 165731 | 68990679686 | Urbano |
| 02203 | 1 | 37 | 2017 | 2 | 692 | 2017 | 3 | 230 | 2017 | 4 | 96 | 2017 | 5 | 443 | 2017 | 6 | 18 | 2017 | San Pedro de Atacama | 437934.7 | 2017 | 2203 | 10996 | 4815529626 | Urbano |
| 02301 | 1 | 1767 | 2017 | 2 | 3776 | 2017 | 3 | 1545 | 2017 | 4 | 399 | 2017 | 5 | 21 | 2017 | 6 | 52 | 2017 | Tocopilla | 271720.8 | 2017 | 2301 | 25186 | 6843559467 | Urbano |
| 02302 | 1 | 481 | 2017 | 2 | 663 | 2017 | 3 | 90 | 2017 | 4 | 22 | 2017 | 5 | 87 | 2017 | 6 | 12 | 2017 | María Elena | 466266.9 | 2017 | 2302 | 6457 | 3010685220 | Urbano |
| 03101 | 1 | 7183 | 2017 | 2 | 27319 | 2017 | 3 | 4636 | 2017 | 4 | 2834 | 2017 | 5 | 2102 | 2017 | 6 | 292 | 2017 | Copiapó | 330574.6 | 2017 | 3101 | 153937 | 50887663717 | Urbano |
| 03102 | 1 | 706 | 2017 | 2 | 2901 | 2017 | 3 | 803 | 2017 | 4 | 346 | 2017 | 5 | 32 | 2017 | 6 | 14 | 2017 | Caldera | 299314.8 | 2017 | 3102 | 17662 | 5286498241 | Urbano |
| 03103 | 1 | 136 | 2017 | 2 | 1398 | 2017 | 3 | 572 | 2017 | 4 | 452 | 2017 | 5 | 289 | 2017 | 6 | 17 | 2017 | Tierra Amarilla | 315860.6 | 2017 | 3103 | 14019 | 4428049932 | Urbano |
| 03201 | 1 | 301 | 2017 | 2 | 1685 | 2017 | 3 | 932 | 2017 | 4 | 276 | 2017 | 5 | 8 | 2017 | 6 | 64 | 2017 | Chañaral | 286389.3 | 2017 | 3201 | 12219 | 3499391196 | Urbano |
| 03202 | 1 | 367 | 2017 | 2 | 2575 | 2017 | 3 | 808 | 2017 | 4 | 240 | 2017 | 5 | 237 | 2017 | 6 | 15 | 2017 | Diego de Almagro | 325861.5 | 2017 | 3202 | 13925 | 4537621312 | Urbano |
| 03301 | 1 | 2766 | 2017 | 2 | 7904 | 2017 | 3 | 1706 | 2017 | 4 | 663 | 2017 | 5 | 597 | 2017 | 6 | 124 | 2017 | Vallenar | 311577.0 | 2017 | 3301 | 51917 | 16176145007 | Urbano |
| 03303 | 1 | 167 | 2017 | 2 | 822 | 2017 | 3 | 203 | 2017 | 4 | 125 | 2017 | 5 | 58 | 2017 | 6 | 6 | 2017 | Freirina | 289049.9 | 2017 | 3303 | 7041 | 2035200054 | Urbano |
| 03304 | 1 | 417 | 2017 | 2 | 1661 | 2017 | 3 | 484 | 2017 | 4 | 227 | 2017 | 5 | 32 | 2017 | 6 | 12 | 2017 | Huasco | 337414.8 | 2017 | 3304 | 10149 | 3424422750 | Urbano |
| 04101 | 1 | 17322 | 2017 | 2 | 37330 | 2017 | 3 | 4360 | 2017 | 4 | 1228 | 2017 | 5 | 1202 | 2017 | 6 | 83 | 2017 | La Serena | 272136.8 | 2017 | 4101 | 221054 | 60156924947 | Urbano |
| 04102 | 1 | 12698 | 2017 | 2 | 41382 | 2017 | 3 | 5276 | 2017 | 4 | 1780 | 2017 | 5 | 2045 | 2017 | 6 | 125 | 2017 | Coquimbo | 264340.0 | 2017 | 4102 | 227730 | 60198159091 | Urbano |
| 04103 | 1 | 151 | 2017 | 2 | 1582 | 2017 | 3 | 511 | 2017 | 4 | 191 | 2017 | 5 | 599 | 2017 | 6 | 17 | 2017 | Andacollo | 251267.7 | 2017 | 4103 | 11044 | 2775000288 | Urbano |
| 04104 | 1 | 14 | 2017 | 2 | 30 | 2017 | 3 | 250 | 2017 | 4 | 77 | 2017 | 5 | 20 | 2017 | 6 | 2 | 2017 | La Higuera | 214257.0 | 2017 | 4104 | 4241 | 908664019 | Urbano |
| 04106 | 1 | 315 | 2017 | 2 | 3802 | 2017 | 3 | 506 | 2017 | 4 | 203 | 2017 | 5 | 511 | 2017 | 6 | 17 | 2017 | Vicuña | 245957.4 | 2017 | 4106 | 27771 | 6830481918 | Urbano |
| 04201 | 1 | 420 | 2017 | 2 | 4315 | 2017 | 3 | 1368 | 2017 | 4 | 487 | 2017 | 5 | 165 | 2017 | 6 | 15 | 2017 | Illapel | 270316.5 | 2017 | 4201 | 30848 | 8338722128 | Urbano |
| 04202 | 1 | 13 | 2017 | 2 | 336 | 2017 | 3 | 132 | 2017 | 4 | 43 | 2017 | 5 | 174 | 2017 | NA | NA | NA | Canela | 233397.3 | 2017 | 4202 | 9093 | 2122281844 | Urbano |
| 04203 | 1 | 418 | 2017 | 2 | 3490 | 2017 | 3 | 1272 | 2017 | 4 | 417 | 2017 | 5 | 165 | 2017 | 6 | 6 | 2017 | Los Vilos | 282415.6 | 2017 | 4203 | 21382 | 6038609501 | Urbano |
| 04204 | 1 | 264 | 2017 | 2 | 3302 | 2017 | 3 | 906 | 2017 | 4 | 367 | 2017 | 5 | 136 | 2017 | 6 | 21 | 2017 | Salamanca | 262056.9 | 2017 | 4204 | 29347 | 7690585032 | Urbano |
| 04301 | 1 | 2670 | 2017 | 2 | 20451 | 2017 | 3 | 1946 | 2017 | 4 | 814 | 2017 | 5 | 764 | 2017 | 6 | 47 | 2017 | Ovalle | 274771.4 | 2017 | 4301 | 111272 | 30574361012 | Urbano |
| 04302 | 1 | 42 | 2017 | 2 | 1329 | 2017 | 3 | 201 | 2017 | 4 | 66 | 2017 | 5 | 441 | 2017 | 6 | 9 | 2017 | Combarbalá | 228990.4 | 2017 | 4302 | 13322 | 3050610572 | Urbano |
| 04303 | 1 | 160 | 2017 | 2 | 2526 | 2017 | 3 | 1194 | 2017 | 4 | 536 | 2017 | 5 | 368 | 2017 | 6 | 22 | 2017 | Monte Patria | 225369.1 | 2017 | 4303 | 30751 | 6930326684 | Urbano |
| 04304 | 1 | 27 | 2017 | 2 | 1373 | 2017 | 3 | 277 | 2017 | 4 | 103 | 2017 | 5 | 114 | 2017 | 6 | 14 | 2017 | Punitaqui | 212496.1 | 2017 | 4304 | 10956 | 2328107498 | Urbano |
| 05101 | 1 | 26836 | 2017 | 2 | 31126 | 2017 | 3 | 22899 | 2017 | 4 | 6249 | 2017 | 5 | 8842 | 2017 | 6 | 976 | 2017 | Valparaíso | 297929.0 | 2017 | 5101 | 296655 | 88382118059 | Urbano |
| 05102 | 1 | 595 | 2017 | 2 | 3472 | 2017 | 3 | 1154 | 2017 | 4 | 313 | 2017 | 5 | 165 | 2017 | 6 | 14 | 2017 | Casablanca | 341641.8 | 2017 | 5102 | 26867 | 9178890241 | Urbano |
| 05103 | 1 | 4892 | 2017 | 2 | 3646 | 2017 | 3 | 3629 | 2017 | 4 | 660 | 2017 | 5 | 37 | 2017 | 6 | 22 | 2017 | Concón | 318496.3 | 2017 | 5103 | 42152 | 13425257057 | Urbano |
| 05105 | 1 | 358 | 2017 | 2 | 1442 | 2017 | 3 | 2834 | 2017 | 4 | 677 | 2017 | 5 | 52 | 2017 | 6 | 18 | 2017 | Puchuncaví | 296035.5 | 2017 | 5105 | 18546 | 5490274928 | Urbano |
| 05107 | 1 | 1365 | 2017 | 2 | 3583 | 2017 | 3 | 2890 | 2017 | 4 | 841 | 2017 | 5 | 43 | 2017 | 6 | 31 | 2017 | Quintero | 308224.7 | 2017 | 5107 | 31923 | 9839456903 | Urbano |
| 05109 | 1 | 48422 | 2017 | 2 | 36723 | 2017 | 3 | 22227 | 2017 | 4 | 5973 | 2017 | 5 | 1888 | 2017 | 6 | 576 | 2017 | Viña del Mar | 337006.1 | 2017 | 5109 | 334248 | 112643604611 | Urbano |
| 05201 | 1 | 265 | 2017 | 2 | 619 | 2017 | 3 | 1221 | 2017 | 4 | 153 | 2017 | 5 | 12 | 2017 | 6 | 22 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 05301 | 1 | 3217 | 2017 | 2 | 13881 | 2017 | 3 | 1002 | 2017 | 4 | 288 | 2017 | 5 | 877 | 2017 | 6 | 39 | 2017 | Los Andes | 339720.2 | 2017 | 5301 | 66708 | 22662055502 | Urbano |
| 05302 | 1 | 421 | 2017 | 2 | 2119 | 2017 | 3 | 451 | 2017 | 4 | 163 | 2017 | 5 | 176 | 2017 | 6 | 4 | 2017 | Calle Larga | 246387.3 | 2017 | 5302 | 14832 | 3654416747 | Urbano |
| 05303 | 1 | 165 | 2017 | 2 | 1763 | 2017 | 3 | 312 | 2017 | 4 | 110 | 2017 | 5 | 132 | 2017 | 6 | 2 | 2017 | Rinconada | 273904.7 | 2017 | 5303 | 10207 | 2795744821 | Urbano |
| 05304 | 1 | 478 | 2017 | 2 | 2602 | 2017 | 3 | 345 | 2017 | 4 | 81 | 2017 | 5 | 135 | 2017 | 6 | 2 | 2017 | San Esteban | 219571.6 | 2017 | 5304 | 18855 | 4140022481 | Urbano |
| 05401 | 1 | 662 | 2017 | 2 | 4371 | 2017 | 3 | 2591 | 2017 | 4 | 826 | 2017 | 5 | 106 | 2017 | 6 | 21 | 2017 | La Ligua | 250134.4 | 2017 | 5401 | 35390 | 8852256241 | Urbano |
| 05402 | 1 | 222 | 2017 | 2 | 1980 | 2017 | 3 | 1204 | 2017 | 4 | 353 | 2017 | 5 | 71 | 2017 | 6 | 5 | 2017 | Cabildo | 262745.9 | 2017 | 5402 | 19388 | 5094117762 | Urbano |
| 05403 | 1 | 147 | 2017 | 2 | 266 | 2017 | 3 | 1176 | 2017 | 4 | 154 | 2017 | 5 | 12 | 2017 | 6 | 2 | 2017 | Papudo | 294355.2 | 2017 | 5403 | 6356 | 1870921373 | Urbano |
| 05404 | 1 | 72 | 2017 | 2 | 600 | 2017 | 3 | 492 | 2017 | 4 | 181 | 2017 | 5 | 83 | 2017 | 6 | 2 | 2017 | Petorca | 237510.8 | 2017 | 5404 | 9826 | 2333781007 | Urbano |
| 05405 | 1 | 149 | 2017 | 2 | 572 | 2017 | 3 | 783 | 2017 | 4 | 133 | 2017 | 5 | 21 | 2017 | 6 | 2 | 2017 | Zapallar | 294389.2 | 2017 | 5405 | 7339 | 2160521991 | Urbano |
| 05501 | 1 | 4613 | 2017 | 2 | 16370 | 2017 | 3 | 2507 | 2017 | 4 | 851 | 2017 | 5 | 607 | 2017 | 6 | 39 | 2017 | Quillota | 286029.5 | 2017 | 5501 | 90517 | 25890529852 | Urbano |
names(df_2017_2)[3] <- "Hormigón"
names(df_2017_2)[6] <- "Albañilería"
names(df_2017_2)[9] <- "Tabique forrado"
names(df_2017_2)[12] <- "Tabique sin forro"
names(df_2017_2)[15] <- "Adobe"
names(df_2017_2)[18] <- "Materiales precarios"1.2 Correlaciones
1.2.1 Pearson
El coeficiente de correlación de Pearson es probablemente la medida más utilizada para las relaciones lineales entre dos variables distribuidas normales y, por lo tanto, a menudo se denomina simplemente “coeficiente de correlación”. Por lo general, el coeficiente de Pearson se obtiene mediante un ajuste de mínimos cuadrados y un valor de 1 representa una relación positiva perfecta, -1 una relación negativa perfecta y 0 indica la ausencia de una relación entre las variables.
\[ \rho = \frac{\text{cov}(X,Y)}{\sigma_x \sigma_y} codigos <- d_t \] \[ r = \frac{{}\sum_{i=1}^{n} (x_i - \overline{x})(y_i - \overline{y})} {\sqrt{\sum_{i=1}^{n} (x_i - \overline{x})^2(y_i - \overline{y})^2}} \]
III <- seq(3,18,3)
my_data <- df_2017_2[, c(III,ncol(df_2017_2)-1)]
chart.Correlation(my_data, histogram=TRUE, method = c( "pearson"), pch=20)
1.2.2 Spearman
Relacionado con el coeficiente de correlación de Pearson, el coeficiente de correlación de Spearman (rho) mide la relación entre dos variables. La rho de Spearman puede entenderse como una versión basada en rangos del coeficiente de correlación de Pearson, que se puede utilizar para variables que no tienen una distribución normal y tienen una relación no lineal. Además, su uso no solo está restringido a datos continuos, sino que también puede usarse en análisis de atributos ordinales.
\[ \rho = 1- {\frac {6 \sum d_i^2}{n(n^2 - 1)}} \]
III <- seq(3,18,3)
my_data <- df_2017_2[, c(III,ncol(df_2017_2)-1)]
chart.Correlation(my_data, histogram=TRUE, method = c( "spearman"), pch=20)
1.2.3 Kendall
Similar al coeficiente de correlación de Pearson, la tau de Kendall mide el grado de una relación monótona entre variables y, como la rho de Spearman, calcula la dependencia entre variables clasificadas, lo que hace que sea factible para datos distribuidos no normales. Kendall tau se puede calcular tanto para datos continuos como ordinales. En términos generales, la tau de Kendall se distingue de la rho de Spearman por una penalización más fuerte de las dislocaciones no secuenciales (en el contexto de las variables clasificadas).
\[ \tau = \frac{c-d}{c+d} = \frac{S}{ \left( \begin{matrix} n \\ 2 \end{matrix} \right)} = \frac{2S}{n(n-1)} \]
\[\tau = \frac{S}{\sqrt{n(n-1)/2-T}\sqrt{n(n-1)/2-U}} \\ \\ T = \sum_t t(t-1)/2 \\ \\ U = \sum_u u(u-1)/2 \\\]
III <- seq(3,18,3)
my_data <- df_2017_2[, c(III,ncol(df_2017_2)-1)]
chart.Correlation(my_data, histogram=TRUE, method = c( "kendall"), pch=20)
RURAL
2 Pregunta P03A: Material de los muros exteriores
Ésta pregunta posee 6 categorías de respuesta:
1 Hormigón armado
2 Albañilería: bloque de cemento, piedra o ladrillo
3 Tabique forrado por ambas caras (madera o acero)
4 Tabique sin forro interior (madera u otro)
5 Adobe, barro, quincha, pirca u otro artesanal tradicional
6 Materiales precarios (lata, cartón, plástico, etc.)
98 No aplica
99 Missing
2.1 Cálculo de frecuencias
Leemos las respuestas a la pregunta P03A del censo de viviendas 2017 y obtenemos la tabla de frecuencias por categoría de respuesta:
tabla_con_clave <- readRDS("../censo_viviendas_con_clave_17.rds")
tabla_con_clave <- filter(tabla_con_clave, tabla_con_clave$AREA == 2)
b <- tabla_con_clave$COMUNA
c <- tabla_con_clave$P03A
cross_tab = xtabs( ~ unlist(b) + unlist(c))
tabla <- as.data.frame(cross_tab)
d <-tabla[!(tabla$Freq == 0),]
d$anio <- "2017"
d_t <- filter(d,d$unlist.c. == 1)
for(i in 2:6){
d_i <- filter(d,d$unlist.c. == i)
d_t = merge( x = d_t, y = d_i, by = "unlist.b.", all.x = TRUE)
}
codigos <- d_t$unlist.b.
rango <- seq(1:nrow(d_t))
cadena <- paste("0",codigos[rango], sep = "")
cadena <- substr(cadena,(nchar(cadena)[rango])-(4),6)
codigos <- as.data.frame(codigos)
cadena <- as.data.frame(cadena)
comuna_corr <- cbind(d_t,cadena)
comuna_corr <- comuna_corr[,-c(1),drop=FALSE]
names(comuna_corr)[19] <- "código"
ingresos_expandidos_2017 <- readRDS("ingresos_expandidos_17_rural_nacional.rds")
df_2017_2 = merge( x = comuna_corr, y = ingresos_expandidos_2017, by = "código", all.x = TRUE)
tablamadre <- head(df_2017_2,50)
kbl(tablamadre) %>%
kable_styling(bootstrap_options = c("striped", "hover")) %>%
kable_paper() %>%
scroll_box(width = "100%", height = "300px")| código | unlist.c..x | Freq.x | anio.x | unlist.c..y | Freq.y | anio.y | unlist.c..x.1 | Freq.x.1 | anio.x.1 | unlist.c..y.1 | Freq.y.1 | anio.y.1 | unlist.c..x.2 | Freq.x.2 | anio.x.2 | unlist.c..y.2 | Freq.y.2 | anio.y.2 | comuna.x | promedio_i | año | comuna.y | personas | Ingresos_expandidos | tipo |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 01101 | 1 | 51 | 2017 | 2 | 127 | 2017 | 3 | 295 | 2017 | 4 | 250 | 2017 | 5 | 7 | 2017 | 6 | 39 | 2017 | Iquique | 289375.3 | 2017 | 1101 | 191468 | 55406102543 | Rural |
| 01107 | 1 | 7 | 2017 | NA | NA | NA | 3 | 8 | 2017 | 4 | 13 | 2017 | 5 | 2 | 2017 | 6 | 15 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 01401 | 1 | 151 | 2017 | 2 | 417 | 2017 | 3 | 399 | 2017 | 4 | 254 | 2017 | 5 | 67 | 2017 | 6 | 51 | 2017 | Pozo Almonte | 263069.6 | 2017 | 1401 | 15711 | 4133086727 | Rural |
| 01402 | 1 | 25 | 2017 | 2 | 252 | 2017 | 3 | 77 | 2017 | 4 | 84 | 2017 | 5 | 28 | 2017 | 6 | 1 | 2017 | Camiña | 262850.3 | 2017 | 1402 | 1250 | 328562901 | Rural |
| 01403 | 1 | 6 | 2017 | 2 | 48 | 2017 | 3 | 10 | 2017 | 4 | 6 | 2017 | 5 | 393 | 2017 | 6 | 2 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 01404 | 1 | 64 | 2017 | 2 | 183 | 2017 | 3 | 125 | 2017 | 4 | 139 | 2017 | 5 | 46 | 2017 | 6 | 30 | 2017 | Huara | 253968.5 | 2017 | 1404 | 2730 | 693334131 | Rural |
| 01405 | 1 | 26 | 2017 | 2 | 93 | 2017 | 3 | 106 | 2017 | 4 | 72 | 2017 | 5 | 23 | 2017 | 6 | 6 | 2017 | Pica | 290496.7 | 2017 | 1405 | 9296 | 2700457509 | Rural |
| 02101 | 1 | 28 | 2017 | 2 | 64 | 2017 | 3 | 81 | 2017 | 4 | 99 | 2017 | 5 | 3 | 2017 | 6 | 37 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 02102 | 1 | 13 | 2017 | 2 | 39 | 2017 | 3 | 53 | 2017 | 4 | 22 | 2017 | NA | NA | NA | 6 | 10 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 02103 | 1 | 34 | 2017 | 2 | 123 | 2017 | 3 | 107 | 2017 | 4 | 58 | 2017 | 5 | 9 | 2017 | 6 | 9 | 2017 | Sierra Gorda | 403458.5 | 2017 | 2103 | 10186 | 4109628188 | Rural |
| 02104 | 1 | 10 | 2017 | 2 | 58 | 2017 | 3 | 100 | 2017 | 4 | 97 | 2017 | 5 | 10 | 2017 | 6 | 24 | 2017 | Taltal | 345494.0 | 2017 | 2104 | 13317 | 4600943086 | Rural |
| 02201 | 1 | 83 | 2017 | 2 | 239 | 2017 | 3 | 320 | 2017 | 4 | 171 | 2017 | 5 | 90 | 2017 | 6 | 54 | 2017 | Calama | 310025.0 | 2017 | 2201 | 165731 | 51380756402 | Rural |
| 02203 | 1 | 73 | 2017 | 2 | 687 | 2017 | 3 | 111 | 2017 | 4 | 39 | 2017 | 5 | 406 | 2017 | 6 | 14 | 2017 | San Pedro de Atacama | 356147.9 | 2017 | 2203 | 10996 | 3916202829 | Rural |
| 02301 | 1 | 3 | 2017 | 2 | 5 | 2017 | 3 | 100 | 2017 | 4 | 80 | 2017 | 5 | 5 | 2017 | 6 | 17 | 2017 | Tocopilla | 180218.1 | 2017 | 2301 | 25186 | 4538972205 | Rural |
| 02302 | 1 | 6 | 2017 | 2 | 18 | 2017 | 3 | 14 | 2017 | 4 | 9 | 2017 | 5 | 9 | 2017 | 6 | 2 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 03101 | 1 | 78 | 2017 | 2 | 213 | 2017 | 3 | 366 | 2017 | 4 | 213 | 2017 | 5 | 52 | 2017 | 6 | 34 | 2017 | Copiapó | 308502.8 | 2017 | 3101 | 153937 | 47489990283 | Rural |
| 03102 | 1 | 48 | 2017 | 2 | 83 | 2017 | 3 | 392 | 2017 | 4 | 210 | 2017 | 5 | 14 | 2017 | 6 | 43 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 03103 | 1 | 20 | 2017 | 2 | 195 | 2017 | 3 | 325 | 2017 | 4 | 231 | 2017 | 5 | 137 | 2017 | 6 | 19 | 2017 | Tierra Amarilla | 312457.3 | 2017 | 3103 | 14019 | 4380339153 | Rural |
| 03201 | 1 | 21 | 2017 | 2 | 114 | 2017 | 3 | 160 | 2017 | 4 | 80 | 2017 | 5 | 4 | 2017 | 6 | 31 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 03202 | 1 | 14 | 2017 | 2 | 19 | 2017 | 3 | 90 | 2017 | 4 | 38 | 2017 | 5 | 48 | 2017 | 6 | 38 | 2017 | Diego de Almagro | 374511.6 | 2017 | 3202 | 13925 | 5215073473 | Rural |
| 03301 | 1 | 124 | 2017 | 2 | 417 | 2017 | 3 | 692 | 2017 | 4 | 408 | 2017 | 5 | 212 | 2017 | 6 | 62 | 2017 | Vallenar | 254290.6 | 2017 | 3301 | 51917 | 13202005308 | Rural |
| 03302 | 1 | 109 | 2017 | 2 | 681 | 2017 | 3 | 354 | 2017 | 4 | 207 | 2017 | 5 | 371 | 2017 | 6 | 21 | 2017 | Alto del Carmen | 227130.4 | 2017 | 3302 | 5299 | 1203563833 | Rural |
| 03303 | 1 | 38 | 2017 | 2 | 226 | 2017 | 3 | 317 | 2017 | 4 | 198 | 2017 | 5 | 64 | 2017 | 6 | 25 | 2017 | Freirina | 214803.3 | 2017 | 3303 | 7041 | 1512429891 | Rural |
| 03304 | 1 | 26 | 2017 | 2 | 84 | 2017 | 3 | 172 | 2017 | 4 | 169 | 2017 | 5 | 24 | 2017 | 6 | 22 | 2017 | Huasco | 227560.7 | 2017 | 3304 | 10149 | 2309513927 | Rural |
| 04101 | 1 | 484 | 2017 | 2 | 1428 | 2017 | 3 | 2538 | 2017 | 4 | 963 | 2017 | 5 | 298 | 2017 | 6 | 37 | 2017 | La Serena | 233184.2 | 2017 | 4101 | 221054 | 51546306303 | Rural |
| 04102 | 1 | 209 | 2017 | 2 | 1149 | 2017 | 3 | 1898 | 2017 | 4 | 601 | 2017 | 5 | 173 | 2017 | 6 | 40 | 2017 | Coquimbo | 231810.7 | 2017 | 4102 | 227730 | 52790242466 | Rural |
| 04103 | 1 | 8 | 2017 | 2 | 56 | 2017 | 3 | 174 | 2017 | 4 | 101 | 2017 | 5 | 66 | 2017 | 6 | 5 | 2017 | Andacollo | 242908.2 | 2017 | 4103 | 11044 | 2682678345 | Rural |
| 04104 | 1 | 34 | 2017 | 2 | 230 | 2017 | 3 | 508 | 2017 | 4 | 205 | 2017 | 5 | 64 | 2017 | 6 | 22 | 2017 | La Higuera | 250699.6 | 2017 | 4104 | 4241 | 1063217069 | Rural |
| 04105 | 1 | 59 | 2017 | 2 | 601 | 2017 | 3 | 334 | 2017 | 4 | 161 | 2017 | 5 | 428 | 2017 | 6 | 13 | 2017 | Paiguano | 205942.1 | 2017 | 4105 | 4497 | 926121774 | Rural |
| 04106 | 1 | 300 | 2017 | 2 | 1214 | 2017 | 3 | 968 | 2017 | 4 | 399 | 2017 | 5 | 442 | 2017 | 6 | 34 | 2017 | Vicuña | 176130.6 | 2017 | 4106 | 27771 | 4891322768 | Rural |
| 04201 | 1 | 93 | 2017 | 2 | 1339 | 2017 | 3 | 1284 | 2017 | 4 | 478 | 2017 | 5 | 169 | 2017 | 6 | 6 | 2017 | Illapel | 191976.8 | 2017 | 4201 | 30848 | 5922099530 | Rural |
| 04202 | 1 | 43 | 2017 | 2 | 925 | 2017 | 3 | 761 | 2017 | 4 | 394 | 2017 | 5 | 541 | 2017 | 6 | 19 | 2017 | Canela | 171370.3 | 2017 | 4202 | 9093 | 1558270441 | Rural |
| 04203 | 1 | 60 | 2017 | 2 | 350 | 2017 | 3 | 708 | 2017 | 4 | 226 | 2017 | 5 | 87 | 2017 | 6 | 5 | 2017 | Los Vilos | 173238.5 | 2017 | 4203 | 21382 | 3704185607 | Rural |
| 04204 | 1 | 89 | 2017 | 2 | 1588 | 2017 | 3 | 1271 | 2017 | 4 | 516 | 2017 | 5 | 195 | 2017 | 6 | 32 | 2017 | Salamanca | 223234.2 | 2017 | 4204 | 29347 | 6551254640 | Rural |
| 04301 | 1 | 339 | 2017 | 2 | 2479 | 2017 | 3 | 2721 | 2017 | 4 | 1436 | 2017 | 5 | 827 | 2017 | 6 | 58 | 2017 | Ovalle | 241393.7 | 2017 | 4301 | 111272 | 26860360045 | Rural |
| 04302 | 1 | 61 | 2017 | 2 | 1000 | 2017 | 3 | 658 | 2017 | 4 | 411 | 2017 | 5 | 617 | 2017 | 6 | 31 | 2017 | Combarbalá | 179139.6 | 2017 | 4302 | 13322 | 2386498044 | Rural |
| 04303 | 1 | 143 | 2017 | 2 | 2074 | 2017 | 3 | 1157 | 2017 | 4 | 833 | 2017 | 5 | 1144 | 2017 | 6 | 43 | 2017 | Monte Patria | 201205.8 | 2017 | 4303 | 30751 | 6187280931 | Rural |
| 04304 | 1 | 52 | 2017 | 2 | 593 | 2017 | 3 | 508 | 2017 | 4 | 410 | 2017 | 5 | 245 | 2017 | 6 | 23 | 2017 | Punitaqui | 171931.7 | 2017 | 4304 | 10956 | 1883683880 | Rural |
| 04305 | 1 | 37 | 2017 | 2 | 720 | 2017 | 3 | 269 | 2017 | 4 | 93 | 2017 | 5 | 547 | 2017 | 6 | 14 | 2017 | Río Hurtado | 182027.2 | 2017 | 4305 | 4278 | 778712384 | Rural |
| 05101 | 1 | 9 | 2017 | 2 | 21 | 2017 | 3 | 139 | 2017 | 4 | 82 | 2017 | 5 | 20 | 2017 | 6 | 7 | 2017 | Valparaíso | 331716.1 | 2017 | 5101 | 296655 | 98405237576 | Rural |
| 05102 | 1 | 177 | 2017 | 2 | 430 | 2017 | 3 | 1757 | 2017 | 4 | 430 | 2017 | 5 | 136 | 2017 | 6 | 19 | 2017 | Casablanca | 268917.1 | 2017 | 5102 | 26867 | 7224996933 | Rural |
| 05103 | 1 | 25 | 2017 | 2 | 121 | 2017 | 3 | 555 | 2017 | 4 | 71 | 2017 | 5 | 5 | 2017 | 6 | 2 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 05104 | 1 | 4 | 2017 | 2 | 6 | 2017 | 3 | 311 | 2017 | 4 | 27 | 2017 | 5 | 1 | 2017 | 6 | 2 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 05105 | 1 | 39 | 2017 | 2 | 102 | 2017 | 3 | 654 | 2017 | 4 | 143 | 2017 | 5 | 23 | 2017 | 6 | 8 | 2017 | Puchuncaví | 279614.4 | 2017 | 5105 | 18546 | 5185728335 | Rural |
| 05107 | 1 | 208 | 2017 | 2 | 236 | 2017 | 3 | 941 | 2017 | 4 | 183 | 2017 | 5 | 26 | 2017 | 6 | 7 | 2017 | Quintero | 334628.2 | 2017 | 5107 | 31923 | 10682335196 | Rural |
| 05201 | 1 | 13 | 2017 | 2 | 43 | 2017 | 3 | 74 | 2017 | 4 | 9 | 2017 | 5 | 2 | 2017 | 6 | 1 | 2017 | NA | NA | NA | NA | NA | NA | NA |
| 05301 | 1 | 47 | 2017 | 2 | 335 | 2017 | 3 | 520 | 2017 | 4 | 172 | 2017 | 5 | 142 | 2017 | 6 | 5 | 2017 | Los Andes | 324402.1 | 2017 | 5301 | 66708 | 21640215030 | Rural |
| 05302 | 1 | 93 | 2017 | 2 | 557 | 2017 | 3 | 339 | 2017 | 4 | 143 | 2017 | 5 | 179 | 2017 | 6 | 6 | 2017 | Calle Larga | 242743.8 | 2017 | 5302 | 14832 | 3600375502 | Rural |
| 05303 | 1 | 85 | 2017 | 2 | 261 | 2017 | 3 | 184 | 2017 | 4 | 57 | 2017 | 5 | 70 | 2017 | 6 | 6 | 2017 | Rinconada | 326532.5 | 2017 | 5303 | 10207 | 3332917471 | Rural |
| 05304 | 1 | 101 | 2017 | 2 | 781 | 2017 | 3 | 852 | 2017 | 4 | 311 | 2017 | 5 | 373 | 2017 | 6 | 9 | 2017 | San Esteban | 223168.6 | 2017 | 5304 | 18855 | 4207844130 | Rural |
names(df_2017_2)[3] <- "Hormigón"
names(df_2017_2)[6] <- "Albañilería"
names(df_2017_2)[9] <- "Tabique forrado"
names(df_2017_2)[12] <- "Tabique sin forro"
names(df_2017_2)[15] <- "Adobe"
names(df_2017_2)[18] <- "Materiales precarios"2.2 Correlaciones
2.2.1Pearson
El coeficiente de correlación de Pearson es probablemente la medida más utilizada para las relaciones lineales entre dos variables distribuidas normales y, por lo tanto, a menudo se denomina simplemente “coeficiente de correlación”. Por lo general, el coeficiente de Pearson se obtiene mediante un ajuste de mínimos cuadrados y un valor de 1 representa una relación positiva perfecta, -1 una relación negativa perfecta y 0 indica la ausencia de una relación entre las variables.
\[ \rho = \frac{\text{cov}(X,Y)}{\sigma_x \sigma_y} codigos <- d_t \] \[ r = \frac{{}\sum_{i=1}^{n} (x_i - \overline{x})(y_i - \overline{y})} {\sqrt{\sum_{i=1}^{n} (x_i - \overline{x})^2(y_i - \overline{y})^2}} \]
III <- seq(3,18,3)
my_data <- df_2017_2[, c(III,ncol(df_2017_2)-1)]
chart.Correlation(my_data, histogram=TRUE, method = c( "pearson"), pch=20)
2.2.2 Spearman
Relacionado con el coeficiente de correlación de Pearson, el coeficiente de correlación de Spearman (rho) mide la relación entre dos variables. La rho de Spearman puede entenderse como una versión basada en rangos del coeficiente de correlación de Pearson, que se puede utilizar para variables que no tienen una distribución normal y tienen una relación no lineal. Además, su uso no solo está restringido a datos continuos, sino que también puede usarse en análisis de atributos ordinales.
\[ \rho = 1- {\frac {6 \sum d_i^2}{n(n^2 - 1)}} \]
III <- seq(3,18,3)
my_data <- df_2017_2[, c(III,ncol(df_2017_2)-1)]
chart.Correlation(my_data, histogram=TRUE, method = c( "spearman"), pch=20)
2.2.3 Kendall
Similar al coeficiente de correlación de Pearson, la tau de Kendall mide el grado de una relación monótona entre variables y, como la rho de Spearman, calcula la dependencia entre variables clasificadas, lo que hace que sea factible para datos distribuidos no normales. Kendall tau se puede calcular tanto para datos continuos como ordinales. En términos generales, la tau de Kendall se distingue de la rho de Spearman por una penalización más fuerte de las dislocaciones no secuenciales (en el contexto de las variables clasificadas).
\[ \tau = \frac{c-d}{c+d} = \frac{S}{ \left( \begin{matrix} n \\ 2 \end{matrix} \right)} = \frac{2S}{n(n-1)} \]
\[\tau = \frac{S}{\sqrt{n(n-1)/2-T}\sqrt{n(n-1)/2-U}} \\ \\ T = \sum_t t(t-1)/2 \\ \\ U = \sum_u u(u-1)/2 \\\]
III <- seq(3,18,3)
my_data <- df_2017_2[, c(III,ncol(df_2017_2)-1)]
chart.Correlation(my_data, histogram=TRUE, method = c( "kendall"), pch=20)