library(rio)#PREGUNTA 1
library(readr)
data <- read_csv("V-Dem-2024 - V-Dem-2024.csv")## Rows: 179 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): country_name
## dbl (5): v2x_polyarchy, v2x_liberal, v2x_partip, v2xdl_delib, v2x_egal
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(data)Electoral democracy index (v2x_polyarchy)
Liberal component index (v2x_liberal)
Participatory component index (v2x_partip)
Deliberative component index (v2xdl_delib)
Egalitarian component index (v2x_egal)
#HIPOTESIS: El componente participativo (v2x_partip), el deliberativo (v2xdl_delib), el igualitario (v2x_egal) y el liberal (v2x_liberal) explican el índice de democracia electoral (v2x_polyarchy).
modelolineal <- lm(v2x_polyarchy ~ v2x_partip + v2xdl_delib + v2x_egal + v2x_liberal, data = data)
summary(modelolineal)##
## Call:
## lm(formula = v2x_polyarchy ~ v2x_partip + v2xdl_delib + v2x_egal +
## v2x_liberal, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.27888 -0.06142 0.01883 0.06897 0.19187
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.09343 0.02400 -3.893 0.000141 ***
## v2x_partip 0.34928 0.06361 5.491 1.39e-07 ***
## v2xdl_delib -0.01623 0.05634 -0.288 0.773587
## v2x_egal 0.12920 0.05385 2.399 0.017474 *
## v2x_liberal 0.60183 0.06025 9.989 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09657 on 174 degrees of freedom
## Multiple R-squared: 0.8663, Adjusted R-squared: 0.8632
## F-statistic: 281.9 on 4 and 174 DF, p-value: < 2.2e-16#PREGUNTA 2
data2 <- read_csv("PL2 - PC3.csv")## Rows: 1874 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Departamento, Provincia, Distrito
## dbl (12): Ubigeo, Hogares_T, V_CarFisInadec_T, V_CarFisInadec, V_Hacin_T, V_...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(data2)Hogares_T: Número de hogares V_CarFisIna_des_T: Viviendas con características físicas inadecuadas V_Hacin_T: Viviendas con hacinamiento H_NinosNoEsc_T: Hogares con niños que no asisten a la escuela H_AltaDepEcon_T: Hogares con alta dependencia económica V_ServHig_T: Vivienda sin acceso a servicios higiénicos
names(data2)## [1] "Ubigeo" "Departamento" "Provincia" "Distrito"
## [5] "Hogares_T" "V_CarFisInadec_T" "V_CarFisInadec" "V_Hacin_T"
## [9] "V_Hacin" "V_ServHig_T" "V_ServHig" "H_NinosNoEsc_T"
## [13] "H_NinosNoEsc" "H_AltaDepEcon_T" "H_AltaDepEcon"modelopoisson1 <- glm(Hogares_T ~ H_AltaDepEcon_T + V_CarFisInadec_T + V_Hacin_T,
data = data2, family = poisson(link = "log"))
summary(modelopoisson1)##
## Call:
## glm(formula = Hogares_T ~ H_AltaDepEcon_T + V_CarFisInadec_T +
## V_Hacin_T, family = poisson(link = "log"), data = data2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -512.40 -54.30 -39.73 -13.47 648.76
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 7.909e+00 4.398e-04 17983 <2e-16 ***
## H_AltaDepEcon_T 1.433e-03 1.228e-06 1167 <2e-16 ***
## V_CarFisInadec_T -1.962e-04 1.529e-07 -1284 <2e-16 ***
## V_Hacin_T 3.945e-04 2.280e-07 1730 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 22374858 on 1873 degrees of freedom
## Residual deviance: 10589754 on 1870 degrees of freedom
## AIC: 10606688
##
## Number of Fisher Scoring iterations: 6modelopoisson2 <- glm(Hogares_T ~ H_AltaDepEcon_T + V_CarFisInadec_T + V_Hacin_T + H_NinosNoEsc_T + V_ServHig_T,
data = data2, family = poisson(link = "log"))
summary(modelopoisson2)##
## Call:
## glm(formula = Hogares_T ~ H_AltaDepEcon_T + V_CarFisInadec_T +
## V_Hacin_T + H_NinosNoEsc_T + V_ServHig_T, family = poisson(link = "log"),
## data = data2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -463.88 -53.91 -39.22 -12.48 636.69
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 7.871e+00 4.534e-04 17359.4 <2e-16 ***
## H_AltaDepEcon_T 1.140e-03 1.555e-06 733.3 <2e-16 ***
## V_CarFisInadec_T -2.132e-04 1.624e-07 -1313.1 <2e-16 ***
## V_Hacin_T 1.410e-04 9.081e-07 155.2 <2e-16 ***
## H_NinosNoEsc_T 1.420e-03 4.369e-06 325.1 <2e-16 ***
## V_ServHig_T 2.002e-04 5.312e-07 376.8 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 22374858 on 1873 degrees of freedom
## Residual deviance: 10315026 on 1868 degrees of freedom
## AIC: 10331964
##
## Number of Fisher Scoring iterations: 6#comparando modelo1 y modelo2
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(kableExtra)##
## Attaching package: 'kableExtra'## The following object is masked from 'package:dplyr':
##
## group_rowsanova(modelopoisson1,modelopoisson2,test = "Chisq") %>%
kable(caption = "Tabla ANOVA para comparar modelos poisson")%>%kableExtra::kable_styling(full_width = FALSE)| Resid. Df | Resid. Dev | Df | Deviance | Pr(>Chi) |
|---|---|---|---|---|
| 1870 | 10589754 | NA | NA | NA |
| 1868 | 10315026 | 2 | 274727.7 | 0 |
#PREGUNTA 3
data3 <- read_csv("Ceplan.xlsx - Hoja 1.csv")## Rows: 228 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): TIPO, UBIGEO, PROVINCIA, IVIA, IDE, ABASTOS, IDH
## num (1): POBREZA
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(data3)#limpieza
data3 = data3%>%filter(TIPO == "Provincia")%>%dplyr::select(c(4:8))
data3$IVIA = gsub(",", ".", data3$IVIA)
data3$IDE = gsub(",", ".", data3$IDE)
data3$ABASTOS = gsub(",", ".", data3$ABASTOS)
data3$IDH = gsub(",", ".", data3$IDH)
data3$POBREZA = gsub(",", ".", data3$POBREZA)
data3 = as.data.frame(lapply(data3, as.numeric))## Warning in lapply(data3, as.numeric): NAs introducidos por coercióndata3 = data3[complete.cases(data3),]
data3$IDH_cat = ifelse(data3$IDH < 0.430, 0, 1)
data3$IDH_cat = factor(data3$IDH_cat, levels = c(0,1), labels = c("No desarrollo humano", "Desarrollo humano"))modelologistico <- glm(IDH_cat ~ ABASTOS + IVIA + IDE + POBREZA, data = data3, family = binomial(link = "logit"))## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredsummary(modelologistico)##
## Call:
## glm(formula = IDH_cat ~ ABASTOS + IVIA + IDE + POBREZA, family = binomial(link = "logit"),
## data = data3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.95574 -0.09568 0.00000 0.01236 2.84968
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.855e+01 7.775e+00 3.672 0.000241 ***
## ABASTOS 3.187e-01 1.767e-01 1.804 0.071252 .
## IVIA -4.268e+01 1.024e+01 -4.167 3.08e-05 ***
## IDE -7.285e+00 5.637e+00 -1.292 0.196215
## POBREZA -6.472e-04 5.893e-04 -1.098 0.272082
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 253.643 on 182 degrees of freedom
## Residual deviance: 46.614 on 178 degrees of freedom
## AIC: 56.614
##
## Number of Fisher Scoring iterations: 9