| title: “CIENCIA DE DATOS/ Análisis de Base de datos de Emprendimiento Femenino UE” |
| author: “Dr. Roberto Chang López/ Certificado en Machine Learning por MIT” |
| date: “13/12/2020” |
| output: |
| html_document: default |
Base de Datos KAGGLE
#########################Dr. Roberto Enrique Chang López########################## ###################################rchang@unah.edu.hn############################### ##################################################################################### #####################################################################################
Algunos Dashboards elaborados son: Para Bolsa de Valores https://rchang.shinyapps.io/rchang-stock-exchange/
Para el Estado del Clima https://rchang.shinyapps.io/rchang-app_clima_ho/
Para Machine Learning https://rchang.shinyapps.io/rchang-app/
Para Empresariales e Industriales https://rchang.shinyapps.io/rchang-app_final_emp/
Para Dashboards con log in https://rchang.shinyapps.io/clase_3-shiny-2/_w_ae4e775f/_w_f249a9a1/?page=sign_in
y para Sistemas de Información Geográfica
El Planteamiento del Problema
#De las Variables presentadas en la base de datos de Kaggle sobre el empredimiento #femeninino en Europa, se requiere conocer ¿Cuál es el impacto de la inflación en el #índice de emprendimiento femenino en el caso de que la inflación afecte? Asimismo, #Se requiere realizar un análisis y exploración de datos previos con histogramas, #box plots, diagramas de dispersión, pruebas de normalidad, matriz de correlación, #matriz de correlación con p-values, prueba de hipótesis, pruebas de potencia #y el análisis de regresiones que contesten la pregunta de investigación?
#Lectura del archivo csv.
library(readr)## Warning: package 'readr' was built under R version 4.0.5Dataset3 <- read_delim("Dataset3.csv", ";",
escape_double = FALSE, trim_ws = TRUE)##
## -- Column specification --------------------------------------------------------
## cols(
## No = col_double(),
## Country = col_character(),
## `Level of development` = col_character(),
## `European Union Membership` = col_character(),
## Currency = col_character(),
## `Women Entrepreneurship Index` = col_double(),
## `Entrepreneurship Index` = col_double(),
## `Inflation rate` = col_double(),
## `Female Labor Force Participation Rate` = col_double()
## )Dataset3## # A tibble: 51 x 9
## No Country `Level of develo~ `European Union M~ Currency `Women Entrepren~
## <dbl> <chr> <chr> <chr> <chr> <dbl>
## 1 4 Austria Developed Member Euro 54.9
## 2 6 Belgium Developed Member Euro 63.6
## 3 17 Estonia Developed Member Euro 55.4
## 4 18 Finland Developed Member Euro 66.4
## 5 19 France Developed Member Euro 68.8
## 6 20 Germany Developed Member Euro 63.6
## 7 22 Greece Developed Member Euro 43
## 8 28 Ireland Developed Member Euro 64.3
## 9 30 Italy Developed Member Euro 51.4
## 10 34 Latvia Developed Member Euro 56.6
## # ... with 41 more rows, and 3 more variables: Entrepreneurship Index <dbl>,
## # Inflation rate <dbl>, Female Labor Force Participation Rate <dbl>#Instalación de paquetes
#install.packages(“dplyr”) #install.packages(“ggplot2”) #install.packages(“GGally”) #install.packages(“Hmisc”) #install.packages(“corrplot”) #install.packages(“PerformanceAnalytics”)
#Llamar los paquetes instalados con los que vamos a trabajar
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.0.5## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v dplyr 1.0.7
## v tibble 3.1.2 v stringr 1.4.0
## v tidyr 1.1.3 v forcats 0.5.1
## v purrr 0.3.4## Warning: package 'ggplot2' was built under R version 4.0.5## Warning: package 'tibble' was built under R version 4.0.5## Warning: package 'tidyr' was built under R version 4.0.5## Warning: package 'dplyr' was built under R version 4.0.5## Warning: package 'forcats' was built under R version 4.0.5## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(dplyr)
library(ggplot2)
library(GGally)## Warning: package 'GGally' was built under R version 4.0.5## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2library(Hmisc)## Warning: package 'Hmisc' was built under R version 4.0.5## Loading required package: lattice## Loading required package: survival## Loading required package: Formula## Warning: package 'Formula' was built under R version 4.0.3##
## Attaching package: 'Hmisc'## The following objects are masked from 'package:dplyr':
##
## src, summarize## The following objects are masked from 'package:base':
##
## format.pval, unitslibrary(corrplot)## corrplot 0.90 loadedlibrary(stats)EXPLORACIÓN DE DATOS
Arreglar el Dataset 3 por país, país miembro de la UE, tasa de inflación,
#emprendimiento femenino, tasa laboral femenina y asiganarlo en el objeto df4
df4<-Dataset3 %>% group_by(Country, `European Union Membership`,`Inflation rate`,`Women Entrepreneurship Index`, `Female Labor Force Participation Rate`)
df4## # A tibble: 51 x 9
## # Groups: Country, European Union Membership, Inflation rate, Women
## # Entrepreneurship Index, Female Labor Force Participation Rate [51]
## No Country `Level of develo~ `European Union M~ Currency `Women Entrepren~
## <dbl> <chr> <chr> <chr> <chr> <dbl>
## 1 4 Austria Developed Member Euro 54.9
## 2 6 Belgium Developed Member Euro 63.6
## 3 17 Estonia Developed Member Euro 55.4
## 4 18 Finland Developed Member Euro 66.4
## 5 19 France Developed Member Euro 68.8
## 6 20 Germany Developed Member Euro 63.6
## 7 22 Greece Developed Member Euro 43
## 8 28 Ireland Developed Member Euro 64.3
## 9 30 Italy Developed Member Euro 51.4
## 10 34 Latvia Developed Member Euro 56.6
## # ... with 41 more rows, and 3 more variables: Entrepreneurship Index <dbl>,
## # Inflation rate <dbl>, Female Labor Force Participation Rate <dbl>###ANÁLISIS DE NORMALIDAD DE LAS VARIABLES
shapiro.test(Dataset3$`Women Entrepreneurship Index`)##
## Shapiro-Wilk normality test
##
## data: Dataset3$`Women Entrepreneurship Index`
## W = 0.94077, p-value = 0.01318shapiro.test(Dataset3$`Female Labor Force Participation Rate`)##
## Shapiro-Wilk normality test
##
## data: Dataset3$`Female Labor Force Participation Rate`
## W = 0.85947, p-value = 2.399e-05shapiro.test(Dataset3$`Inflation rate`)##
## Shapiro-Wilk normality test
##
## data: Dataset3$`Inflation rate`
## W = 0.68624, p-value = 3.728e-09shapiro.test(Dataset3$`Entrepreneurship Index`)##
## Shapiro-Wilk normality test
##
## data: Dataset3$`Entrepreneurship Index`
## W = 0.91004, p-value = 0.0009261###Las cuatro variables no son normales, por lo que recurrimos a la ###prueba de Spearman en lugar de Pearson.
ANÁLISIS DE CORRELACIÓN DE SPEARMAN
En el objeto de df10 asigne las variables cuantitativas con las que realizará el
análisis de correlación Inflation rate,Women Entrepreneurship Index, Female Labor Force Participation Rate
df10<-Dataset3[1:51,6:9]
df10 ## # A tibble: 51 x 4
## `Women Entrepreneur~ `Entrepreneurshi~ `Inflation rate` `Female Labor Force ~
## <dbl> <dbl> <dbl> <dbl>
## 1 54.9 64.9 0.9 67.1
## 2 63.6 65.5 0.6 58
## 3 55.4 60.2 -0.88 68.5
## 4 66.4 65.7 -0.2 67.7
## 5 68.8 67.3 0 60.6
## 6 63.6 67.4 0.5 69.9
## 7 43 42 -1.7 42.5
## 8 64.3 65.3 -0.3 59.4
## 9 51.4 41.3 0 47.2
## 10 56.6 54.5 0.2 66.4
## # ... with 41 more rowscor(df10, method = c("spearman"))## Women Entrepreneurship Index
## Women Entrepreneurship Index 1.0000000
## Entrepreneurship Index 0.9077539
## Inflation rate -0.3946565
## Female Labor Force Participation Rate 0.4346547
## Entrepreneurship Index Inflation rate
## Women Entrepreneurship Index 0.9077539 -0.39465651
## Entrepreneurship Index 1.0000000 -0.37079984
## Inflation rate -0.3707998 1.00000000
## Female Labor Force Participation Rate 0.3710827 -0.00493626
## Female Labor Force Participation Rate
## Women Entrepreneurship Index 0.43465472
## Entrepreneurship Index 0.37108270
## Inflation rate -0.00493626
## Female Labor Force Participation Rate 1.00000000rcorr(as.matrix(df10,method = c("spearman")))## Women Entrepreneurship Index
## Women Entrepreneurship Index 1.00
## Entrepreneurship Index 0.91
## Inflation rate -0.46
## Female Labor Force Participation Rate 0.44
## Entrepreneurship Index Inflation rate
## Women Entrepreneurship Index 0.91 -0.46
## Entrepreneurship Index 1.00 -0.40
## Inflation rate -0.40 1.00
## Female Labor Force Participation Rate 0.33 -0.14
## Female Labor Force Participation Rate
## Women Entrepreneurship Index 0.44
## Entrepreneurship Index 0.33
## Inflation rate -0.14
## Female Labor Force Participation Rate 1.00
##
## n= 51
##
##
## P
## Women Entrepreneurship Index
## Women Entrepreneurship Index
## Entrepreneurship Index 0.0000
## Inflation rate 0.0008
## Female Labor Force Participation Rate 0.0012
## Entrepreneurship Index Inflation rate
## Women Entrepreneurship Index 0.0000 0.0008
## Entrepreneurship Index 0.0041
## Inflation rate 0.0041
## Female Labor Force Participation Rate 0.0165 0.3279
## Female Labor Force Participation Rate
## Women Entrepreneurship Index 0.0012
## Entrepreneurship Index 0.0165
## Inflation rate 0.3279
## Female Labor Force Participation Rate####Elabore los gráficos de frecuencia de cada una de las variables
hist(Dataset3$`Women Entrepreneurship Index`)
hist(Dataset3$`Female Labor Force Participation Rate`)
hist(Dataset3$`Inflation rate`)
hist(Dataset3$`Entrepreneurship Index`)
####Elabore el gráfico de frecuencia de cada una de las variables ggplot2 #### con la variable Dataset3\(`Women Entrepreneurship Index` y rellene con la ####variable Dataset3\)“European Union Membership”
library(ggplot2)
ggplot(data = Dataset3,
mapping = aes(x = Dataset3$`Women Entrepreneurship Index`,
fill = Dataset3$"European Union Membership")) +
geom_histogram(bins = 9,
position = 'identity',
alpha = 0.8) +
labs(title = 'Indice de Emprendimiento de las Mujeres',
fill = 'Estados Miembros y No Miembros',
x = "Indice de Emprendimiento",
y = 'Frecuencia de Casos',
subtitle = 'Histograma de Frecuencia',
caption = 'BAse de datos de R "Dataset3 de Kaggle"')
####Elabore el gráfico de frecuencia de cada una de las variables ggplot2 #### con la variable Dataset3\("Entrepreneurship Index" y rellene con la ####variable Dataset3\)“European Union Membership”
library(ggplot2)
ggplot(data = Dataset3,
mapping = aes(x = Dataset3$"Entrepreneurship Index",
fill = Dataset3$"European Union Membership")) +
geom_histogram(bins = 9,
position = 'identity',
alpha = 0.8) +
labs(title = 'Indice de Emprendimiento',
fill = 'Estados Miembros y No Miembros',
x = "Indice de Emprendimiento",
y = 'Frecuencia de Casos',
subtitle = 'Histograma de Frecuencia',
caption = 'BAse de datos de R "Dataset3 de Kaggle"')
####Elabore el gráfico de frecuencia de cada una de las variables ggplot2 #### con la variable Dataset3\("Female Labor Force Participation Rate" y rellene con la ####variable Dataset3\)“European Union Membership”
library(ggplot2)
ggplot(data = Dataset3,
mapping = aes(x = Dataset3$"Female Labor Force Participation Rate",
fill = Dataset3$"European Union Membership")) +
geom_histogram(bins = 9,
position = 'identity',
alpha = 0.8) +
labs(title = 'Tasa de Participación Laboral de la Mujer',
fill = 'Estados Miembros y No Miembros',
x = "Tasa Labora Femenina",
y = 'Frecuencia de Casos',
subtitle = 'Histograma de Frecuencia',
caption = 'BAse de datos de R "Dataset3 de Kaggle"')
####Elabore el gráfico de frecuencia de cada una de las variables ggplot2 #### con la variableDataset3\(`Inflation rate` y rellene con la ####variable Dataset3\)“European Union Membership”
library(ggplot2)
ggplot(data = Dataset3,
mapping = aes(x = Dataset3$`Inflation rate`,
fill = Dataset3$"European Union Membership")) +
geom_histogram(bins = 9,
position = 'identity',
alpha = 0.8) +
labs(title = 'Tasa de de inflación',
fill = 'Estados Miembros y No Miembros',
x = "Inflación %",
y = 'Frecuencia de Casos',
subtitle = 'Histograma de Frecuencia',
caption = 'BAse de datos de R "Dataset3 de Kaggle"')
####Elabore el gráfico de Boxplot del índice de emprendimiento femenino y #### por países miembros y no miembros de la UE
boxplot(Dataset3$`Women Entrepreneurship Index`~Dataset3$`European Union Membership`)
####Elabore el gráfico de dispersión x = Dataset3\(`Entrepreneurship Index`, ####y = Dataset3\)Women Entrepreneurship Indexen ggplot2 #### con la variable Dataset3\(`Inflation rate` y utilice ####facet_grid(Dataset3\)Level of development ~ Dataset3$European Union Membership) ####Tambien utilice la suavización de la línea con intervalos de confianza al 95%
ggplot(Dataset3, aes(x = Dataset3$`Entrepreneurship Index`, y = Dataset3$`Women Entrepreneurship Index`)) +
geom_point() + geom_smooth() + facet_grid(Dataset3$`Level of development` ~ Dataset3$`European Union Membership`)## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#####################Pruebas de Hipótesis t.test Medias############################# #################################################################################### ################################################################################### Dataset3
ICM<-log(Dataset3$`Women Entrepreneurship Index`)
Dataset3<-cbind(Dataset3, ICM)
IC<-log(Dataset3$`Entrepreneurship Index`)
Dataset3<-cbind(Dataset3, ICM)##Normalidad Shapiro de las variables normalizadas
shapiro.test(Dataset3$ICM)##
## Shapiro-Wilk normality test
##
## data: Dataset3$ICM
## W = 0.94269, p-value = 0.01577hist(Dataset3$ICM)
############Recodificación de la variable índice de emprendimiento de la mujer## #####Esta recodificación es necesaria para llevar la prueba de hipótesis de la media
Se calcula la variable indice de emprendimiento de la mujer entre alto y bajo (dicotómico)
ICMM<-ifelse(Dataset3$`Women Entrepreneurship Index`>50.0, 1,0)
Dataset3<-cbind(Dataset3, ICMM)
Dataset3## No Country Level of development European Union Membership
## 1 4 Austria Developed Member
## 2 6 Belgium Developed Member
## 3 17 Estonia Developed Member
## 4 18 Finland Developed Member
## 5 19 France Developed Member
## 6 20 Germany Developed Member
## 7 22 Greece Developed Member
## 8 28 Ireland Developed Member
## 9 30 Italy Developed Member
## 10 34 Latvia Developed Member
## 11 35 Lithuania Developed Member
## 12 39 Netherlands Developed Member
## 13 50 Slovakia Developed Member
## 14 51 Slovenia Developed Member
## 15 53 Spain Developed Member
## 16 12 Croatia Developed Member
## 17 13 Denmark Developed Member
## 18 24 Hungary Developed Member
## 19 44 Poland Developed Member
## 20 54 Sweden Developed Member
## 21 3 Australia Developed Not Member
## 22 25 Iceland Developed Not Member
## 23 32 Japan Developed Not Member
## 24 40 Norway Developed Not Member
## 25 49 Singapore Developed Not Member
## 26 55 Switzerland Developed Not Member
## 27 56 Taiwan Developed Not Member
## 28 1 Algeria Developing Not Member
## 29 2 Argentina Developing Not Member
## 30 7 Bolivia Developing Not Member
## 31 8 Bosnia and Herzegovina Developing Not Member
## 32 9 Brazil Developing Not Member
## 33 10 China Developing Not Member
## 34 11 Costa Rica Developing Not Member
## 35 14 Ecuador Developing Not Member
## 36 15 Egypt Developing Not Member
## 37 16 El Salvador Developing Not Member
## 38 21 Ghana Developing Not Member
## 39 26 India Developing Not Member
## 40 31 Jamaica Developing Not Member
## 41 36 Macedonia Developing Not Member
## 42 37 Malaysia Developing Not Member
## 43 38 Mexico Developing Not Member
## 44 42 Panama Developing Not Member
## 45 43 Peru Developing Not Member
## 46 47 Russia Developing Not Member
## 47 48 Saudi Arabia Developing Not Member
## 48 57 Thailand Developing Not Member
## 49 58 Tunisia Developing Not Member
## 50 59 Turkey Developing Not Member
## 51 60 Uruguay Developing Not Member
## Currency Women Entrepreneurship Index Entrepreneurship Index
## 1 Euro 54.9 64.9
## 2 Euro 63.6 65.5
## 3 Euro 55.4 60.2
## 4 Euro 66.4 65.7
## 5 Euro 68.8 67.3
## 6 Euro 63.6 67.4
## 7 Euro 43.0 42.0
## 8 Euro 64.3 65.3
## 9 Euro 51.4 41.3
## 10 Euro 56.6 54.5
## 11 Euro 58.5 54.6
## 12 Euro 69.3 66.5
## 13 Euro 54.8 45.4
## 14 Euro 55.9 53.1
## 15 Euro 52.5 49.6
## 16 National Currency 49.9 40.6
## 17 National Currency 69.7 71.4
## 18 National Currency 53.7 42.7
## 19 National Currency 57.7 47.4
## 20 National Currency 66.7 71.8
## 21 National Currency 74.8 77.6
## 22 National Currency 68.0 70.4
## 23 National Currency 40.0 49.5
## 24 National Currency 66.3 65.6
## 25 National Currency 59.8 68.1
## 26 National Currency 63.7 68.6
## 27 National Currency 53.4 69.1
## 28 National Currency 27.4 30.2
## 29 National Currency 35.7 37.2
## 30 National Currency 29.7 28.0
## 31 National Currency 31.6 28.9
## 32 National Currency 31.1 25.8
## 33 National Currency 38.3 36.4
## 34 National Currency 36.1 37.7
## 35 National Currency 32.3 28.2
## 36 National Currency 27.7 28.1
## 37 National Currency 29.9 29.6
## 38 National Currency 25.8 24.8
## 39 National Currency 25.3 25.3
## 40 National Currency 38.6 27.2
## 41 National Currency 41.2 37.1
## 42 National Currency 39.2 40.0
## 43 National Currency 42.8 30.7
## 44 National Currency 36.9 32.2
## 45 National Currency 43.6 30.9
## 46 National Currency 35.6 31.7
## 47 National Currency 37.0 49.6
## 48 National Currency 36.6 32.1
## 49 National Currency 30.7 35.5
## 50 National Currency 39.3 54.6
## 51 National Currency 44.5 41.4
## Inflation rate Female Labor Force Participation Rate ICM ICM ICMM
## 1 0.90 67.10 4.005513 4.005513 1
## 2 0.60 58.00 4.152613 4.152613 1
## 3 -0.88 68.50 4.014580 4.014580 1
## 4 -0.20 67.70 4.195697 4.195697 1
## 5 0.00 60.60 4.231204 4.231204 1
## 6 0.50 69.90 4.152613 4.152613 1
## 7 -1.70 42.50 3.761200 3.761200 0
## 8 -0.30 59.40 4.163560 4.163560 1
## 9 0.00 47.20 3.939638 3.939638 1
## 10 0.20 66.40 4.036009 4.036009 1
## 11 -0.90 66.50 4.069027 4.069027 1
## 12 0.60 69.20 4.238445 4.238445 1
## 13 -0.30 55.90 4.003690 4.003690 1
## 14 -0.50 61.00 4.023564 4.023564 1
## 15 -0.50 52.70 3.960813 3.960813 1
## 16 -0.50 60.40 3.910021 3.910021 0
## 17 0.50 70.30 4.244200 4.244200 1
## 18 -0.10 57.80 3.983413 3.983413 1
## 19 -0.90 56.60 4.055257 4.055257 1
## 20 0.00 74.00 4.200205 4.200205 1
## 21 1.50 66.80 4.314818 4.314818 1
## 22 1.60 82.30 4.219508 4.219508 1
## 23 0.80 64.70 3.688879 3.688879 0
## 24 2.17 69.20 4.194190 4.194190 1
## 25 -0.50 59.18 4.091006 4.091006 1
## 26 -1.10 74.70 4.154185 4.154185 1
## 27 -0.61 55.00 3.977811 3.977811 1
## 28 4.80 18.00 3.310543 3.310543 0
## 29 26.50 47.30 3.575151 3.575151 0
## 30 4.10 69.40 3.391147 3.391147 0
## 31 -1.00 51.90 3.453157 3.453157 0
## 32 10.67 55.90 3.437208 3.437208 0
## 33 1.40 62.40 3.645450 3.645450 0
## 34 0.80 59.40 3.586293 3.586293 0
## 35 -0.50 63.50 3.475067 3.475067 0
## 36 11.00 64.60 3.321432 3.321432 0
## 37 -2.25 55.70 3.397858 3.397858 0
## 38 17.20 60.80 3.250374 3.250374 0
## 39 5.90 61.10 3.230804 3.230804 0
## 40 3.70 37.70 3.653252 3.653252 0
## 41 3.70 73.00 3.718438 3.718438 0
## 42 2.30 58.50 3.668677 3.668677 0
## 43 2.70 44.70 3.756538 3.756538 0
## 44 0.10 67.90 3.608212 3.608212 0
## 45 3.50 63.40 3.775057 3.775057 0
## 46 15.50 65.20 3.572346 3.572346 0
## 47 1.20 13.00 3.610918 3.610918 0
## 48 -0.90 62.00 3.600048 3.600048 0
## 49 4.80 25.19 3.424263 3.424263 0
## 50 7.70 30.40 3.671225 3.671225 0
## 51 8.67 68.00 3.795489 3.795489 0Pruebas de las medias entre el índice normalizado ICM y índice alto y bajo de
###competitividad de las mujeres
tt1<-t.test( ICM ~ ICMM ,data=Dataset3)
tt1##
## Welch Two Sample t-test
##
## data: ICM by ICMM
## t = -13.339, df = 43.573, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.6250306 -0.4609106
## sample estimates:
## mean in group 0 mean in group 1
## 3.566261 4.109232Existe diferencia significativa
#Prueba de potencia # Realice la prueba de potencia para el error tipo Beta al 95% con 51 observaciones. #Delta es la diferencia de las medias 3.566261 - 4.109232 (Resultados de la tabla anterior)
Para calcular la desviación estándar que solicita el power.t.test
sdif_1<- tapply(Dataset3$ICM,Dataset3$ICMM, sd)
sdif_1## 0 1
## 0.1778147 0.1079920Un parámetro debe estar en NULL porque es el que vamos a buscar
power.t.test(n=315, delta= -0.542979, sd= 0.00698227, sig.level=0.05,power=NULL, alternative= c("two.sided"))##
## Two-sample t test power calculation
##
## n = 315
## delta = 0.542979
## sd = 0.00698227
## sig.level = 0.05
## power = 1
## alternative = two.sided
##
## NOTE: n is number in *each* group############################REGRESIÓN LINEAL##################### #Aun y cuando vimos que no existe normalidad en las variables de estudio realice un #análisis de regresión lineal.
x<-Dataset3$`Inflation rate`
y<-Dataset3$`Women Entrepreneurship Index`
modelo<-lm(y ~ x)
summary(modelo)##
## Call:
## lm(formula = y ~ x)
##
## Residuals:
## Min 1Q Median 3Q Max
## -23.7791 -10.0047 0.9349 9.8225 25.6508
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 50.9611 1.9974 25.513 < 2e-16 ***
## x -1.2080 0.3372 -3.582 0.000782 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 12.83 on 49 degrees of freedom
## Multiple R-squared: 0.2075, Adjusted R-squared: 0.1913
## F-statistic: 12.83 on 1 and 49 DF, p-value: 0.0007823#Elabore el gráfico de la regresión
plot(x,y)
abline(a=modelo$coefficients[1],b=modelo$coefficients[2])
##Calcule el intervalo de confianza y evalue el modelo
confint(modelo)## 2.5 % 97.5 %
## (Intercept) 46.947176 54.9751120
## x -1.885704 -0.5302744res <- residuals( modelo ) # residuos
pre <- predict(modelo) #predicciones
###Modelo BIC y Modelo AIC
BIC(modelo)## [1] 414.7773AIC(modelo)## [1] 408.9819como saber cual modelo se ajusta mejor
R cuadrado y Rcuadrado ajustado - mas grande mejor (>70)
AIC y BIC - mas pequeño mejor
diagnostico del modelo
una vez tenemos el modelo ajustado procedemos con su
#diagnostico, que se realiza a traves de analisis de residuos
#Elabore un segundo modelo de regersión lineal sin el intercepto para evaluar #R-Squared o el R cuadrado
modelo2<-lm(y ~ 0 + x)
summary(modelo2)##
## Call:
## lm(formula = y ~ 0 + x)
##
## Residuals:
## Min 1Q Median 3Q Max
## -31.91 32.55 47.34 60.78 70.97
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## x 2.551 1.135 2.248 0.029 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 48.01 on 50 degrees of freedom
## Multiple R-squared: 0.09177, Adjusted R-squared: 0.07361
## F-statistic: 5.052 on 1 and 50 DF, p-value: 0.02904plot(x,y)
abline(a=modelo2$coefficients[1],b=modelo$coefficients[2])
############################REGRESIÓN LOGÍSTICA#####################
Representación gráfica del modelo logit simple
##Ajuste de un modelo logístico simple con una variable independiente
Con las estadísticas descriptiva convierta en variable categórica la variable
##f4$Women Entrepreneurship Index, la cual arriba de la media se considera un ##Indice alto de emprendimiento con codificación 1, mientras abajo de ese umbral ## se considera un indice bajo con 0.
summary(Dataset3$`Women Entrepreneurship Index`)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 25.30 36.35 44.50 47.84 59.15 74.80Dataset3$`Women Entrepreneurship Index`<-ifelse(Dataset3$`Women Entrepreneurship Index` >44.5,1,0)
Dataset3## No Country Level of development European Union Membership
## 1 4 Austria Developed Member
## 2 6 Belgium Developed Member
## 3 17 Estonia Developed Member
## 4 18 Finland Developed Member
## 5 19 France Developed Member
## 6 20 Germany Developed Member
## 7 22 Greece Developed Member
## 8 28 Ireland Developed Member
## 9 30 Italy Developed Member
## 10 34 Latvia Developed Member
## 11 35 Lithuania Developed Member
## 12 39 Netherlands Developed Member
## 13 50 Slovakia Developed Member
## 14 51 Slovenia Developed Member
## 15 53 Spain Developed Member
## 16 12 Croatia Developed Member
## 17 13 Denmark Developed Member
## 18 24 Hungary Developed Member
## 19 44 Poland Developed Member
## 20 54 Sweden Developed Member
## 21 3 Australia Developed Not Member
## 22 25 Iceland Developed Not Member
## 23 32 Japan Developed Not Member
## 24 40 Norway Developed Not Member
## 25 49 Singapore Developed Not Member
## 26 55 Switzerland Developed Not Member
## 27 56 Taiwan Developed Not Member
## 28 1 Algeria Developing Not Member
## 29 2 Argentina Developing Not Member
## 30 7 Bolivia Developing Not Member
## 31 8 Bosnia and Herzegovina Developing Not Member
## 32 9 Brazil Developing Not Member
## 33 10 China Developing Not Member
## 34 11 Costa Rica Developing Not Member
## 35 14 Ecuador Developing Not Member
## 36 15 Egypt Developing Not Member
## 37 16 El Salvador Developing Not Member
## 38 21 Ghana Developing Not Member
## 39 26 India Developing Not Member
## 40 31 Jamaica Developing Not Member
## 41 36 Macedonia Developing Not Member
## 42 37 Malaysia Developing Not Member
## 43 38 Mexico Developing Not Member
## 44 42 Panama Developing Not Member
## 45 43 Peru Developing Not Member
## 46 47 Russia Developing Not Member
## 47 48 Saudi Arabia Developing Not Member
## 48 57 Thailand Developing Not Member
## 49 58 Tunisia Developing Not Member
## 50 59 Turkey Developing Not Member
## 51 60 Uruguay Developing Not Member
## Currency Women Entrepreneurship Index Entrepreneurship Index
## 1 Euro 1 64.9
## 2 Euro 1 65.5
## 3 Euro 1 60.2
## 4 Euro 1 65.7
## 5 Euro 1 67.3
## 6 Euro 1 67.4
## 7 Euro 0 42.0
## 8 Euro 1 65.3
## 9 Euro 1 41.3
## 10 Euro 1 54.5
## 11 Euro 1 54.6
## 12 Euro 1 66.5
## 13 Euro 1 45.4
## 14 Euro 1 53.1
## 15 Euro 1 49.6
## 16 National Currency 1 40.6
## 17 National Currency 1 71.4
## 18 National Currency 1 42.7
## 19 National Currency 1 47.4
## 20 National Currency 1 71.8
## 21 National Currency 1 77.6
## 22 National Currency 1 70.4
## 23 National Currency 0 49.5
## 24 National Currency 1 65.6
## 25 National Currency 1 68.1
## 26 National Currency 1 68.6
## 27 National Currency 1 69.1
## 28 National Currency 0 30.2
## 29 National Currency 0 37.2
## 30 National Currency 0 28.0
## 31 National Currency 0 28.9
## 32 National Currency 0 25.8
## 33 National Currency 0 36.4
## 34 National Currency 0 37.7
## 35 National Currency 0 28.2
## 36 National Currency 0 28.1
## 37 National Currency 0 29.6
## 38 National Currency 0 24.8
## 39 National Currency 0 25.3
## 40 National Currency 0 27.2
## 41 National Currency 0 37.1
## 42 National Currency 0 40.0
## 43 National Currency 0 30.7
## 44 National Currency 0 32.2
## 45 National Currency 0 30.9
## 46 National Currency 0 31.7
## 47 National Currency 0 49.6
## 48 National Currency 0 32.1
## 49 National Currency 0 35.5
## 50 National Currency 0 54.6
## 51 National Currency 0 41.4
## Inflation rate Female Labor Force Participation Rate ICM ICM ICMM
## 1 0.90 67.10 4.005513 4.005513 1
## 2 0.60 58.00 4.152613 4.152613 1
## 3 -0.88 68.50 4.014580 4.014580 1
## 4 -0.20 67.70 4.195697 4.195697 1
## 5 0.00 60.60 4.231204 4.231204 1
## 6 0.50 69.90 4.152613 4.152613 1
## 7 -1.70 42.50 3.761200 3.761200 0
## 8 -0.30 59.40 4.163560 4.163560 1
## 9 0.00 47.20 3.939638 3.939638 1
## 10 0.20 66.40 4.036009 4.036009 1
## 11 -0.90 66.50 4.069027 4.069027 1
## 12 0.60 69.20 4.238445 4.238445 1
## 13 -0.30 55.90 4.003690 4.003690 1
## 14 -0.50 61.00 4.023564 4.023564 1
## 15 -0.50 52.70 3.960813 3.960813 1
## 16 -0.50 60.40 3.910021 3.910021 0
## 17 0.50 70.30 4.244200 4.244200 1
## 18 -0.10 57.80 3.983413 3.983413 1
## 19 -0.90 56.60 4.055257 4.055257 1
## 20 0.00 74.00 4.200205 4.200205 1
## 21 1.50 66.80 4.314818 4.314818 1
## 22 1.60 82.30 4.219508 4.219508 1
## 23 0.80 64.70 3.688879 3.688879 0
## 24 2.17 69.20 4.194190 4.194190 1
## 25 -0.50 59.18 4.091006 4.091006 1
## 26 -1.10 74.70 4.154185 4.154185 1
## 27 -0.61 55.00 3.977811 3.977811 1
## 28 4.80 18.00 3.310543 3.310543 0
## 29 26.50 47.30 3.575151 3.575151 0
## 30 4.10 69.40 3.391147 3.391147 0
## 31 -1.00 51.90 3.453157 3.453157 0
## 32 10.67 55.90 3.437208 3.437208 0
## 33 1.40 62.40 3.645450 3.645450 0
## 34 0.80 59.40 3.586293 3.586293 0
## 35 -0.50 63.50 3.475067 3.475067 0
## 36 11.00 64.60 3.321432 3.321432 0
## 37 -2.25 55.70 3.397858 3.397858 0
## 38 17.20 60.80 3.250374 3.250374 0
## 39 5.90 61.10 3.230804 3.230804 0
## 40 3.70 37.70 3.653252 3.653252 0
## 41 3.70 73.00 3.718438 3.718438 0
## 42 2.30 58.50 3.668677 3.668677 0
## 43 2.70 44.70 3.756538 3.756538 0
## 44 0.10 67.90 3.608212 3.608212 0
## 45 3.50 63.40 3.775057 3.775057 0
## 46 15.50 65.20 3.572346 3.572346 0
## 47 1.20 13.00 3.610918 3.610918 0
## 48 -0.90 62.00 3.600048 3.600048 0
## 49 4.80 25.19 3.424263 3.424263 0
## 50 7.70 30.40 3.671225 3.671225 0
## 51 8.67 68.00 3.795489 3.795489 0table(Dataset3$`Women Entrepreneurship Index`)##
## 0 1
## 26 25boxplot(Dataset3$`Inflation rate`~Dataset3$`Women Entrepreneurship Index`, Dataset3)
modelo_logit1 <- glm(Dataset3$`Women Entrepreneurship Index` ~ Dataset3$`Inflation rate`,
data = Dataset3, family = "binomial")
summary(modelo_logit1)##
## Call:
## glm(formula = Dataset3$`Women Entrepreneurship Index` ~ Dataset3$`Inflation rate`,
## family = "binomial", data = Dataset3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.10469 -0.64982 -0.00066 0.85234 1.43209
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.7347 0.3712 1.979 0.04779 *
## Dataset3$`Inflation rate` -0.6065 0.2144 -2.828 0.00468 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 70.681 on 50 degrees of freedom
## Residual deviance: 50.488 on 49 degrees of freedom
## AIC: 54.488
##
## Number of Fisher Scoring iterations: 6###Evaluación del modelo Logit simple #1
Diferencia de residuos
En R, un objeto glm almacena la “deviance” del modelo, así como la “deviance”
del modelo nulo.
#dif_residuos1 <- modelo_logit1\(null.deviance - modelo_logit1\)deviance
Grados libertad
#df1 <- modelo_logit1\(df.null - modelo_logit1\)df.residual
p-value
#p_value1 <- pchisq(q = dif_residuos1,df = df1, lower.tail = FALSE)
#p_value1
dif_residuos1 <- modelo_logit1$null.deviance - modelo_logit1$deviance
# Grados libertad
df1 <- modelo_logit1$df.null - modelo_logit1$df.residual
# p-value
p_value1 <- pchisq(q = dif_residuos1,df = df1, lower.tail = FALSE)
p_value1## [1] 6.998e-06#Calcule el intervalo de confianza del modelo
confint(object = modelo_logit1, level = 0.95)## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## 2.5 % 97.5 %
## (Intercept) 0.0376576 1.5106602
## Dataset3$`Inflation rate` -1.1056479 -0.2579834#si alguien tiene una inflación de 3.0, cual es la #probabilidad de tener un indice alto
inflación<-3.0##La probabilidad es:
exp(0.7347-0.6065*(inflación))/(1+exp(0.7347-0.6065*(inflación)))*100## [1] 25.25987#######################Modelo Logit Múltiple No.2 ################################
modelo_logit <- glm(`Women Entrepreneurship Index` ~ `Inflation rate` +
`Female Labor Force Participation Rate`,
data = Dataset3, family = "binomial")
summary(modelo_logit)##
## Call:
## glm(formula = `Women Entrepreneurship Index` ~ `Inflation rate` +
## `Female Labor Force Participation Rate`, family = "binomial",
## data = Dataset3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.97313 -0.46280 -0.00006 0.79328 1.55737
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -6.44365 3.37142 -1.911 0.0560 .
## `Inflation rate` -0.73190 0.29208 -2.506 0.0122 *
## `Female Labor Force Participation Rate` 0.11830 0.05557 2.129 0.0333 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 70.681 on 50 degrees of freedom
## Residual deviance: 42.644 on 48 degrees of freedom
## AIC: 48.644
##
## Number of Fisher Scoring iterations: 7#Una forma para mejorar la interpretación de los exponentes es elevarlos exp
exp(coefficients(modelo_logit))## (Intercept) `Inflation rate`
## 0.001590594 0.480995725
## `Female Labor Force Participation Rate`
## 1.125585100##El comando confint muestra el intervalo de confianza del modelo Logit
confint(modelo_logit)## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## 2.5 % 97.5 %
## (Intercept) -14.11299093 -0.9113272
## `Inflation rate` -1.42420583 -0.2788619
## `Female Labor Force Participation Rate` 0.02808125 0.2457519###Evaluación del modelo Logit multiple
Diferencia de residuos
En R, un objeto glm almacena la “deviance” del modelo, así como la “deviance”
del modelo nulo.
dif_residuos <- modelo_logit\(null.deviance - modelo_logit\)deviance
Grados libertad
df <- modelo_logit\(df.null - modelo_logit\)df.residual
p-value
p_value <- pchisq(q = dif_residuos,df = df, lower.tail = FALSE)
p_value
si el p valor < 0.05 es estadisticamente significativo el modelo
dif_residuos <- modelo_logit$null.deviance - modelo_logit$deviance
# Grados libertad
df <- modelo_logit$df.null - modelo_logit$df.residual
# p-value
p_value <- pchisq(q = dif_residuos,df = df, lower.tail = FALSE)
p_value## [1] 8.163183e-07