link="https://docs.google.com/spreadsheets/d/e/2PACX-1vQWAwF5XnCfLYkPoPsWzR8Ut-h1_KSsTYQB1uC6lPxIgRe-EI9x7r5ELluLXgl_5g/pub?output=csv"
midata=read.csv(link,stringsAsFactors = F)
table(midata$BECARIO)
##
## NO SI
## 26478 40771
names(midata)
## [1] "REGION" "BECARIO" "GESTION" "DISTRITO" "POBREZA"
midata[ ,c(1:5)] = lapply(midata[ , c(1:5)], as.factor)
summary(midata)
## REGION BECARIO GESTION DISTRITO POBREZA
## LIMA : 7639 NO:26478 Privada: 5628 Rural :26837 NoP:34339
## CUSCO : 4760 SI:40771 Publica:61621 Urbana:40412 P :32910
## PIURA : 4744
## JUNIN : 4606
## LORETO : 4403
## CAJAMARCA: 3895
## (Other) :37202
set.seed(2019)
vars1=midata[,c("BECARIO","POBREZA")]
#regresion
rlog1=glm(BECARIO~., data=vars1,family = binomial)
#resultado clásico:
summary(rlog1)
##
## Call:
## glm(formula = BECARIO ~ ., family = binomial, data = vars1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.3667 -1.3641 0.9992 1.0016 1.0016
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.428769 0.011042 38.831 <2e-16 ***
## POBREZAP 0.005903 0.015789 0.374 0.708
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 90166 on 67248 degrees of freedom
## Residual deviance: 90166 on 67247 degrees of freedom
## AIC: 90170
##
## Number of Fisher Scoring iterations: 4
### semilla
set.seed(2019)
### primer modelo:
#data como subset
#BECARIO DEPENDIENTE
#TAMBIEN SE PUEDE PONER EL NUMERO DE LAS COLUMNAS DE LAS VARIABLES INDEPEDIENTES
vars2=midata[,c("BECARIO","POBREZA","GESTION")]
#regresion
rlog2=glm(BECARIO~., data=vars2,family = binomial)
#resultado clásico:
summary(rlog2)
##
## Call:
## glm(formula = BECARIO ~ ., family = binomial, data = vars2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.3756 -1.3721 0.9914 0.9945 1.0846
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.230123 0.027282 8.435 < 2e-16 ***
## POBREZAP -0.007801 0.015893 -0.491 0.624
## GESTIONPublica 0.224493 0.028248 7.947 1.91e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 90166 on 67248 degrees of freedom
## Residual deviance: 90103 on 67246 degrees of freedom
## AIC: 90109
##
## Number of Fisher Scoring iterations: 4
vars3=midata[,c("BECARIO","POBREZA","GESTION","DISTRITO")]
#regresion
rlog3=glm(BECARIO~., data=vars3,family = binomial)
#resultado clásico:
summary(rlog3)
##
## Call:
## glm(formula = BECARIO ~ ., family = binomial, data = vars3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.3820 -1.3624 0.9858 1.0030 1.0966
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.933e-01 3.058e-02 6.320 2.62e-10 ***
## POBREZAP -8.051e-05 1.616e-02 -0.005 0.99602
## GESTIONPublica 2.318e-01 2.838e-02 8.167 3.16e-16 ***
## DISTRITOUrbana 4.401e-02 1.649e-02 2.669 0.00762 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 90166 on 67248 degrees of freedom
## Residual deviance: 90096 on 67245 degrees of freedom
## AIC: 90104
##
## Number of Fisher Scoring iterations: 4
###TABLAS
j1 = table(midata $REGION)
j1
##
## AMAZONAS ANCASH APURIMAC AREQUIPA AYACUCHO
## 2595 3535 2967 1309 2295
## CAJAMARCA CALLAO CUSCO HUANCAVELICA HUANUCO
## 3895 1413 4760 2513 2276
## ICA JUNIN LA LIBERTAD LAMBAYEQUE LIMA
## 1497 4606 3328 2362 7639
## LORETO MADRE DE DIOS MOQUEGUA PASCO PIURA
## 4403 431 312 1872 4744
## PUNO SAN MARTIN TACNA TUMBES UCAYALI
## 2988 2832 682 652 1343
ni <- prop.table(j1)
ni
##
## AMAZONAS ANCASH APURIMAC AREQUIPA AYACUCHO
## 0.038587934 0.052565837 0.044119615 0.019464973 0.034126902
## CAJAMARCA CALLAO CUSCO HUANCAVELICA HUANUCO
## 0.057919077 0.021011465 0.070781722 0.037368585 0.033844369
## ICA JUNIN LA LIBERTAD LAMBAYEQUE LIMA
## 0.022260554 0.068491725 0.049487725 0.035123199 0.113592767
## LORETO MADRE DE DIOS MOQUEGUA PASCO PIURA
## 0.065473093 0.006409017 0.004639474 0.027836845 0.070543800
## PUNO SAN MARTIN TACNA TUMBES UCAYALI
## 0.044431887 0.042112150 0.010141415 0.009695311 0.019970557
pi <- prop.table(ni)*100
pi
##
## AMAZONAS ANCASH APURIMAC AREQUIPA AYACUCHO
## 3.8587934 5.2565837 4.4119615 1.9464973 3.4126902
## CAJAMARCA CALLAO CUSCO HUANCAVELICA HUANUCO
## 5.7919077 2.1011465 7.0781722 3.7368585 3.3844369
## ICA JUNIN LA LIBERTAD LAMBAYEQUE LIMA
## 2.2260554 6.8491725 4.9487725 3.5123199 11.3592767
## LORETO MADRE DE DIOS MOQUEGUA PASCO PIURA
## 6.5473093 0.6409017 0.4639474 2.7836845 7.0543800
## PUNO SAN MARTIN TACNA TUMBES UCAYALI
## 4.4431887 4.2112150 1.0141415 0.9695311 1.9970557
t1 = table(midata$REGION,midata$BECARIO)
t1
##
## NO SI
## AMAZONAS 894 1701
## ANCASH 1389 2146
## APURIMAC 1194 1773
## AREQUIPA 510 799
## AYACUCHO 709 1586
## CAJAMARCA 1447 2448
## CALLAO 499 914
## CUSCO 2095 2665
## HUANCAVELICA 899 1614
## HUANUCO 938 1338
## ICA 591 906
## JUNIN 1889 2717
## LA LIBERTAD 1297 2031
## LAMBAYEQUE 825 1537
## LIMA 3121 4518
## LORETO 1993 2410
## MADRE DE DIOS 204 227
## MOQUEGUA 88 224
## PASCO 824 1048
## PIURA 1699 3045
## PUNO 1512 1476
## SAN MARTIN 989 1843
## TACNA 210 472
## TUMBES 220 432
## UCAYALI 442 901
t2 = table(midata$DISTRITO,midata$BECARIO)
t2
##
## NO SI
## Rural 10678 16159
## Urbana 15800 24612
j2 = table(midata$POBREZA, midata$REGION)
j2
##
## AMAZONAS ANCASH APURIMAC AREQUIPA AYACUCHO CAJAMARCA CALLAO CUSCO
## NoP 0 3535 0 1309 0 0 1413 4760
## P 2595 0 2967 0 2295 3895 0 0
##
## HUANCAVELICA HUANUCO ICA JUNIN LA LIBERTAD LAMBAYEQUE LIMA LORETO
## NoP 0 0 1497 4606 3328 0 7639 0
## P 2513 2276 0 0 0 2362 0 4403
##
## MADRE DE DIOS MOQUEGUA PASCO PIURA PUNO SAN MARTIN TACNA TUMBES UCAYALI
## NoP 431 312 0 0 0 2832 682 652 1343
## P 0 0 1872 4744 2988 0 0 0 0
t3 = table(midata$POBREZA,midata$BECARIO)
t3
##
## NO SI
## NoP 13544 20795
## P 12934 19976
t4 = table(midata$GESTION, midata $BECARIO)
t4
##
## NO SI
## Privada 2495 3133
## Publica 23983 37638
library(stargazer)
##
## Please cite as:
## Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.
## R package version 5.2.2. https://CRAN.R-project.org/package=stargazer
###al usar stargazer poner esto:
##```{r, results='asis',eval=TRUE}
##Aquí oner el código
##```
library(papeR)
## Loading required package: car
## Loading required package: carData
## Loading required package: xtable
## Registered S3 method overwritten by 'papeR':
## method from
## Anova.lme car
##
## Attaching package: 'papeR'
## The following object is masked from 'package:utils':
##
## toLatex
stargazer(rlog3, type = "html")
|
|
|
|
Dependent variable:
|
|
|
|
|
|
BECARIO
|
|
|
|
POBREZAP
|
-0.0001
|
|
|
(0.016)
|
|
|
|
|
GESTIONPublica
|
0.232***
|
|
|
(0.028)
|
|
|
|
|
DISTRITOUrbana
|
0.044***
|
|
|
(0.016)
|
|
|
|
|
Constant
|
0.193***
|
|
|
(0.031)
|
|
|
|
|
|
|
Observations
|
67,249
|
|
Log Likelihood
|
-45,047.950
|
|
Akaike Inf. Crit.
|
90,103.900
|
|
|
|
Note:
|
p<0.1; p<0.05; p<0.01
|
newVarLabels1=c( "Región considerada en pobreza", "Gestión educativa pública", "Territorio urbano")
depLabel="Beca"
stargazer(rlog3, type = "html",
covariate.labels =newVarLabels1,
dep.var.caption = "Variable Dependiente",
dep.var.labels = depLabel)
|
|
|
|
Variable Dependiente
|
|
|
|
|
|
Beca
|
|
|
|
Región considerada en pobreza
|
-0.0001
|
|
|
(0.016)
|
|
|
|
|
Gestión educativa pública
|
0.232***
|
|
|
(0.028)
|
|
|
|
|
Territorio urbano
|
0.044***
|
|
|
(0.016)
|
|
|
|
|
Constant
|
0.193***
|
|
|
(0.031)
|
|
|
|
|
|
|
Observations
|
67,249
|
|
Log Likelihood
|
-45,047.950
|
|
Akaike Inf. Crit.
|
90,103.900
|
|
|
|
Note:
|
p<0.1; p<0.05; p<0.01
|