library("stats")
library("psych")
library("readxl")
library("MASS")
library("ISLR")
library("fRegression")
library("vcd")
## Loading required package: grid
##
## Attaching package: 'vcd'
## The following object is masked from 'package:ISLR':
##
## Hitters
library("openxlsx")
library(readr)
Evidencia1 <- read_csv("Documents/Evidencia1.csv")
## Rows: 12510 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (6): ent, mun, est, pea, ocupados, informales
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
normalizar <- function(x) { (x - min(x)) / (max(x) - min(x)) }
# Aplicar la normalización a las variables pea, ocupados e informales
Evidencia1$pea <- normalizar(Evidencia1$pea)
Evidencia1$ocupados <- normalizar(Evidencia1$ocupados)
Evidencia1$informales <- normalizar(Evidencia1$informales)
head(Evidencia1)
## # A tibble: 6 × 6
## ent mun est pea ocupados informales
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0 0 1 0.703 0.965 0.552
## 2 0 0 2 0.00122 0 0.00231
## 3 0 0 3 0.700 0.964 0.548
## 4 0 0 4 0.707 0.967 0.557
## 5 0 0 5 0.00261 0.0000300 0.00450
## 6 1 0 1 0.700 0.965 0.406
modelo_logit1 = glm(pea~ocupados+informales,data=Evidencia1,family=binomial(link="logit"))
## Warning in eval(family$initialize): non-integer #successes in a binomial glm!
modelo_probit1 = glm(pea~ocupados+informales,data=Evidencia1,family=binomial(link="probit"))
## Warning in eval(family$initialize): non-integer #successes in a binomial glm!
summary(modelo_logit1)
##
## Call:
## glm(formula = pea ~ ocupados + informales, family = binomial(link = "logit"),
## data = Evidencia1)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.24025 0.07139 -45.385 <2e-16 ***
## ocupados 4.51189 0.14279 31.597 <2e-16 ***
## informales -0.40448 0.15826 -2.556 0.0106 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 6004.06 on 12509 degrees of freedom
## Residual deviance: 143.96 on 12507 degrees of freedom
## AIC: 6315.5
##
## Number of Fisher Scoring iterations: 6
summary(modelo_probit1)
##
## Call:
## glm(formula = pea ~ ocupados + informales, family = binomial(link = "probit"),
## data = Evidencia1)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.80403 0.03280 -54.998 <2e-16 ***
## ocupados 2.55722 0.08006 31.939 <2e-16 ***
## informales -0.21877 0.09559 -2.289 0.0221 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 6004.06 on 12509 degrees of freedom
## Residual deviance: 143.78 on 12507 degrees of freedom
## AIC: 6307.8
##
## Number of Fisher Scoring iterations: 6
plot(modelo_logit1)
plot(modelo_probit1)
