Taller

2023-11-01

estaturas <- rnorm(n = 10000, mean = 176, sd = 15)

cat("la media de las estaturas es: ", round(mean(estaturas),0)," y ","la desviación estándar de las esta

## la media de las estaturas es: 176 y la desviación estándar de las estaturas es: 15
library(ggplot2)
qplot(estaturas, geom = "histogram", bins = 30, main="Histograma de las estaturas", xlab="Estaturas", fi

## Warning: `qplot()` was deprecated in ggplot2 3.4.0.

## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
Histograma de las estaturas

900

600

300

100 150 200

Estaturas
n <- c(5, 11, 17, 23, 31)
t <- c(10, 100, 1000, 10000)

muestras.de.estaturas <- data.frame()

for(i in n) {

1
 col <- c()
for(j in t) {
trial <- 1:j
counter <- j
value <- c()
while(counter > 0) {
bucket <- sample(estaturas, i, replace = TRUE)
sbar <- sd(bucket)
value <- c(value, sbar)
counter <- counter - 1
}
col <- cbind(trial, value, sbar, i, j)
muestras.de.estaturas <- rbind(muestras.de.estaturas, col)
}
}

rm(col, bucket, value, counter, i, j, n, sbar, t, sbar, trial)

## Warning in rm(col, bucket, value, counter, i, j, n, sbar, t, sbar, trial):

## object 'sbar' not found
str(muestras.de.estaturas)

## 'data.frame': 55550 obs. of 5 variables:

## $ trial: num 1 2 3 4 5 6 7 8 9 10 ...
## $ value: num 19.61 10.19 16.22 9.28 8.82 ...
## $ sbar : num 13.7 13.7 13.7 13.7 13.7 ...
## $ i : num 5 5 5 5 5 5 5 5 5 5 ...
## $ j : num 10 10 10 10 10 10 10 10 10 10 ...
names(muestras.de.estaturas) <- c("trial#", "value", "sdev", "samples", "trials")

g <- ggplot(muestras.de.estaturas, aes(x = value)) + geom_density(fill = "purple") +

facet_grid(samples ~ trials, labeller = label_both) +
ggtitle("Distribución de la varianza poblacional simulada") +
geom_vline(xintercept = round(mean(estaturas),1), linetype = "dashed")
g

2
 Distribución de la varianza poblacional simulada
trials: 10 trials: 100 trials: 1000 trials: 10000
0.4

samples: 5 samples: 11 samples: 17 samples: 23 samples: 31

0.3
0.2
0.1
0.0
0.4
0.3
0.2
0.1
0.0
0.4
density

0.3
0.2
0.1
0.0
0.4
0.3
0.2
0.1
0.0
0.4
0.3
0.2
0.1
0.0
0 50 100 150 0 50 100 150 0 50 100 150 0 50 100 150
value
ingresos <- rexp(n = 10000, rate = 1/980657)
cat("la media de los ingresos es: ", round(mean(ingresos),0)," y ","la desviación estándar de los ingres

## la media de los ingresos es: 966085 y la desviación estándar de los ingresos es: 969816
library(ggplot2)
qplot(ingresos, geom = "histogram", bins = 30, main="Histograma de los ingresos", xlab="Ingresos", fill=

3
 Histograma de los ingresos

2000

1000

0e+00 3e+06 6e+06 9e+06

Ingresos
n <- c(5, 11, 17, 23, 31)
t <- c(10, 100, 1000, 10000)

muestras.de.ingresos <- data.frame()

for(i in n) {
col <- c()
for(j in t) {
trial <- 1:j
counter <- j
value <- c()
while(counter > 0) {
bucket <- sample(ingresos, i, replace = TRUE)
sbar <- sd(bucket)
value <- c(value, sbar)
counter <- counter - 1
}
sbar <- sd(value)
col <- cbind(trial, value, sbar, i, j)
muestras.de.ingresos <- rbind(muestras.de.ingresos, col)
}
}

rm(col, bucket, value, counter, i, j, n, sbar, t, xbar, trial)

## Warning in rm(col, bucket, value, counter, i, j, n, sbar, t, xbar, trial):

## object 'xbar' not found

4
str(muestras.de.ingresos)

## 'data.frame': 55550 obs. of 5 variables:

## $ trial: num 1 2 3 4 5 6 7 8 9 10 ...
## $ value: num 802084 405943 1165363 471261 3241518 ...
## $ sbar : num 931579 931579 931579 931579 931579 ...
## $ i : num 5 5 5 5 5 5 5 5 5 5 ...
## $ j : num 10 10 10 10 10 10 10 10 10 10 ...
names(muestras.de.ingresos) <- c("trial#", "value", "sdev", "samples", "trials")

g <- ggplot(muestras.de.ingresos, aes(x = value)) + geom_density(fill = "brown") +

facet_grid(samples ~ trials, labeller = label_both) +
ggtitle("Distribución de la varianza poblacional simulada") +
geom_vline(xintercept = round(sd(ingresos),1), linetype = "dashed") +
scale_x_continuous(expand = c(0, 1000000))
g

Distribución de la varianza poblacional simulada

trials: 10 trials: 100 trials: 1000 trials: 10000
2.0e−06

samples: 5 samples: 11 samples: 17 samples: 23 samples: 31

1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
density

1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
1.5e−06
1.0e−06
5.0e−07
0.0e+00
0e+00 2e+06 4e+06 0e+00 2e+06 4e+06 0e+00 2e+06 4e+06 0e+00 2e+06 4e+06
value
ingresos <- rexp(n = 10000, rate = 1/980657)
cat("la media de los ingresos es: ", round(mean(ingresos),0)," y ","la desviación estándar de los ingres

## la media de los ingresos es: 990505 y la desviación estándar de los ingresos es: 977635
library(ggplot2)
qplot(ingresos, geom = "histogram", bins = 30, main="Histograma de los ingresos", xlab="Ingresos", fill=

5
 Histograma de los ingresos

2000

1500

1000

500

0 2500000 5000000 7500000

Ingresos
n <- c(17, 23, 31, 41, 47)
t <- c(10, 100, 1000, 10000)

muestras.de.ingresos <- data.frame()

for(i in n) {
col <- c()
for(j in t) {
trial <- 1:j
counter <- j
value <- c()
while(counter > 0) {
bucket <- sample(ingresos, i, replace = TRUE)
sbar <- sd(bucket)
value <- c(value, sbar)
counter <- counter - 1
}
sbar <- sd(value)
col <- cbind(trial, value, sbar, i, j)
muestras.de.ingresos <- rbind(muestras.de.ingresos, col)
}
}

rm(col, bucket, value, counter, i, j, n, sbar, t, xbar, trial)

## Warning in rm(col, bucket, value, counter, i, j, n, sbar, t, xbar, trial):

## object 'xbar' not found

6
str(muestras.de.ingresos)

## 'data.frame': 55550 obs. of 5 variables:

## $ trial: num 1 2 3 4 5 6 7 8 9 10 ...
## $ value: num 829313 1384223 913049 1093447 863818 ...
## $ sbar : num 286839 286839 286839 286839 286839 ...
## $ i : num 17 17 17 17 17 17 17 17 17 17 ...
## $ j : num 10 10 10 10 10 10 10 10 10 10 ...
names(muestras.de.ingresos) <- c("trial#", "value", "sdev", "samples", "trials")

g <- ggplot(muestras.de.ingresos, aes(x = value)) + geom_density(fill = "violet") +

facet_grid(samples ~ trials, labeller = label_both) +
ggtitle("Distribución de la varianza poblacional simulada") +
geom_vline(xintercept = round(sd(ingresos),1), linetype = "dashed") +
scale_x_continuous(expand = c(0, 1000000))
g

Distribución de la varianza poblacional simulada

trials: 10 trials: 100 trials: 1000 trials: 10000

samples: 17 samples: 23 samples: 31 samples: 41 samples: 47

2.0e−06
1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
density

1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
1.5e−06
1.0e−06
5.0e−07
0.0e+00
2.0e−06
1.5e−06
1.0e−06
5.0e−07
0.0e+00
0e+001e+062e+063e+06 0e+001e+062e+063e+06 0e+001e+062e+063e+06 0e+001e+062e+063e+06
value
set.seed(555)
MuestraMunicipios <- round(rnorm(n = 150, mean = 2.68, sd = 0.5), 2) ; MuestraMunicipios

## [1] 2.52 2.93 2.87 3.62 1.79 3.12 2.60 3.36 2.70 2.99 2.54 2.35 2.18 2.25 2.34
## [16] 2.64 2.81 2.30 1.96 2.94 3.03 2.91 2.10 3.32 2.15 2.70 3.02 2.63 2.58 3.40
## [31] 2.58 2.53 2.81 2.55 2.53 2.77 2.46 2.96 2.38 2.19 3.79 3.39 3.12 2.50 2.23
## [46] 2.85 2.88 2.51 3.81 1.12 3.25 2.72 2.82 2.57 2.60 2.20 3.23 2.35 2.12 2.71
## [61] 2.87 3.00 2.02 3.18 3.40 2.36 2.64 3.10 3.71 2.20 2.11 2.48 3.07 2.60 1.93
## [76] 2.31 2.85 2.84 3.31 2.64 1.76 3.33 2.98 2.12 2.77 3.35 2.79 2.06 2.25 2.79
## [91] 2.72 1.90 2.85 3.28 2.77 3.06 3.06 2.53 1.91 3.18 2.28 1.92 2.70 3.00 4.39

7
## [106] 2.29 2.62 2.72 2.95 2.74 2.81 2.40 3.05 1.81 2.04 2.76 3.27 3.00 2.75 1.84
## [121] 2.64 2.42 3.02 3.30 3.22 2.33 2.18 3.01 2.79 2.61 3.70 2.59 3.33 2.32 2.30
## [136] 1.73 1.99 2.85 2.61 3.21 2.17 1.52 2.23 2.64 2.35 2.36 3.86 3.17 2.24 2.22
VarianzaMunicipal_X <- round(var(MuestraMunicipios), 2) ; VarianzaMunicipal_X

## [1] 0.26
size <- length(MuestraMunicipios) ; size

## [1] 150
df <- length(MuestraMunicipios)-1 ; df

## [1] 149
nivel.conf <- 0.9; chi_alfa_0_5 <- qchisq(1 - (1 + nivel.conf)/2, df, TRUE); chi_alfa_0_5

## [1] 122.6049
nivel.conf <- 0.9; chi_alfa_9_5 <- qchisq((1 + nivel.conf)/2, df, TRUE); chi_alfa_9_5

## [1] 179.6825
Int.inf <- (df*VarianzaMunicipal_X)/(chi_alfa_9_5) ; Int.inf

## [1] 0.2156025
Int.sup <- (df*VarianzaMunicipal_X)/(chi_alfa_0_5) ; Int.sup

## [1] 0.3159742
c(Int.inf, Int.sup)

## [1] 0.2156025 0.3159742

library(mosaic)

## Registered S3 method overwritten by 'mosaic':

## method from
## fortify.SpatialPolygonsDataFrame ggplot2
##
## The 'mosaic' package masks several functions from core packages in order to add
## additional features. The original behavior of these functions should not be affected by this.
##
## Attaching package: 'mosaic'
## The following objects are masked from 'package:dplyr':
##
## count, do, tally
## The following object is masked from 'package:Matrix':
##
## mean
## The following object is masked from 'package:ggplot2':
##
## stat
## The following objects are masked from 'package:stats':
##
## binom.test, cor, cor.test, cov, fivenum, IQR, median, prop.test,

8
## quantile, sd, t.test, var
## The following objects are masked from 'package:base':
##
## max, mean, min, prod, range, sample, sum
(df*VarianzaMunicipal_X)/cdist( "chisq", .90, df=149, lower.tail=FALSE)

0.020

0.015

probability
density

A:0.900

0.010 B:0.100

0.005

0.000

120 160 200

## [1] 0.2170486 0.3180962

nivel.conf <- 0.98; chi_alfa_9_5 <- qchisq((1 + nivel.conf)/2, df, TRUE); chi_alfa_9_5

## [1] 193.361
nivel.conf <- 0.95; chi_alfa_9_5 <- qchisq((1 + nivel.conf)/2, df, TRUE); chi_alfa_9_5

## [1] 185.9255
nivel.conf <- 0.94; chi_alfa_9_5 <- qchisq((1 + nivel.conf)/2, df, TRUE); chi_alfa_9_5

## [1] 184.3438
nivel.conf <- 0.9; chi_alfa_9_5 <- qchisq((1 + nivel.conf)/2, df, TRUE); chi_alfa_9_5

## [1] 179.6825
nivel.conf <- 0.93; chi_alfa_9_5 <- qchisq((1 + nivel.conf)/2, df, TRUE); chi_alfa_9_5

## [1] 182.9749
nivel.conf <- 0.97; chi_alfa_9_5 <- qchisq((1 + nivel.conf)/2, df, TRUE); chi_alfa_9_5

## [1] 190.1665