PARCIAL ESTADISTICA 2

setwd("C:/Users/Propietario/Downloads")

library(rio)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ✔ readr     2.1.5

## ── 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(fastDummies)

## Thank you for using fastDummies!
## To acknowledge our work, please cite the package:
## Kaplan, J. & Schlegel, B. (2023). fastDummies: Fast Creation of Dummy (Binary) Columns and Rows from Categorical Variables. Version 1.7.1. URL: https://github.com/jacobkap/fastDummies, https://jacobkap.github.io/fastDummies/.

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(knitr)
library(kableExtra)

## 
## Attaching package: 'kableExtra'
## 
## The following object is masked from 'package:dplyr':
## 
##     group_rows

library(rvest)

## 
## Attaching package: 'rvest'
## 
## The following object is masked from 'package:readr':
## 
##     guess_encoding

library(readxl)

data=import("dataPeru.xlsx")

Pregunta 1

data$contribuyentes_por = data$contribuyentesSunat / data$pobTotal * 100
data$peaOcupada_por= data$peaOcupada / data$pobTotal * 100

modelo = lm(buenEstado ~ contribuyentes_por + peaOcupada_por, data = data)
summary(modelo)

## 
## Call:
## lm(formula = buenEstado ~ contribuyentes_por + peaOcupada_por, 
##     data = data)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -10.0928  -4.3610   0.2575   4.4003  11.0196 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)
## (Intercept)        -22.6095    15.9617  -1.416    0.171
## contribuyentes_por   0.1003     0.3121   0.321    0.751
## peaOcupada_por       1.0218     0.6424   1.590    0.126
## 
## Residual standard error: 6.299 on 22 degrees of freedom
## Multiple R-squared:  0.4669, Adjusted R-squared:  0.4184 
## F-statistic: 9.633 on 2 and 22 DF,  p-value: 0.000989

Pregunta 2

modelode_pea = lm(peaOcupada ~ contribuyentesSunat + buenEstado, data = data)
summary(modelode_pea)

## 
## Call:
## lm(formula = peaOcupada ~ contribuyentesSunat + buenEstado, data = data)
## 
## 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