#PRACTICA 1
Mujeres = c(75,77,78,79,77,73,78,79,78,80)
Hombres= c(74,72,77,76,76,73,75,73,74,75)
datos<-data.frame(Mujeres=Mujeres, Hombres=Hombres)
resultado <-t.test(Mujeres,Hombres,
alternative="two.sided",
var.equal=FALSE)
resultado
##
## Welch Two Sample t-test
##
## data: Mujeres and Hombres
## t = 3.5254, df = 16.851, p-value = 0.002626
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 1.163304 4.636696
## sample estimates:
## mean of x mean of y
## 77.4 74.5
Mujeres = c(75,77,78,79,77,73,78,79,78,80)
Hombres= c(74,72,77,76,76,73,75,73,74,75)
Sexo<-c(rep("Mujer",10), rep("Hombre",10))
Temp<-c(Mujeres,Hombres)
datos<-data.frame(Sexo=Sexo,T=Temp)
resultado<-t.test(Mujeres,Hombres,
alternative="two.sided",
var.equal=FALSE)
print(resultado)
##
## Welch Two Sample t-test
##
## data: Mujeres and Hombres
## t = 3.5254, df = 16.851, p-value = 0.002626
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 1.163304 4.636696
## sample estimates:
## mean of x mean of y
## 77.4 74.5
datos
## Sexo T
## 1 Mujer 75
## 2 Mujer 77
## 3 Mujer 78
## 4 Mujer 79
## 5 Mujer 77
## 6 Mujer 73
## 7 Mujer 78
## 8 Mujer 79
## 9 Mujer 78
## 10 Mujer 80
## 11 Hombre 74
## 12 Hombre 72
## 13 Hombre 77
## 14 Hombre 76
## 15 Hombre 76
## 16 Hombre 73
## 17 Hombre 75
## 18 Hombre 73
## 19 Hombre 74
## 20 Hombre 75
datos$Sexo<-factor(datos$Sexo)
boxplot(T~Sexo,data=datos,col=c("orange","purple"))
library(car)
## Cargando paquete requerido: carData
leveneTest(T~Sexo,data=datos,center=mean)
## Levene's Test for Homogeneity of Variance (center = mean)
## Df F value Pr(>F)
## group 1 0.2085 0.6534
## 18
#PROBLEMA 2
actual<-c(1.88,1.84,1.83,1.90,2.19,1.89,2.27,2.03,1.96,1.98,2.00,1.92,1.83,1.94,1.94,1.95,1.93,2.01)
nuevo<-c(1.87,1.9,1.85,1.88,2.18,1.87,2.23,1.97,2.00,1.98,1.99,1.89,1.78,1.92,2.02,2.00,1.95,2.05)
resultado<-t.test(actual,nuevo,
alternative="two.sided", paired=T,
var.equal=F)
resultado
##
## Paired t-test
##
## data: actual and nuevo
## t = -0.23874, df = 17, p-value = 0.8142
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
## -0.02186024 0.01741580
## sample estimates:
## mean difference
## -0.002222222
PROBLEMA 3
desgaste<-c(264, 260, 258, 241, 262, 255,208, 220, 216, 200, 213, 206,220, 263, 219, 225, 230, 228,217, 226, 215, 227, 220, 222)
tipoCuero<-c(rep("A",6),rep("B",6),rep("C",6),rep("D",6))
datos<-data.frame(tipoCuero=tipoCuero,desgaste=desgaste)
datos
## tipoCuero desgaste
## 1 A 264
## 2 A 260
## 3 A 258
## 4 A 241
## 5 A 262
## 6 A 255
## 7 B 208
## 8 B 220
## 9 B 216
## 10 B 200
## 11 B 213
## 12 B 206
## 13 C 220
## 14 C 263
## 15 C 219
## 16 C 225
## 17 C 230
## 18 C 228
## 19 D 217
## 20 D 226
## 21 D 215
## 22 D 227
## 23 D 220
## 24 D 222
datos$tipoCuero<-factor(datos$tipoCuero)
modelo<-aov(desgaste~tipoCuero, data=datos)
summary(modelo)
## Df Sum Sq Mean Sq F value Pr(>F)
## tipoCuero 3 7019 2339.8 22.75 1.18e-06 ***
## Residuals 20 2056 102.8
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
boxplot(desgaste~tipoCuero, data=datos, col=c("yellow","black", "green","red"))
plot(modelo)
shapiro.test(modelo$residuals)
##
## Shapiro-Wilk normality test
##
## data: modelo$residuals
## W = 0.88326, p-value = 0.00967
hist(modelo$residuals,breaks = 8)
TukeyHSD(modelo)
## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = desgaste ~ tipoCuero, data = datos)
##
## $tipoCuero
## diff lwr upr p adj
## B-A -46.166667 -62.552998 -29.780336 0.0000008
## C-A -25.833333 -42.219664 -9.447002 0.0014117
## D-A -35.500000 -51.886331 -19.113669 0.0000349
## C-B 20.333333 3.947002 36.719664 0.0118160
## D-B 10.666667 -5.719664 27.052998 0.2926431
## D-C -9.666667 -26.052998 6.719664 0.3742863
esta prueba solo se utiliza cuando hay diferencias significativas debe ser igual con el boxplot
#RegresionLineal
x1<-seq(0,10,length=10)
y<-0.8+2.3*x1
y<-y+rnorm(1,0,0.8)
plot(x1,y)
modelo<-lm(y~x1)
summary(modelo)
## Warning in summary.lm(modelo): essentially perfect fit: summary may be
## unreliable
##
## Call:
## lm(formula = y ~ x1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.833e-15 -4.576e-16 -1.742e-16 7.768e-16 1.449e-15
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.705e+00 6.493e-16 2.625e+15 <2e-16 ***
## x1 2.300e+00 1.095e-16 2.101e+16 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.105e-15 on 8 degrees of freedom
## Multiple R-squared: 1, Adjusted R-squared: 1
## F-statistic: 4.415e+32 on 1 and 8 DF, p-value: < 2.2e-16