#HOLA 1. Cargar data

link="https://docs.google.com/spreadsheets/d/e/2PACX-1vSPZ-j8hoFfZbf5qNnAf0tNIiaucIPMVljywf5s4B3sXzGtB0xbbpIw3Zr8o_ulTcFo21qjFwDOZ32t/pub?gid=2057947663&single=true&output=csv"

pavidata=read.csv(link,stringsAsFactors = T)
  1. Verificar tipo de datos:
str(pavidata)
## 'data.frame':    1096 obs. of  8 variables:
##  $ poblacioncienmil: num  20.9155 0.2406 0.0398 0.0558 0.2723 ...
##  $ nbi             : num  12.2 33.8 28.5 33.1 27.1 ...
##  $ consejocomunal  : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ priorizado      : num  0 1 0 0 0 0 0 0 1 0 ...
##  $ uribista        : num  0 1 1 1 1 1 1 1 1 NA ...
##  $ ejecucion       : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ apropiaciondolar: num  102.17 4.19 1.59 0 0 ...
##  $ pctopo          : num  14.82 14.51 15.08 6.15 47.31 ...

Hacer ajustes:

# pavidata[,c("consejocomunal","priorizado","uribista","ejecucion)]
pavidata[,(3:6)]=lapply(pavidata[,(3:6)],as.factor)
  1. Resumenes

3.1 simple:

summary(pavidata)
##  poblacioncienmil        nbi        consejocomunal priorizado uribista  
##  Min.   : 0.00158   Min.   : 5.36   0:1036         0:820      0   :332  
##  1st Qu.: 0.07422   1st Qu.:28.35   1:  60         1:276      1   :560  
##  Median : 0.13998   Median :41.30                             NA's:204  
##  Mean   : 0.40470   Mean   :42.96                                       
##  3rd Qu.: 0.26255   3rd Qu.:55.48                                       
##  Max.   :69.26836   Max.   :98.81                                       
##                     NA's   :30                                          
##  ejecucion apropiaciondolar      pctopo      
##  0:1055    Min.   :  0.000   Min.   : 0.000  
##  1:  41    1st Qu.:  0.000   1st Qu.: 5.922  
##            Median :  0.000   Median :20.308  
##            Mean   :  8.276   Mean   :27.874  
##            3rd Qu.:  9.385   3rd Qu.:45.711  
##            Max.   :132.643   Max.   :99.419  
##                              NA's   :7

Modificar orden:

newOrder=c("apropiaciondolar","pctopo","uribista","priorizado","consejocomunal","ejecucion","poblacioncienmil","nbi")
pavidata=pavidata[,newOrder]

Primer intento:

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
summarize(pavidata)
## Factors are dropped from the summary
##                       N Missing    Mean    SD    Min    Q1 Median    Q3    Max
## 1 apropiaciondolar 1096       0    8.28 16.04   0.00  0.00   0.00  9.40 132.64
## 2           pctopo 1089       7   27.87 25.59   0.00  5.92  20.31 45.71  99.42
## 3 poblacioncienmil 1096       0    0.40  2.39   0.00  0.07   0.14  0.26  69.27
## 4              nbi 1066      30   42.96 18.70   5.36 28.34  41.30 55.49  98.81

Sin mensajes:

library("papeR")

summarize(pavidata)
##                       N Missing    Mean    SD    Min    Q1 Median    Q3    Max
## 1 apropiaciondolar 1096       0    8.28 16.04   0.00  0.00   0.00  9.40 132.64
## 2           pctopo 1089       7   27.87 25.59   0.00  5.92  20.31 45.71  99.42
## 3 poblacioncienmil 1096       0    0.40  2.39   0.00  0.07   0.14  0.26  69.27
## 4              nbi 1066      30   42.96 18.70   5.36 28.34  41.30 55.49  98.81
summarize(pavidata, type = "factor")
## Non-factors are dropped from the summary
##                      Level      N    %
## 1       uribista         0    332 30.3
## 2                        1    560 51.1
## 3                <Missing>    204 18.6
## 4     priorizado         0    820 74.8
## 5                        1    276 25.2
## 6 consejocomunal         0   1036 94.5
## 7                        1     60  5.5
## 8      ejecucion         0   1055 96.3
## 9                        1     41  3.7

Sin cuartiles:

summarize(pavidata,quantiles = FALSE)
##                       N Missing    Mean    SD
## 1 apropiaciondolar 1096       0    8.28 16.04
## 2           pctopo 1089       7   27.87 25.59
## 3 poblacioncienmil 1096       0    0.40  2.39
## 4              nbi 1066      30   42.96 18.70

Sin valores perdidos:

summarize(pavidata,quantiles = FALSE,show.NAs=FALSE)
## Factors are dropped from the summary
##                       N    Mean    SD
## 1 apropiaciondolar 1096    8.28 16.04
## 2           pctopo 1089   27.87 25.59
## 3 poblacioncienmil 1096    0.40  2.39
## 4              nbi 1066   42.96 18.70

Etiquetas nuevas:

newVarLabels=c("Apropiacion Presupuestal (millones de US$)", "Votos Oposición (%)", "Alcalde coalición Uribista", "Prioridad Técnica","Consejo Comunal","Consejo Comunal con ejecucion d recursos", "Poblacion (100 000 habs.", "NBI")

newColLabels=c("Variables","N" ,"Promedio", "Desv. Tipica")

##
summarize(pavidata,quantiles=F,
          show.NAs=FALSE,
          variable.labels=newVarLabels,
          colnames=newColLabels)
## Factors are dropped from the summary
##                                    Variables    N   Promedio Desv. Tipica
## 1 Apropiacion Presupuestal (millones de US$) 1096       8.28        16.04
## 2                        Votos Oposición (%) 1089      27.87        25.59
## 3                   Poblacion (100 000 habs. 1096       0.40         2.39
## 4                                        NBI 1066      42.96        18.70

Para tu pdf:

##
# header-includes:
#   \usepackage{booktabs}

##
xtable(summarize(pavidata,quantiles=F,
          show.NAs=FALSE,
          variable.labels=newVarLabels,
          colnames=newColLabels))
## Factors are dropped from the summary
## NOTE: Output requires \usepackage{booktabs} in your preamble.
# solo para pdf
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
stargazer(pavidata, type = "latex",summary.stat = c("n", "min", "sd","max","mean"))
% Table created by stargazer v.5.2.2 by Marek Hlavac, Harvard University. E-mail: hlavac at fas.harvard.edu % Date and time: Thu, Jul 09, 2020 - 20:26:57
regresion=lm(apropiaciondolar~.,data=pavidata)
summary(regresion)
## 
## Call:
## lm(formula = apropiaciondolar ~ ., data = pavidata)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -60.201  -8.207  -5.875   2.505  92.488 
## 
## Coefficients:
##                  Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      14.13182    1.67651   8.429  < 2e-16 ***
## pctopo           -0.03096    0.02126  -1.456  0.14563    
## uribista1        -2.57184    1.09188  -2.355  0.01872 *  
## priorizado1      -2.21395    1.18715  -1.865  0.06253 .  
## consejocomunal1  14.05017    2.32452   6.044 2.23e-09 ***
## ejecucion1        2.95688    2.80758   1.053  0.29255    
## poblacioncienmil  1.83866    0.20024   9.182  < 2e-16 ***
## nbi              -0.09292    0.02941  -3.160  0.00163 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 15.38 on 868 degrees of freedom
##   (220 observations deleted due to missingness)
## Multiple R-squared:  0.1751, Adjusted R-squared:  0.1684 
## F-statistic: 26.32 on 7 and 868 DF,  p-value: < 2.2e-16
stargazer(regresion, type = "html")
Dependent variable:
apropiaciondolar
pctopo -0.031
(0.021)
uribista1 -2.572**
(1.092)
priorizado1 -2.214*
(1.187)
consejocomunal1 14.050***
(2.325)
ejecucion1 2.957
(2.808)
poblacioncienmil 1.839***
(0.200)
nbi -0.093***
(0.029)
Constant 14.132***
(1.677)
Observations 876
R2 0.175
Adjusted R2 0.168
Residual Std. Error 15.378 (df = 868)
F Statistic 26.316*** (df = 7; 868)
Note: p<0.1; p<0.05; p<0.01
newVarLabels2=c( "Votos Oposición (%)", "Alcalde coalición Uribista", "Prioridad Técnica","Consejo Comunal","Consejo Comunal con ejecucion d recursos", "Poblacion (100 000 habs.", "NBI", "Constante")
depLabel="Apropiacion Presupuestal (millones de US$)"
stargazer(regresion, type = "html",
          covariate.labels =newVarLabels2,
          dep.var.caption = "Variable Dependiente",
          dep.var.labels = depLabel)
Variable Dependiente
Apropiacion Presupuestal (millones de US)
Votos Oposición (%) -0.031
(0.021)
Alcalde coalición Uribista -2.572**
(1.092)
Prioridad Técnica -2.214*
(1.187)
Consejo Comunal 14.050***
(2.325)
Consejo Comunal con ejecucion d recursos 2.957
(2.808)
Poblacion (100 000 habs. 1.839***
(0.200)
NBI -0.093***
(0.029)
Constante 14.132***
(1.677)
Observations 876
R2 0.175
Adjusted R2 0.168
Residual Std. Error 15.378 (df = 868)
F Statistic 26.316*** (df = 7; 868)
Note: p<0.1; p<0.05; p<0.01
regresion2=lm(apropiaciondolar~.,data=pavidata[,-c(7,8)])

newVarLabels3=c( "Votos Oposición (%)", "Alcalde coalición Uribista", "Prioridad Técnica","Consejo Comunal","Consejo Comunal con ejecucion d recursos", "Constante")

depLabel="Apropiacion Presupuestal (millones de US$)"
stargazer(regresion2, type = "html",
          covariate.labels =newVarLabels3,
          dep.var.caption = "Variable Dependiente",
          dep.var.labels = depLabel)
Variable Dependiente
Apropiacion Presupuestal (millones de US)
Votos Oposición (%) -0.040*
(0.022)
Alcalde coalición Uribista -2.908**
(1.139)
Prioridad Técnica -1.204
(1.240)
Consejo Comunal 18.989***
(2.366)
Consejo Comunal con ejecucion d recursos 1.984
(2.946)
Constante 10.968***
(1.207)
Observations 888
R2 0.078
Adjusted R2 0.073
Residual Std. Error 16.173 (df = 882)
F Statistic 14.998*** (df = 5; 882)
Note: p<0.1; p<0.05; p<0.01
stargazer(regresion2,regresion,type='html', 
          covariate.labels =newVarLabels2,
          dep.var.caption = "Variable Dependiente",
          dep.var.labels = depLabel)
Variable Dependiente
Apropiacion Presupuestal (millones de US)
(1) (2)
Votos Oposición (%) -0.040* -0.031
(0.022) (0.021)
Alcalde coalición Uribista -2.908** -2.572**
(1.139) (1.092)
Prioridad Técnica -1.204 -2.214*
(1.240) (1.187)
Consejo Comunal 18.989*** 14.050***
(2.366) (2.325)
Consejo Comunal con ejecucion d recursos 1.984 2.957
(2.946) (2.808)
Poblacion (100 000 habs. 1.839***
(0.200)
NBI -0.093***
(0.029)
Constante 10.968*** 14.132***
(1.207) (1.677)
Observations 888 876
R2 0.078 0.175
Adjusted R2 0.073 0.168
Residual Std. Error 16.173 (df = 882) 15.378 (df = 868)
F Statistic 14.998*** (df = 5; 882) 26.316*** (df = 7; 868)
Note: p<0.1; p<0.05; p<0.01
library(jtools) # broom / ggstance / broom.mixed
plot_summs(regresion2,regresion)
## Registered S3 methods overwritten by 'broom':
##   method            from  
##   tidy.glht         jtools
##   tidy.summary.glht jtools
## Loading required namespace: broom.mixed
## Registered S3 methods overwritten by 'broom.mixed':
##   method         from 
##   augment.lme    broom
##   augment.merMod broom
##   glance.lme     broom
##   glance.merMod  broom
##   glance.stanreg broom
##   tidy.brmsfit   broom
##   tidy.gamlss    broom
##   tidy.lme       broom
##   tidy.merMod    broom
##   tidy.rjags     broom
##   tidy.stanfit   broom
##   tidy.stanreg   broom