Votos a favor del Apruebo - Plebiscito Nacional Chileno
Column
Grafico de la VD
Reading layer `comunas' from data source
`C:\Users\USER\Desktop\ESTADISTICA 2\comunas.shp' using driver `ESRI Shapefile'
Simple feature collection with 346 features and 11 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: -12184470 ymin: -7554436 xmax: -7393642 ymax: -1978920
Projected CRS: WGS 84 / Pseudo-Mercator
Seccion 1: Regresion Gaussiana - Modelo 1
Column
Modelo 1
| Votos Aprueba (I) | |
|---|---|
| (Intercept) | 0.274+ |
| (0.153) | |
| FemeninoVotoP | 0.911** |
| (0.295) | |
| Voto18a24P | 0.070 |
| (0.060) | |
| Num.Obs. | 345 |
| R2 | 0.035 |
| R2 Adj. | 0.029 |
| AIC | -638.6 |
| BIC | -623.2 |
| Log.Lik. | 323.290 |
| F | 6.163 |
| RMSE | 0.09 |
| + p < 0.1, * p < 0.05, ** p < 0.01, *** p < 0.001 |
Column
Grafico de dispersion - Voto Femenino
Call:
lm(formula = votos_Aprueba ~ FemeninoVotoP, data = dataoficial)
Residuals:
Min 1Q Median 3Q Max
-0.47897 -0.05969 0.01575 0.06874 0.18275
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.2543 0.1526 1.667 0.09647 .
FemeninoVotoP 0.9641 0.2915 3.308 0.00104 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.09526 on 343 degrees of freedom
Multiple R-squared: 0.03092, Adjusted R-squared: 0.02809
F-statistic: 10.94 on 1 and 343 DF, p-value: 0.001039
Column
Grafico de Dispersion - Voto Joven
Call:
lm(formula = votos_Aprueba ~ Voto18a24P, data = dataoficial)
Residuals:
Min 1Q Median 3Q Max
-0.50378 -0.06351 0.01808 0.07221 0.15492
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.746632 0.008974 83.202 <2e-16 ***
Voto18a24P 0.098150 0.059578 1.647 0.1
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.09639 on 343 degrees of freedom
Multiple R-squared: 0.007851, Adjusted R-squared: 0.004958
F-statistic: 2.714 on 1 and 343 DF, p-value: 0.1004
Seccion 2: Regresion Gaussiana - Modelo 2
Column
Modelo 2
| Votos Apruebo (II) | |
|---|---|
| (Intercept) | 0.303+ |
| (0.157) | |
| FemeninoVotoP | 0.826** |
| (0.311) | |
| Voto18a24P | 0.068 |
| (0.060) | |
| IDC | 0.039 |
| (0.046) | |
| Num.Obs. | 345 |
| R2 | 0.037 |
| R2 Adj. | 0.028 |
| AIC | -637.3 |
| BIC | -618.1 |
| Log.Lik. | 323.656 |
| F | 4.347 |
| RMSE | 0.09 |
| + p < 0.1, * p < 0.05, ** p < 0.01, *** p < 0.001 |
Column
Grafico de Dispersion - Indice de Desarrollo Humano
Call:
lm(formula = votos_Aprueba ~ IDC, data = dataoficial)
Residuals:
Min 1Q Median 3Q Max
-0.49203 -0.06003 0.01742 0.06989 0.16255
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.72716 0.01735 41.918 <2e-16 ***
IDC 0.08321 0.04368 1.905 0.0576 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.09626 on 343 degrees of freedom
Multiple R-squared: 0.01047, Adjusted R-squared: 0.007583
F-statistic: 3.629 on 1 and 343 DF, p-value: 0.05763
Seccion 3: Regresion Gaussiana - Modelo 3
Column
Modelo 3
| Votos Apruebo (III) | |
|---|---|
| (Intercept) | 0.925*** |
| (0.098) | |
| FemeninoVotoP | 0.584** |
| (0.187) | |
| Voto18a24P | 0.070+ |
| (0.036) | |
| IDC | 0.013 |
| (0.028) | |
| votos_Sebastian | -0.887*** |
| (0.036) | |
| Num.Obs. | 345 |
| R2 | 0.653 |
| R2 Adj. | 0.649 |
| AIC | -987.8 |
| BIC | -964.8 |
| Log.Lik. | 499.907 |
| F | 160.163 |
| RMSE | 0.06 |
| + p < 0.1, * p < 0.05, ** p < 0.01, *** p < 0.001 |
Column
Grafico de Dispersion - Votos a Piñera
Call:
lm(formula = votos_Aprueba ~ votos_Sebastian, data = dataoficial)
Residuals:
Min 1Q Median 3Q Max
-0.183033 -0.038243 0.000382 0.043542 0.135441
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.25009 0.02039 61.31 <2e-16 ***
votos_Sebastian -0.89688 0.03677 -24.39 <2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.05852 on 343 degrees of freedom
Multiple R-squared: 0.6343, Adjusted R-squared: 0.6333
F-statistic: 595 on 1 and 343 DF, p-value: < 2.2e-16
Seccion 4: Eleccion de mejor modelo
Column
Eligiendo el mejor modelo
Column
Prueba ANOVA
| Res.Df | RSS | Df | Sum of Sq | F | Pr(>F) |
|---|---|---|---|---|---|
| 342 | 3.100371 | NA | NA | NA | NA |
| 341 | 3.093798 | 1 | 0.0065724 | 2.006548 | 0.1575369 |
| 340 | 1.113666 | 1 | 1.9801324 | 604.530456 | 0.0000000 |
Column
Linealidad
Se elige el modelo 3 como mejor modelo
Column
Homocedasticidad
Se elige el modelo 3 como mejor modelo
Column
Tambien se puede evaluar de otra forma
| BP | df | p.value | |
|---|---|---|---|
| BP | 24.20604 | 4 | 7.26e-05 |
Column
Normalidad de los residuos
Se elige el modelo 3 como mejor modelo
Column
Tambien se puede aplicar la prueba Shapiro
| SW | p.value | |
|---|---|---|
| W | 0.9912576 | 0.0389324 |
Column
No multicolinelidad
Se elige el modelo 3 como mejor modelo
| VIF | |
|---|---|
| FemeninoVotoP | 1.143930 |
| Voto18a24P | 1.025662 |
| IDC | 1.122967 |
| votos_Sebastian | 1.006237 |
Column
Valores Influyentes
Se elige el modelo 3 como mejor modelo
Column
Indice Cook
| cook.d | hat | |
|---|---|---|
| 132 | TRUE | TRUE |
Column
Seccion 6: CLUSTERIZACION - PAM
Column
[1] "Comuna" "total_votos2020" "votos_aprobacion1"
[4] "votos_Aprueba" "total_votos2017" "votos_candidato1"
[7] "votos_Sebastian" "FemeninoVotoP" "Voto18a24P"
[10] "TotalVotacion" "FemeninoPadronP" "de18a24Padron"
[13] "totalPadron" "BIENESTAR" "ECONOMÍA"
[16] "EDUCACIÓN" "IDC" "RANKING"
[19] "RANGOS" Column
Prueba PAM
Column
Evaluando el uso de PAM
Column
Datos mal clusterizados
[1] "ANGOL" "CABRERO" "CISNES" "COLBUN" "COMBARBALA"
[6] "CONCON" "LA UNION" "LAJA" "MALLOA" "MARCHIGUE"
[11] "MONTE PATRIA" "PAIHUANO" "PALMILLA" "PARRAL" "PICA"
[16] "PROVIDENCIA" "RAUCO" "RIO CLARO" "SAN JAVIER" "SAN ROSENDO"
[21] "SIERRA GORDA" "TEMUCO" "TUCAPEL" "VITACURA" "ZAPALLAR" Seccion 6: CLUSTERIZACION - AGNES
Column
Prueba AGNES
Column
Dendograma que muestra el proceso de conglomeración AGNES:
Column
Evaluando el uso de AGNES
Column
Datos mal clusterizados
[1] "ALHUE" "ANDACOLLO" "ANGOL"
[4] "CABRERO" "CARTAGENA" "CATEMU"
[7] "CHANARAL" "COLINA" "EL QUISCO"
[10] "HUASCO" "ILLAPEL" "ISLA DE PASCUA"
[13] "LAJA" "LITUECHE" "LOS ALAMOS"
[16] "LOS ANGELES" "LOS VILOS" "MALLOA"
[19] "MARCHIGUE" "MULCHEN" "PALMILLA"
[22] "PARRAL" "PERALILLO" "PETORCA"
[25] "PEUMO" "PICHIDEGUA" "PUCHUNCAVI"
[28] "PUERTO VARAS" "PURRANQUE" "PUTAENDO"
[31] "QUIRIHUE" "SALAMANCA" "SAN CARLOS"
[34] "SAN JAVIER" "SAN NICOLAS" "SAN PEDRO DE ATACAMA"
[37] "SAN ROSENDO" "SIERRA GORDA" "TALTAL"
[40] "TORTEL" "VICUNA" "YUNGAY"
[43] "ZAPALLAR" Seccion 7: CLUSTERIZACION - DIANA
Column
Prueba DIANA
Column
Dendograma que muestra el proceso de conglomeración DIANA:
Column
Datos mal clusterizados
character(0)Seccion 8: CLUSTERIZACION - VISUALIZACION COMPARATIVA
Column
[,1] [,2]
ALGARROBO -0.05351684 0.090476193
ALHUE 0.06614413 -0.169598200
ALTO BIOBIO -0.27828509 0.002421128
ALTO DEL CARMEN -0.12652276 -0.104684011
ALTO HOSPICIO 0.05214483 0.009482302
ANCUD 0.03300428 -0.041236179
ANDACOLLO 0.04097558 -0.158135464
ANGOL 0.01547977 0.200482462
ANTOFAGASTA 0.21588830 0.053617326
ANTUCO -0.12307575 -0.008673436
ARAUCO 0.05832798 0.067135380
ARICA 0.17308676 0.060055528
AYSEN 0.13632040 -0.040449064
BUIN 0.08250395 0.064024025
BULNES -0.06175024 0.052392343
CABILDO 0.15224084 -0.124254875
CABO DE HORNOS(EX-NAVARINO) -0.13199902 0.119755829
CABRERO -0.01854573 0.093571776
CALAMA 0.09689059 0.068850997
CALBUCO -0.10100963 -0.026863952Column
Mapa
Column
Prueba PAM
