library(rio)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.0     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(dplyr)
library(ggplot2)
library(sjPlot)
library(ggfortify)
library(forcats)
library(lsr)
library(scales)
## 
## Attaching package: 'scales'
## 
## The following object is masked from 'package:purrr':
## 
##     discard
## 
## The following object is masked from 'package:readr':
## 
##     col_factor
library(DescTools)
library(magrittr)
## 
## Attaching package: 'magrittr'
## 
## The following object is masked from 'package:purrr':
## 
##     set_names
## 
## The following object is masked from 'package:tidyr':
## 
##     extract
library(margins)
library(knitr)
library(jtools)
## 
## Attaching package: 'jtools'
## 
## The following object is masked from 'package:DescTools':
## 
##     %nin%
library(stargazer)
## 
## Please cite as: 
## 
##  Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables.
##  R package version 5.2.3. https://CRAN.R-project.org/package=stargazer
library(lmtest)
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## 
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
library(kableExtra)
## 
## Attaching package: 'kableExtra'
## 
## The following object is masked from 'package:dplyr':
## 
##     group_rows
library(car)
## Loading required package: carData
## 
## Attaching package: 'car'
## 
## The following object is masked from 'package:DescTools':
## 
##     Recode
## 
## The following object is masked from 'package:dplyr':
## 
##     recode
## 
## The following object is masked from 'package:purrr':
## 
##     some
library(summarytools)
## 
## Attaching package: 'summarytools'
## 
## The following object is masked from 'package:tibble':
## 
##     view
library(cvms)
library(survminer)
## Loading required package: ggpubr
## 
## Attaching package: 'ggpubr'
## 
## The following object is masked from 'package:cvms':
## 
##     font
library(survival)
## 
## Attaching package: 'survival'
## 
## The following object is masked from 'package:survminer':
## 
##     myeloma
library(modelsummary)
## `modelsummary` 2.0.0 now uses `tinytable` as its default table-drawing
##   backend. Learn more at: https://vincentarelbundock.github.io/tinytable/
## 
## Revert to `kableExtra` for one session:
## 
##   options(modelsummary_factory_default = 'kableExtra')
##   options(modelsummary_factory_latex = 'kableExtra')
##   options(modelsummary_factory_html = 'kableExtra')
## 
## Silence this message forever:
## 
##   config_modelsummary(startup_message = FALSE)
## 
## Attaching package: 'modelsummary'
## 
## The following objects are masked from 'package:DescTools':
## 
##     Format, Mean, Median, N, SD, Var
data = import("dataPeru.xlsx")
str(data)
## 'data.frame':    25 obs. of  8 variables:
##  $ DEPARTAMENTO       : chr  "AMAZONAS" "ÁNCASH" "APURÍMAC" "AREQUIPA" ...
##  $ UBIGEO             : chr  "010000" "020000" "030000" "040000" ...
##  $ buenEstado         : num  18.6 13.9 8.7 27.4 17 18 33.8 11.9 10.1 15.6 ...
##  $ contribuyentesSunat: num  75035 302906 103981 585628 151191 ...
##  $ peaOcupada         : num  130019 387976 140341 645001 235857 ...
##  $ pobUrbana          : num  205976 806065 243354 1383694 444473 ...
##  $ PobRural           : num  211389 333050 180905 76739 206467 ...
##  $ pobTotal           : num  417365 1139115 424259 1460433 650940 ...
data$contribuyentesSunat_pct <- (data$contribuyentesSunat / data$pobTotal) * 100
data$peaOcupada_pct <- (data$peaOcupada / data$pobTotal) * 100
hipotesis1 = formula(data$buenEstado~data$contribuyentesSunat_pct+data$peaOcupada_pct)
regresion1=glm(hipotesis1, data=data,family = gaussian)
summary(regresion1)
## 
## Call:
## glm(formula = hipotesis1, family = gaussian, data = data)
## 
## Coefficients:
##                              Estimate Std. Error t value Pr(>|t|)
## (Intercept)                  -22.6095    15.9617  -1.416    0.171
## data$contribuyentesSunat_pct   0.1003     0.3121   0.321    0.751
## data$peaOcupada_pct            1.0218     0.6424   1.590    0.126
## 
## (Dispersion parameter for gaussian family taken to be 39.67738)
## 
##     Null deviance: 1637.3  on 24  degrees of freedom
## Residual deviance:  872.9  on 22  degrees of freedom
## AIC: 167.77
## 
## Number of Fisher Scoring iterations: 2
hipotesis2 = formula(data$peaOcupada~data$contribuyentesSunat+data$buenEstado)
regresion2 = glm(hipotesis2, data = data, family = poisson)
summary(regresion2)
## 
## Call:
## glm(formula = hipotesis2, family = poisson, data = data)
## 
## Coefficients:
##                           Estimate Std. Error z value Pr(>|z|)    
## (Intercept)              1.238e+01  9.007e-04 13744.7   <2e-16 ***
## data$contribuyentesSunat 5.575e-07  1.786e-10  3121.7   <2e-16 ***
## data$buenEstado          7.924e-03  4.530e-05   174.9   <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: 16555865  on 24  degrees of freedom
## Residual deviance:  2148535  on 22  degrees of freedom
## AIC: 2148901
## 
## Number of Fisher Scoring iterations: 4