#UNIVERSIDAD NACIONAL DEL ALTIPLANO
#REGRESION AVANZADA
#FINESI
#TEMA: Variables Dummy
#Caso1
library(readxl)
## Warning: package 'readxl' was built under R version 4.0.2
Caso1 <- read_excel("D:/VII-RA/Caso1.xlsx")
Caso1
## # A tibble: 26 x 4
## Individuo CP GIM Grupo
## <dbl> <dbl> <dbl> <dbl>
## 1 1 -4 -7.44 0
## 2 2 -5.2 -6.29 0
## 3 3 -9.2 -8.99 0
## 4 4 -5.9 -4.27 0
## 5 5 -7.2 -8.08 0
## 6 6 -6.3 -10.5 0
## 7 7 -4.7 -3.11 0
## 8 8 -9.3 -6.66 0
## 9 9 -4.9 -5.75 0
## 10 10 0.4 -5.33 0
## # ... with 16 more rows
View(Caso1)
Grupo <- as.factor(Caso1$Grupo)
Grupo
## [1] 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1
## Levels: 0 1
#VARIABLES
y<- Caso1$CP
y
## [1] -4.0 -5.2 -9.2 -5.9 -7.2 -6.3 -4.7 -9.3 -4.9 0.4 -2.7 -10.4
## [13] -1.7 0.2 -2.7 -2.8 -1.8 -2.2 -0.3 -0.9 -0.4 -1.7 -2.7 1.3
## [25] 1.0 0.3
x<- Caso1$GIM
x
## [1] -7.4420 -6.2894 -8.9897 -4.2663 -8.0755 -10.5133 -3.1076 -6.6595
## [9] -5.7514 -5.3274 -10.5106 -14.9994 -2.5526 -0.9783 0.0000 0.0000
## [17] 0.4440 1.3548 -0.9278 -0.7464 1.9881 -0.9783 1.3591 0.9031
## [25] -1.4125 0.1430
#MODELO
mod<- lm(y~x+Grupo)
mod
##
## Call:
## lm(formula = y ~ x + Grupo)
##
## Coefficients:
## (Intercept) x Grupo1
## -2.4374 0.4171 1.4236
#ANOVA
summary(mod)
##
## Call:
## lm(formula = y ~ x + Grupo)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.0846 -1.6854 -0.1773 1.4699 5.0597
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.4374 1.4432 -1.689 0.1047
## x 0.4171 0.1794 2.325 0.0293 *
## Grupo1 1.4236 1.5832 0.899 0.3779
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.229 on 23 degrees of freedom
## Multiple R-squared: 0.5804, Adjusted R-squared: 0.5439
## F-statistic: 15.91 on 2 and 23 DF, p-value: 4.602e-05
#GRAFICO Y VARIABLE DUMMY
plot(y~x,pch=as.character(Grupo))
coef(mod)
## (Intercept) x Grupo1
## -2.4373979 0.4171451 1.4236121
abline(-2.4373979, 0.4171451, col="blue")
abline(-2.4373979, 1.4236121, col="red")
#Caso2
library(readxl)
Caso2 <- read_excel("D:/VII-RA/Caso2.xlsx")
Caso2
## # A tibble: 15 x 4
## Individuo y x Sexo
## <dbl> <dbl> <dbl> <dbl>
## 1 1 41 1.05 1
## 2 2 46.2 0.46 1
## 3 3 44.3 0.580 1
## 4 4 53.1 0.7 1
## 5 5 57.8 1.07 1
## 6 6 48.4 0.68 1
## 7 7 31.3 0.71 1
## 8 8 39.6 0.87 1
## 9 9 21.8 0.73 0
## 10 10 49.1 0.72 0
## 11 11 47.4 0.82 0
## 12 12 27.3 0.54 0
## 13 13 39.7 0.580 0
## 14 14 48.5 1.53 0
## 15 15 39.7 0.53 0
View(Caso2)
Sexo <- as.factor(Caso2$Sexo)
Sexo
## [1] 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0
## Levels: 0 1
#VARIABLES
y<- Caso2$y
y
## [1] 41.0 46.2 44.3 53.1 57.8 48.4 31.3 39.6 21.8 49.1 47.4 27.3 39.7 48.5 39.7
x<- Caso2$x
x
## [1] 1.05 0.46 0.58 0.70 1.07 0.68 0.71 0.87 0.73 0.72 0.82 0.54 0.58 1.53 0.53
#MODELO
mod<- lm(y~x+Sexo)
mod
##
## Call:
## lm(formula = y ~ x + Sexo)
##
## Coefficients:
## (Intercept) x Sexo1
## 30.156 11.451 6.296
#ANOVA
summary(mod)
##
## Call:
## lm(formula = y ~ x + Sexo)
##
## Residuals:
## Min 1Q Median 3Q Max
## -16.715 -7.146 2.902 6.167 10.699
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 30.156 7.853 3.840 0.00235 **
## x 11.451 9.024 1.269 0.22854
## Sexo1 6.296 4.804 1.311 0.21451
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.279 on 12 degrees of freedom
## Multiple R-squared: 0.2129, Adjusted R-squared: 0.08168
## F-statistic: 1.623 on 2 and 12 DF, p-value: 0.2378
#GRAFICO Y VARIABLE DUMMY
plot(y~x,pch=as.character(Sexo))
coef(mod)
## (Intercept) x Sexo1
## 30.155834 11.451223 6.296481
abline(30.155834, 11.451223, col="blue")
abline(30.155834, 6.296481, col="red")
#Caso3
library(readxl)
Caso3 <- read_excel("D:/VII-RA/Caso3.xlsx")
Caso3
## # A tibble: 28 x 3
## Biorretroalimentacion Calificacion Numero
## <chr> <dbl> <dbl>
## 1 Si 255 88
## 2 Si 88 102
## 3 No 162 73
## 4 Si 90 105
## 5 No 245 51
## 6 Si 150 52
## 7 Si 87 106
## 8 Si 212 76
## 9 Si 112 100
## 10 Si 77 112
## # ... with 18 more rows
View(Caso3)
Biorretroalimentacion <- as.factor(Caso3$Biorretroalimentacion)
Biorretroalimentacion
## [1] Si Si No Si No Si Si Si Si Si No No No Si No Si No Si No Si No No No No Si
## [26] Si No Si
## Levels: No Si
#VARIABLES
y<- Caso3$Numero
y
## [1] 88 102 73 105 51 52 106 76 100 112 89 52 49 75 50 75 75 112 55
## [20] 115 50 87 106 91 75 70 100 100
x<- Caso3$Calificacion
x
## [1] 255 88 162 90 245 150 87 212 112 77 137 171 199 137 149 251 102 90 180
## [20] 25 142 88 87 101 211 136 100 100
#MODELO
mod<- lm(y~x+Biorretroalimentacion)
mod
##
## Call:
## lm(formula = y ~ x + Biorretroalimentacion)
##
## Coefficients:
## (Intercept) x BiorretroalimentacionSi
## 105.355 -0.237 17.450
#ANOVA
summary(mod)
##
## Call:
## lm(formula = y ~ x + Biorretroalimentacion)
##
## Residuals:
## Min 1Q Median 3Q Max
## -35.248 -8.061 2.977 7.983 25.642
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 105.35487 7.96910 13.220 8.76e-13 ***
## x -0.23704 0.04788 -4.951 4.23e-05 ***
## BiorretroalimentacionSi 17.44955 5.55260 3.143 0.00428 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 14.61 on 25 degrees of freedom
## Multiple R-squared: 0.5961, Adjusted R-squared: 0.5637
## F-statistic: 18.44 on 2 and 25 DF, p-value: 1.2e-05
#GRAFICO Y VARIABLE DUMMY
plot(y~x,pch=as.character(Biorretroalimentacion))
coef(mod)
## (Intercept) x BiorretroalimentacionSi
## 105.3548742 -0.2370442 17.4495491
abline(105.3548742, -0.2370442, col="blue")
abline(105.3548742, 17.4495491, col="red")
