Abrir las bases de datos.

load("datos.rdata")
load("segregacion2017.rdata")

Unir bases de datos y dar un poco de orden a las variables.

EC2016 <- select(EC2016, SEXO, EDAD, VICTIMIZACION, COMUNA_15R, ev.policial,)

EC2016$SEXO <- recode(EC2016$SEXO, 'HOMBRE' = "Hombre",
                      'MUJER' = "Mujer") #Recodificar
EC2016$SEXO <-droplevels(EC2016$SEXO) # Borrar niveles no usados

EC2016$EDAD <- as.numeric(EC2016$EDAD) #Pasar de character a numeric

EC2016$VICTIMIZACION <- recode(EC2016$VICTIMIZACION, '0. No' = "Si",
                      '1. Si' = "No") #Recodificar
EC2016$VICTIMIZACION <-droplevels(EC2016$VICTIMIZACION) # Borrar niveles no usados

BBDD <- merge(EC2016, indice ,by="COMUNA_15R")

Modelo nulo.

M0 <- lmer(ev.policial ~ 1 + (1 | COMUNA_15R)
           , data = BBDD)

M1 <- lmer(ev.policial ~ 1 + SEXO + EDAD + VICTIMIZACION + (1 | COMUNA_15R)
           , data = BBDD) #efectos fijos nivel 1

M2 <- lmer(ev.policial ~ 1 + SEXO + EDAD + VICTIMIZACION + IDC + IDS + (1 | COMUNA_15R)
           , data = BBDD) # efectos fijos nivel 1 y 2

M3 <- lmer(ev.policial ~ 1 + SEXO + EDAD + VICTIMIZACION + IDC + IDS + IDC*IDS + (1 | COMUNA_15R)
           , data = BBDD) # efectos fijos nivel 1 y 2 con interacción

Índice de correlación intraclase.

icc(M0) #0.087
## # Intraclass Correlation Coefficient
## 
##      Adjusted ICC: 0.087
##   Conditional ICC: 0.087

Reportes

screenreg(list(M1, M2, M3))
## 
## ========================================================================
##                              Model 1        Model 2        Model 3      
## ------------------------------------------------------------------------
## (Intercept)                       0.41 ***       0.47 ***       0.55 ***
##                                  (0.01)         (0.03)         (0.04)   
## SEXOMujer                        -0.00          -0.00          -0.00    
##                                  (0.00)         (0.00)         (0.00)   
## EDAD                              0.00 ***       0.00 ***       0.00 ***
##                                  (0.00)         (0.00)         (0.00)   
## VICTIMIZACIONNo                  -0.02 ***      -0.02 ***      -0.02 ***
##                                  (0.00)         (0.00)         (0.00)   
## IDC                                              0.04          -0.29    
##                                                 (0.07)         (0.15)   
## IDS                                             -0.20 ***      -0.42 ***
##                                                 (0.05)         (0.11)   
## IDC:IDS                                                         1.01 *  
##                                                                (0.43)   
## ------------------------------------------------------------------------
## AIC                          -29756.38      -29760.82      -29764.30    
## BIC                          -29704.37      -29691.48      -29686.28    
## Log Likelihood                14884.19       14888.41       14891.15    
## Num. obs.                     42965          42965          42965       
## Num. groups: COMUNA_15R          63             63             63       
## Var: COMUNA_15R (Intercept)       0.00           0.00           0.00    
## Var: Residual                     0.03           0.03           0.03    
## ========================================================================
## *** p < 0.001; ** p < 0.01; * p < 0.05
texreg(list(M1, M2, M3))
## 
## \begin{table}
## \begin{center}
## \begin{tabular}{l c c c}
## \hline
##  & Model 1 & Model 2 & Model 3 \\
## \hline
## (Intercept)                  & $0.41^{***}$  & $0.47^{***}$  & $0.55^{***}$  \\
##                              & $(0.01)$      & $(0.03)$      & $(0.04)$      \\
## SEXOMujer                    & $-0.00$       & $-0.00$       & $-0.00$       \\
##                              & $(0.00)$      & $(0.00)$      & $(0.00)$      \\
## EDAD                         & $0.00^{***}$  & $0.00^{***}$  & $0.00^{***}$  \\
##                              & $(0.00)$      & $(0.00)$      & $(0.00)$      \\
## VICTIMIZACIONNo              & $-0.02^{***}$ & $-0.02^{***}$ & $-0.02^{***}$ \\
##                              & $(0.00)$      & $(0.00)$      & $(0.00)$      \\
## IDC                          &               & $0.04$        & $-0.29$       \\
##                              &               & $(0.07)$      & $(0.15)$      \\
## IDS                          &               & $-0.20^{***}$ & $-0.42^{***}$ \\
##                              &               & $(0.05)$      & $(0.11)$      \\
## IDC:IDS                      &               &               & $1.01^{*}$    \\
##                              &               &               & $(0.43)$      \\
## \hline
## AIC                          & $-29756.38$   & $-29760.82$   & $-29764.30$   \\
## BIC                          & $-29704.37$   & $-29691.48$   & $-29686.28$   \\
## Log Likelihood               & $14884.19$    & $14888.41$    & $14891.15$    \\
## Num. obs.                    & $42965$       & $42965$       & $42965$       \\
## Num. groups: COMUNA\_15R     & $63$          & $63$          & $63$          \\
## Var: COMUNA\_15R (Intercept) & $0.00$        & $0.00$        & $0.00$        \\
## Var: Residual                & $0.03$        & $0.03$        & $0.03$        \\
## \hline
## \multicolumn{4}{l}{\scriptsize{$^{***}p<0.001$; $^{**}p<0.01$; $^{*}p<0.05$}}
## \end{tabular}
## \caption{Statistical models}
## \label{table:coefficients}
## \end{center}
## \end{table}
g1 <- plot_model(M3, type = "pred", terms = "IDC")
g2 <- plot_model(M3, type = "pred", terms = "IDS")
g3 <- plot_model(M3, type = "pred", terms = c("IDC", "IDS"))

g1

g2

g3