#Examen PyE 3 Unidad
#Elba María Ybarra
#2. Muestreo Aleatorio Simple
crimenes <- data.frame(crimtab)
dim(crimenes)
## [1] 924 3
n <- 50
crime <- sample(1:nrow(crimenes), size = n, replace = FALSE)
crime
## [1] 246 907 53 170 580 663 803 573 523 202 858 99 645 263 355 257 722
## [18] 723 751 578 483 330 540 608 905 834 815 809 100 563 430 909 893 655
## [35] 83 8 368 14 712 498 57 380 487 860 729 408 618 767 880 383
crimes <- crimenes[crime,]
head(crimes)
## Var1 Var2 Freq
## 246 12.9 154.94 0
## 907 11.8 195.58 0
## 53 10.4 144.78 0
## 170 9.5 152.4 0
## 580 12.7 175.26 5
## 663 12.6 180.34 6
#3. Muestreo Aleatorio sin Reemplazo
library(dplyr)
## Warning: package 'dplyr' was built under R version 3.5.3
##
## 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
crime.sin <- crimenes %>%
sample_n(size = n, replace = FALSE)
head(crime.sin)
## Var1 Var2 Freq
## 1 9.5 182.88 0
## 2 10 175.26 0
## 3 11.1 157.48 22
## 4 9.5 177.8 0
## 5 12.3 147.32 0
## 6 9.5 149.86 0
#4. Muestreo con Ponderaciones
crime.pesos <- crimenes %>%
sample_frac(0.04)
head(crime.pesos); dim(crime.pesos)
## Var1 Var2 Freq
## 1 11.1 187.96 0
## 2 11 157.48 15
## 3 13.4 147.32 0
## 4 11.9 193.04 0
## 5 10.2 180.34 0
## 6 12.6 147.32 0
## [1] 37 3
#5.Muestreo Estratificado
library(dplyr)
set.seed(1)
sample_iris <- iris %>%
group_by(Species) %>%
sample_n(10)
sample_iris
## # A tibble: 30 x 5
## # Groups: Species [3]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## <dbl> <dbl> <dbl> <dbl> <fct>
## 1 4.3 3 1.1 0.1 setosa
## 2 5.7 3.8 1.7 0.3 setosa
## 3 5.2 3.5 1.5 0.2 setosa
## 4 4.4 3.2 1.3 0.2 setosa
## 5 4.9 3.1 1.5 0.1 setosa
## 6 5 3.5 1.3 0.3 setosa
## 7 4.5 2.3 1.3 0.3 setosa
## 8 5.2 3.4 1.4 0.2 setosa
## 9 5 3.4 1.6 0.4 setosa
## 10 4.7 3.2 1.3 0.2 setosa
## # ... with 20 more rows
#6. Prueba de Hipotesis y Normalidad
library(readxl)
correlacion <- read_excel("correlacion.xlsx")
View(correlacion)
boxplot(correlacion$chino ~ correlacion$cerdo, col = "pink")
#Prueba de Normalidad Shapiro Wilk
shapiro.test(correlacion$cerdo)
##
## Shapiro-Wilk normality test
##
## data: correlacion$cerdo
## W = 0.76938, p-value = 1.228e-10