rm(list = ls()) 

library(rio)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ 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)

data1= import("dataPeru.xlsx")

str(data1)

## '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 ...

data1=data1[complete.cases(data1),]

modelo1=formula(buenEstado~contribuyentesSunat+peaOcupada)

reg1=lm(modelo1,data=data1)
summary(reg1)

## 
## Call:
## lm(formula = modelo1, data = data1)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -10.589  -3.966  -1.347   1.907  21.518 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)          1.865e+01  2.694e+00   6.922 5.98e-07 ***
## contribuyentesSunat  1.786e-05  2.060e-05   0.867    0.395    
## peaOcupada          -1.596e-05  2.241e-05  -0.712    0.484    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 7.925 on 22 degrees of freedom
## Multiple R-squared:  0.1561, Adjusted R-squared:  0.07939 
## F-statistic: 2.035 on 2 and 22 DF,  p-value: 0.1546

modelo2=formula(peaOcupada~contribuyentesSunat+buenEstado)

reg2=lm(modelo2,data=data1)
summary(reg2)

## 
## Call:
## lm(formula = modelo2, data = data1)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -91867 -58573 -11166  46174 155851 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)          1.155e+05  3.787e+04   3.049  0.00588 ** 
## contribuyentesSunat  9.206e-01  1.741e-02  52.872  < 2e-16 ***
## buenEstado          -1.412e+03  1.983e+03  -0.712  0.48395    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 74540 on 22 degrees of freedom
## Multiple R-squared:  0.9932, Adjusted R-squared:  0.9926 
## F-statistic:  1603 on 2 and 22 DF,  p-value: < 2.2e-16

data1$buenEstado <- data1$buenEstado / 100

data1$logit_buenEstado <- log(data1$buenEstado / (1 - data1$buenEstado))

modelox=formula(logit_buenEstado~contribuyentesSunat+peaOcupada)

regx=lm(modelox,data=data1)
summary(regx)

## 
## Call:
## lm(formula = modelox, data = data1)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -0.87418 -0.22370  0.01662  0.18746  1.18092 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)         -1.591e+00  1.788e-01  -8.897 9.67e-09 ***
## contribuyentesSunat  7.815e-07  1.367e-06   0.572    0.573    
## peaOcupada          -6.339e-07  1.487e-06  -0.426    0.674    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.526 on 22 degrees of freedom
## Multiple R-squared:  0.1296, Adjusted R-squared:  0.05045 
## F-statistic: 1.638 on 2 and 22 DF,  p-value: 0.2173