R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

#EJERCICIO_1
library(datasets)
library(knitr)
data(iris)
data(Orange)
head(iris)
##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa
head(Orange)
##   Tree  age circumference
## 1    1  118            30
## 2    1  484            58
## 3    1  664            87
## 4    1 1004           115
## 5    1 1231           120
## 6    1 1372           142
summary(iris)
##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
## 
summary(Orange)
##  Tree       age         circumference  
##  3:7   Min.   : 118.0   Min.   : 30.0  
##  1:7   1st Qu.: 484.0   1st Qu.: 65.5  
##  5:7   Median :1004.0   Median :115.0  
##  2:7   Mean   : 922.1   Mean   :115.9  
##  4:7   3rd Qu.:1372.0   3rd Qu.:161.5  
##        Max.   :1582.0   Max.   :214.0
kable(table(iris$Sepal.Length))
Var1 Freq
4.3 1
4.4 3
4.5 1
4.6 4
4.7 2
4.8 5
4.9 6
5 10
5.1 9
5.2 4
5.3 1
5.4 6
5.5 7
5.6 6
5.7 8
5.8 7
5.9 3
6 6
6.1 6
6.2 4
6.3 9
6.4 7
6.5 5
6.6 2
6.7 8
6.8 3
6.9 4
7 1
7.1 1
7.2 3
7.3 1
7.4 1
7.6 1
7.7 4
7.9 1 
kable(table(iris$Sepal.Width))
Var1 Freq
2 1
2.2 3
2.3 4
2.4 3
2.5 8
2.6 5
2.7 9
2.8 14
2.9 10
3 26
3.1 11
3.2 13
3.3 6
3.4 12
3.5 6
3.6 4
3.7 3
3.8 6
3.9 2
4 1
4.1 1
4.2 1
4.4 1 
kable(table(iris$Petal.Length))
Var1 Freq
1 1
1.1 1
1.2 2
1.3 7
1.4 13
1.5 13
1.6 7
1.7 4
1.9 2
3 1
3.3 2
3.5 2
3.6 1
3.7 1
3.8 1
3.9 3
4 5
4.1 3
4.2 4
4.3 2
4.4 4
4.5 8
4.6 3
4.7 5
4.8 4
4.9 5
5 4
5.1 8
5.2 2
5.3 2
5.4 2
5.5 3
5.6 6
5.7 3
5.8 3
5.9 2
6 2
6.1 3
6.3 1
6.4 1
6.6 1
6.7 2
6.9 1 
kable(table(iris$Petal.Width))
Var1 Freq
0.1 5
0.2 29
0.3 7
0.4 7
0.5 1
0.6 1
1 7
1.1 3
1.2 5
1.3 13
1.4 8
1.5 12
1.6 4
1.7 2
1.8 12
1.9 5
2 6
2.1 6
2.2 3
2.3 8
2.4 3
2.5 3 
kable(table(iris$Species))
Var1 Freq
setosa 50
versicolor 50
virginica 50 
kable(prop.table(iris$Sepal.Length))
x
0.0058186
0.0055904
0.0053622
0.0052481
0.0057045
0.0061609
0.0052481
0.0057045
0.0050200
0.0055904
0.0061609
0.0054763
0.0054763
0.0049059
0.0066172
0.0065031
0.0061609
0.0058186
0.0065031
0.0058186
0.0061609
0.0058186
0.0052481
0.0058186
0.0054763
0.0057045
0.0057045
0.0059327
0.0059327
0.0053622
0.0054763
0.0061609
0.0059327
0.0062750
0.0055904
0.0057045
0.0062750
0.0055904
0.0050200
0.0058186
0.0057045
0.0051341
0.0050200
0.0057045
0.0058186
0.0054763
0.0058186
0.0052481
0.0060468
0.0057045
0.0079863
0.0073018
0.0078722
0.0062750
0.0074159
0.0065031
0.0071877
0.0055904
0.0075299
0.0059327
0.0057045
0.0067313
0.0068454
0.0069595
0.0063890
0.0076440
0.0063890
0.0066172
0.0070736
0.0063890
0.0067313
0.0069595
0.0071877
0.0069595
0.0073018
0.0075299
0.0077581
0.0076440
0.0068454
0.0065031
0.0062750
0.0062750
0.0066172
0.0068454
0.0061609
0.0068454
0.0076440
0.0071877
0.0063890
0.0062750
0.0062750
0.0069595
0.0066172
0.0057045
0.0063890
0.0065031
0.0065031
0.0070736
0.0058186
0.0065031
0.0071877
0.0066172
0.0081004
0.0071877
0.0074159
0.0086708
0.0055904
0.0083286
0.0076440
0.0082145
0.0074159
0.0073018
0.0077581
0.0065031
0.0066172
0.0073018
0.0074159
0.0087849
0.0087849
0.0068454
0.0078722
0.0063890
0.0087849
0.0071877
0.0076440
0.0082145
0.0070736
0.0069595
0.0073018
0.0082145
0.0084427
0.0090131
0.0073018
0.0071877
0.0069595
0.0087849
0.0071877
0.0073018
0.0068454
0.0078722
0.0076440
0.0078722
0.0066172
0.0077581
0.0076440
0.0076440
0.0071877
0.0074159
0.0070736
0.0067313 
kable(prop.table(iris$Sepal.Width))
x
0.0076319
0.0065416
0.0069778
0.0067597
0.0078500
0.0085041
0.0074139
0.0074139
0.0063236
0.0067597
0.0080680
0.0074139
0.0065416
0.0065416
0.0087222
0.0095944
0.0085041
0.0076319
0.0082861
0.0082861
0.0074139
0.0080680
0.0078500
0.0071958
0.0074139
0.0065416
0.0074139
0.0076319
0.0074139
0.0069778
0.0067597
0.0074139
0.0089403
0.0091583
0.0067597
0.0069778
0.0076319
0.0078500
0.0065416
0.0074139
0.0076319
0.0050153
0.0069778
0.0076319
0.0082861
0.0065416
0.0082861
0.0069778
0.0080680
0.0071958
0.0069778
0.0069778
0.0067597
0.0050153
0.0061055
0.0061055
0.0071958
0.0052333
0.0063236
0.0058875
0.0043611
0.0065416
0.0047972
0.0063236
0.0063236
0.0067597
0.0065416
0.0058875
0.0047972
0.0054514
0.0069778
0.0061055
0.0054514
0.0061055
0.0063236
0.0065416
0.0061055
0.0065416
0.0063236
0.0056694
0.0052333
0.0052333
0.0058875
0.0058875
0.0065416
0.0074139
0.0067597
0.0050153
0.0065416
0.0054514
0.0056694
0.0065416
0.0056694
0.0050153
0.0058875
0.0065416
0.0063236
0.0063236
0.0054514
0.0061055
0.0071958
0.0058875
0.0065416
0.0063236
0.0065416
0.0065416
0.0054514
0.0063236
0.0054514
0.0078500
0.0069778
0.0058875
0.0065416
0.0054514
0.0061055
0.0069778
0.0065416
0.0082861
0.0056694
0.0047972
0.0069778
0.0061055
0.0061055
0.0058875
0.0071958
0.0069778
0.0061055
0.0065416
0.0061055
0.0065416
0.0061055
0.0082861
0.0061055
0.0061055
0.0056694
0.0065416
0.0074139
0.0067597
0.0065416
0.0067597
0.0067597
0.0067597
0.0058875
0.0069778
0.0071958
0.0065416
0.0054514
0.0065416
0.0074139
0.0065416 
kable(prop.table(iris$Petal.Length))
x
0.0024836
0.0024836
0.0023062
0.0026610
0.0024836
0.0030158
0.0024836
0.0026610
0.0024836
0.0026610
0.0026610
0.0028384
0.0024836
0.0019514
0.0021288
0.0026610
0.0023062
0.0024836
0.0030158
0.0026610
0.0030158
0.0026610
0.0017740
0.0030158
0.0033706
0.0028384
0.0028384
0.0026610
0.0024836
0.0028384
0.0028384
0.0026610
0.0026610
0.0024836
0.0026610
0.0021288
0.0023062
0.0024836
0.0023062
0.0026610
0.0023062
0.0023062
0.0023062
0.0028384
0.0033706
0.0024836
0.0028384
0.0024836
0.0026610
0.0024836
0.0083378
0.0079830
0.0086926
0.0070960
0.0081604
0.0079830
0.0083378
0.0058542
0.0081604
0.0069186
0.0062090
0.0074508
0.0070960
0.0083378
0.0063864
0.0078056
0.0079830
0.0072734
0.0079830
0.0069186
0.0085152
0.0070960
0.0086926
0.0083378
0.0076282
0.0078056
0.0085152
0.0088700
0.0079830
0.0062090
0.0067412
0.0065638
0.0069186
0.0090474
0.0079830
0.0079830
0.0083378
0.0078056
0.0072734
0.0070960
0.0078056
0.0081604
0.0070960
0.0058542
0.0074508
0.0074508
0.0074508
0.0076282
0.0053220
0.0072734
0.0106440
0.0090474
0.0104666
0.0099344
0.0102892
0.0117084
0.0079830
0.0111762
0.0102892
0.0108214
0.0090474
0.0094022
0.0097570
0.0088700
0.0090474
0.0094022
0.0097570
0.0118858
0.0122406
0.0088700
0.0101118
0.0086926
0.0118858
0.0086926
0.0101118
0.0106440
0.0085152
0.0086926
0.0099344
0.0102892
0.0108214
0.0113536
0.0099344
0.0090474
0.0099344
0.0108214
0.0099344
0.0097570
0.0085152
0.0095796
0.0099344
0.0090474
0.0090474
0.0104666
0.0101118
0.0092248
0.0088700
0.0092248
0.0095796
0.0090474 
kable(prop.table(iris$Petal.Width))
x
0.0011117
0.0011117
0.0011117
0.0011117
0.0011117
0.0022235
0.0016676
0.0011117
0.0011117
0.0005559
0.0011117
0.0011117
0.0005559
0.0005559
0.0011117
0.0022235
0.0022235
0.0016676
0.0016676
0.0016676
0.0011117
0.0022235
0.0011117
0.0027793
0.0011117
0.0011117
0.0022235
0.0011117
0.0011117
0.0011117
0.0011117
0.0022235
0.0005559
0.0011117
0.0011117
0.0011117
0.0011117
0.0005559
0.0011117
0.0011117
0.0016676
0.0016676
0.0011117
0.0033352
0.0022235
0.0016676
0.0011117
0.0011117
0.0011117
0.0011117
0.0077821
0.0083380
0.0083380
0.0072262
0.0083380
0.0072262
0.0088938
0.0055586
0.0072262
0.0077821
0.0055586
0.0083380
0.0055586
0.0077821
0.0072262
0.0077821
0.0083380
0.0055586
0.0083380
0.0061145
0.0100056
0.0072262
0.0083380
0.0066704
0.0072262
0.0077821
0.0077821
0.0094497
0.0083380
0.0055586
0.0061145
0.0055586
0.0066704
0.0088938
0.0083380
0.0088938
0.0083380
0.0072262
0.0072262
0.0072262
0.0066704
0.0077821
0.0066704
0.0055586
0.0072262
0.0066704
0.0072262
0.0072262
0.0061145
0.0072262
0.0138966
0.0105614
0.0116732
0.0100056
0.0122290
0.0116732
0.0094497
0.0100056
0.0100056
0.0138966
0.0111173
0.0105614
0.0116732
0.0111173
0.0133407
0.0127849
0.0100056
0.0122290
0.0127849
0.0083380
0.0127849
0.0111173
0.0111173
0.0100056
0.0116732
0.0100056
0.0100056
0.0100056
0.0116732
0.0088938
0.0105614
0.0111173
0.0122290
0.0083380
0.0077821
0.0127849
0.0133407
0.0100056
0.0100056
0.0116732
0.0133407
0.0127849
0.0105614
0.0127849
0.0138966
0.0127849
0.0105614
0.0111173
0.0127849
0.0100056 
#prop.table(iris$Species) #Como son factores, no se puede generar la tabla

kable(table(Orange$Tree))
Var1 Freq
3 7
1 7
5 7
2 7
4 7 
kable(table(Orange$age))
Var1 Freq
118 5
484 5
664 5
1004 5
1231 5
1372 5
1582 5 
kable(table(Orange$circumference))
Var1 Freq
30 3
32 1
33 1
49 1
51 1
58 1
62 1
69 1
75 1
81 1
87 1
108 1
111 1
112 1
115 2
120 1
125 1
139 1
140 1
142 2
145 1
156 1
167 1
172 1
174 1
177 1
179 1
203 2
209 1
214 1 
table(Orange$Tree, Orange$age)
##    
##     118 484 664 1004 1231 1372 1582
##   3   1   1   1    1    1    1    1
##   1   1   1   1    1    1    1    1
##   5   1   1   1    1    1    1    1
##   2   1   1   1    1    1    1    1
##   4   1   1   1    1    1    1    1
#EJERCICIO_2
vect1 <- c(1,2,1,2,1,2,1,2,1,2,1,1,1,1,2,2,1,1,2,1)
vect2 <- c(1,1,2,2,2,1,2,1,1,2,1,2,1,1,1,2,1,1,1,1)
Bajo_Peso=factor(vect1, levels=c(1,2), labels=c("Bajo Peso","Peso Normal"))
Bajo_Peso
##  [1] Bajo Peso   Peso Normal Bajo Peso   Peso Normal Bajo Peso   Peso Normal
##  [7] Bajo Peso   Peso Normal Bajo Peso   Peso Normal Bajo Peso   Bajo Peso  
## [13] Bajo Peso   Bajo Peso   Peso Normal Peso Normal Bajo Peso   Bajo Peso  
## [19] Peso Normal Bajo Peso  
## Levels: Bajo Peso Peso Normal
Fumador=factor(vect2, levels=c(1,2), labels=c("Fuma", "No fuma"))
Fumador
##  [1] Fuma    Fuma    No fuma No fuma No fuma Fuma    No fuma Fuma    Fuma   
## [10] No fuma Fuma    No fuma Fuma    Fuma    Fuma    No fuma Fuma    Fuma   
## [19] Fuma    Fuma   
## Levels: Fuma No fuma
tabla<-table(Bajo_Peso, Fumador)
tabla
##              Fumador
## Bajo_Peso     Fuma No fuma
##   Bajo Peso      8       4
##   Peso Normal    5       3
chisq.test(tabla)
## Warning in chisq.test(tabla): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  tabla
## X-squared = 0, df = 1, p-value = 1
fisher.test(tabla)
## 
##  Fisher's Exact Test for Count Data
## 
## data:  tabla
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.1200513 10.9278345
## sample estimates:
## odds ratio 
##   1.189031
#Según Pearson no hay evidencia de relación entre "fumar" y "peso". Sin embargo, nos sale una advertencia ya que este test no es fiable con muestras pequeñas, así que usamos el test de Fisher. Este test confirma el resultado anterior, no podemos rechazar la hipótesis nula de independencia entre fumar y peso ya que el p-valor=1. Además, el cociente de probabilidades (odds-ratio) es cercano a 1 (1.19), lo que demuesta que no hay prácticamente asociación.

#EJERCICIO_3
data("airquality")
data("airmiles")
par(mfrow=c(2,2)) #matriz 2x2
plot(airquality$Ozone, col="blue",pch="#") #apartado a)
boxplot(airquality$Temp, col="red", main="Temperatura (en grados Farenheit)")
plot(airmiles, main = "Datos de pasajeros en vuelos comerciales (miles)",
xlab = "Miles de pasajeros", col = "cadetblue2")
hist(airmiles, col="chocolate2", main="Histrograma de vuelos comerciales")

#EJERCICIO_4
set.seed(333)
x1 <- rnorm(500)
y1 <- x1 + rnorm(500)
plot(x1, y1, main="Gráfico de dispersión")
abline(lm(y1~x1), col="orange")

#EJERCICIO_5
library(ggplot2)

ggplot(airquality, aes(Solar.R, Temp)) +
geom_point(size=3) +
geom_smooth(method="lm", col="darkred")
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 7 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).
ggplot (data=airquality, aes(x=Solar.R, y=Temp, col=factor(Month),
shape=factor(Month))) +
geom_point()
## Warning: Removed 7 rows containing missing values or values outside the scale range
## (`geom_point()`).
library (MASS)
ggplot(birthwt,aes(age)) +
geom_histogram(binwidth=5, fill="blue",col="black")

ggplot(birthwt,aes(age)) +
geom_histogram(binwidth=5, fill="violet",col="black")+
facet_grid(~smoke)

#EJERCICIO_6
jpeg("migrafic1.jpg") #abrimos el dispositivo gráfico
data(iris)
boxplot(iris$Petal.Width, col="green")
dev.off
## function (which = dev.cur()) 
## {
##     if (which == 1) 
##         stop("cannot shut down device 1 (the null device)")
##     .External(C_devoff, as.integer(which))
##     dev.cur()
## }
## <bytecode: 0x144491cd8>
## <environment: namespace:grDevices>
pdf("migrafic2.pdf") #abrimos el dispositivo gráfico
data(iris)
boxplot(iris$Petal.Width, col="green")
dev.off #cerramos el dispositivo gráfico
## function (which = dev.cur()) 
## {
##     if (which == 1) 
##         stop("cannot shut down device 1 (the null device)")
##     .External(C_devoff, as.integer(which))
##     dev.cur()
## }
## <bytecode: 0x144491cd8>
## <environment: namespace:grDevices>
#EJERCICIO_7
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ✖ dplyr::select() masks MASS::select()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
data("Orange")
head(Orange)
## Grouped Data: circumference ~ age | Tree
##   Tree  age circumference
## 1    1  118            30
## 2    1  484            58
## 3    1  664            87
## 4    1 1004           115
## 5    1 1231           120
## 6    1 1372           142
summary(Orange)
##  Tree       age         circumference  
##  3:7   Min.   : 118.0   Min.   : 30.0  
##  1:7   1st Qu.: 484.0   1st Qu.: 65.5  
##  5:7   Median :1004.0   Median :115.0  
##  2:7   Mean   : 922.1   Mean   :115.9  
##  4:7   3rd Qu.:1372.0   3rd Qu.:161.5  
##        Max.   :1582.0   Max.   :214.0
pairs(Orange)

cor.test(Orange$age, Orange$circumference) #Hay correlación puesto que el valor es 0.91
## 
##  Pearson's product-moment correlation
## 
## data:  Orange$age and Orange$circumference
## t = 12.9, df = 33, p-value = 1.931e-14
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.8342364 0.9557955
## sample estimates:
##       cor 
## 0.9135189
mod_reg<-lm(circumference ~ age, data = Orange)
summary(mod_reg)
## 
## Call:
## lm(formula = circumference ~ age, data = Orange)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -46.310 -14.946  -0.076  19.697  45.111 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 17.399650   8.622660   2.018   0.0518 .  
## age          0.106770   0.008277  12.900 1.93e-14 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 23.74 on 33 degrees of freedom
## Multiple R-squared:  0.8345, Adjusted R-squared:  0.8295 
## F-statistic: 166.4 on 1 and 33 DF,  p-value: 1.931e-14
plot(Orange$age,Orange$circumference)
abline(mod_reg)
abline(mod_reg, col = "orange")

días <- 600
medida <- 0.1068 * días + 17.3997
print(medida)
## [1] 81.4797
#EJERCICIO_8
Orange %>%
ggplot(aes(x = age,
y = circumference)) +
geom_point()

Orange %>%
ggplot(aes(x = age,
y = circumference)) +
geom_point() +
geom_abline(intercept = 17.3997,
slope = 0.1068,
col = 'blue') +
geom_vline(xintercept = 800,
col = 'red')

#EJERCICIO_9
data("PlantGrowth")
anova(lm(weight ~ group, data = PlantGrowth))
## Analysis of Variance Table
## 
## Response: weight
##           Df  Sum Sq Mean Sq F value  Pr(>F)  
## group      2  3.7663  1.8832  4.8461 0.01591 *
## Residuals 27 10.4921  0.3886                  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
  #La hipótesis nula del ANOVA es que todas las medias poblacionales de peso son iguales, pero la alternativa es que al menos unamedia es diferente. Como el p-value = 0.01591, rechazamos la hipótesis nula, ya que hay diferencias significativas entre al menos dos tratamientos respecto al peso de las plantas.Sin embargo, para aplicar un ANOVA correctamente tenemos que comprobar que se cumplan tres supuestos: 1)Independencia de las observaciones, 2) Normalidad de los residuos (distribución aproximadamente normal) que se puede comprobar con spahiro.test:
shapiro.test(residuals(lm(weight ~ group, data = PlantGrowth)))
## 
##  Shapiro-Wilk normality test
## 
## data:  residuals(lm(weight ~ group, data = PlantGrowth))
## W = 0.96607, p-value = 0.4379
qqnorm(residuals(lm(weight ~ group, data = PlantGrowth)))
qqline(residuals(lm(weight ~ group, data = PlantGrowth)))

#Y por último 3) Homogeneicdad de varianzas (Homocedaasticidad) que podemos comprobarlo así:
library(car)
## Loading required package: carData
## 
## Attaching package: 'car'
## 
## The following object is masked from 'package:dplyr':
## 
##     recode
## 
## The following object is masked from 'package:purrr':
## 
##     some
bartlett.test(weight ~ group, data = PlantGrowth) #En este caso no se rechaza la hipótesis nula, ya que no hay evidencia estadística de que las varianzas sean diferentes (p-value=0.2371 > 0.05)
## 
##  Bartlett test of homogeneity of variances
## 
## data:  weight by group
## Bartlett's K-squared = 2.8786, df = 2, p-value = 0.2371
#Si estas condiciones no se cumplen (no normalidad o no homocedasticidad) hay que utilizar una alternativa no paramétrica como el test de Kruskal-Wallis que compara medianas en vez de medias. Si la ANOVA es válida hacemos una comprobación post-hoc con el Tukey test:
TukeyHSD(aov(weight ~ group, data = PlantGrowth)) #Hay diferencias significativas comparando trt2 y trt2 (p=0.012)
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = weight ~ group, data = PlantGrowth)
## 
## $group
##             diff        lwr       upr     p adj
## trt1-ctrl -0.371 -1.0622161 0.3202161 0.3908711
## trt2-ctrl  0.494 -0.1972161 1.1852161 0.1979960
## trt2-trt1  0.865  0.1737839 1.5562161 0.0120064
#EJERCICIO_10
#Apartado_a
load("/Users/monicadoblasbajo/Library/Mobile Documents/com~apple~CloudDocs/3. Bioinformatics/UOC_MSc/2025_Software_análisis_datos/PEC_1/LAB_2/bodyfat.rda")
ls()
##  [1] "airmiles"    "airquality"  "Bajo_Peso"   "bodyfat"     "días"       
##  [6] "Fumador"     "iris"        "medida"      "mod_reg"     "Orange"     
## [11] "PlantGrowth" "tabla"       "vect1"       "vect2"       "x1"         
## [16] "y1"
head(bodyfat)
##   density   fat age  weight  height neck chest abdomen   hip thigh knee ankle
## 1  1.0708 0.123  23 70.0295 172.085 36.2  93.1    85.2  94.5  59.0 37.3  21.9
## 2  1.0853 0.061  22 78.6555 183.515 38.5  93.6    83.0  98.7  58.7 37.3  23.4
## 3  1.0414 0.253  22 69.9160 168.275 34.0  95.8    87.9  99.2  59.6 38.9  24.0
## 4  1.0751 0.104  26 83.8765 183.515 37.4 101.8    86.4 101.2  60.1 37.3  22.8
## 5  1.0340 0.287  24 83.6495 180.975 34.4  97.3   100.0 101.9  63.2 42.2  24.0
## 6  1.0502 0.209  24 95.4535 189.865 39.0 104.5    94.4 107.8  66.0 42.0  25.6
##   biceps forearm wrist
## 1   32.0    27.4  17.1
## 2   30.5    28.9  18.2
## 3   28.8    25.2  16.6
## 4   32.4    29.4  18.2
## 5   32.2    27.7  17.7
## 6   35.7    30.6  18.8
str(bodyfat)
## 'data.frame':    249 obs. of  15 variables:
##  $ density: 'labelled' num  1.07 1.09 1.04 1.08 1.03 ...
##   ..- attr(*, "label")= chr "Density"
##   ..- attr(*, "units")= chr "g/cm^3"
##  $ fat    : 'labelled' num  0.123 0.061 0.253 0.104 0.287 0.209 0.192 0.124 0.041 0.117 ...
##   ..- attr(*, "label")= chr "Body Fat"
##   ..- attr(*, "units")= chr "Proportion"
##  $ age    : 'labelled' int  23 22 22 26 24 24 26 25 25 23 ...
##   ..- attr(*, "label")= chr "Age"
##   ..- attr(*, "units")= chr "years"
##  $ weight : 'labelled' num  70 78.7 69.9 83.9 83.6 ...
##   ..- attr(*, "label")= chr "Weight"
##   ..- attr(*, "units")= chr "kg"
##  $ height : 'labelled' num  172 184 168 184 181 ...
##   ..- attr(*, "label")= chr "Height"
##   ..- attr(*, "units")= chr "cm"
##  $ neck   : 'labelled' num  36.2 38.5 34 37.4 34.4 39 36.4 37.8 38.1 42.1 ...
##   ..- attr(*, "label")= chr "Neck Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ chest  : 'labelled' num  93.1 93.6 95.8 101.8 97.3 ...
##   ..- attr(*, "label")= chr "Chest Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ abdomen: 'labelled' num  85.2 83 87.9 86.4 100 94.4 90.7 88.5 82.5 88.6 ...
##   ..- attr(*, "label")= chr "Abdomen Circumference at Umbilicus"
##   ..- attr(*, "units")= chr "cm"
##  $ hip    : 'labelled' num  94.5 98.7 99.2 101.2 101.9 ...
##   ..- attr(*, "label")= chr "Hip Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ thigh  : 'labelled' num  59 58.7 59.6 60.1 63.2 66 58.4 60 62.9 63.1 ...
##   ..- attr(*, "label")= chr "Thigh Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ knee   : 'labelled' num  37.3 37.3 38.9 37.3 42.2 42 38.3 39.4 38.3 41.7 ...
##   ..- attr(*, "label")= chr "Knee Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ ankle  : 'labelled' num  21.9 23.4 24 22.8 24 25.6 22.9 23.2 23.8 25 ...
##   ..- attr(*, "label")= chr "Ankle Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ biceps : 'labelled' num  32 30.5 28.8 32.4 32.2 35.7 31.9 30.5 35.9 35.6 ...
##   ..- attr(*, "label")= chr "Extended Biceps Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ forearm: 'labelled' num  27.4 28.9 25.2 29.4 27.7 30.6 27.8 29 31.1 30 ...
##   ..- attr(*, "label")= chr "Forearm Circumference"
##   ..- attr(*, "units")= chr "cm"
##  $ wrist  : 'labelled' num  17.1 18.2 16.6 18.2 17.7 18.8 17.7 18.8 18.2 19.2 ...
##   ..- attr(*, "label")= chr "Wrist Circumference"
##   ..- attr(*, "units")= chr "cm"
summary(bodyfat)
##     density           fat              age            weight      
##  Min.   :0.995   Min.   :0.0300   Min.   :22.00   Min.   : 56.75  
##  1st Qu.:1.041   1st Qu.:0.1250   1st Qu.:36.00   1st Qu.: 72.30  
##  Median :1.055   Median :0.1920   Median :43.00   Median : 80.24  
##  Mean   :1.055   Mean   :0.1925   Mean   :44.95   Mean   : 81.39  
##  3rd Qu.:1.070   3rd Qu.:0.2530   3rd Qu.:54.00   3rd Qu.: 89.44  
##  Max.   :1.099   Max.   :0.4750   Max.   :81.00   Max.   :164.87  
##      height           neck           chest          abdomen      
##  Min.   :162.6   Min.   :31.10   Min.   : 83.4   Min.   : 70.40  
##  1st Qu.:174.0   1st Qu.:36.40   1st Qu.: 94.6   1st Qu.: 85.20  
##  Median :178.4   Median :38.00   Median : 99.7   Median : 91.00  
##  Mean   :178.7   Mean   :38.03   Mean   :100.9   Mean   : 92.67  
##  3rd Qu.:183.5   3rd Qu.:39.50   3rd Qu.:105.3   3rd Qu.: 99.20  
##  Max.   :197.5   Max.   :51.20   Max.   :136.2   Max.   :148.10  
##       hip             thigh            knee           ankle      
##  Min.   : 85.30   Min.   :49.30   Min.   :33.00   Min.   :19.10  
##  1st Qu.: 95.60   1st Qu.:56.10   1st Qu.:37.10   1st Qu.:22.00  
##  Median : 99.30   Median :59.00   Median :38.50   Median :22.80  
##  Mean   : 99.94   Mean   :59.45   Mean   :38.61   Mean   :23.12  
##  3rd Qu.:103.50   3rd Qu.:62.30   3rd Qu.:39.90   3rd Qu.:24.00  
##  Max.   :147.70   Max.   :87.30   Max.   :49.10   Max.   :33.90  
##      biceps         forearm          wrist      
##  Min.   :25.30   Min.   :21.00   Min.   :15.80  
##  1st Qu.:30.30   1st Qu.:27.30   1st Qu.:17.60  
##  Median :32.10   Median :28.80   Median :18.30  
##  Mean   :32.32   Mean   :28.69   Mean   :18.25  
##  3rd Qu.:34.40   3rd Qu.:30.00   3rd Qu.:18.80  
##  Max.   :45.00   Max.   :34.90   Max.   :21.40
#El dataset seleccionado contiene información de 15 diferentes variables relacionadas con medidas antropométricas para cuantificar la grsa corporal. El dataset contiene datos de personas desde los 22 a los 81 años, una media de p eso de 81,59kg y 1,78 m de altura.Aunque los datos parecen relativamente homogéneos, algunos valores como el mínimo y el máximo de abdomen, podrían corresonder a individuos con obesidad.

#Apartado_b
hist(bodyfat$fat, 
     main = "Distribución % de grasa corporal",
     xlab = "Proporción de grasa corporal",
     col = "lightblue")

boxplot(bodyfat$abdomen,
        main = " Silueta del abdomen",
        ylab = "cm", col = "lightgreen")

plot(density(bodyfat$weight),
     main = "Peso corporal",
     xlab = "Peso (kg)",
     col = "purple", lwd = 2)

plot(density(bodyfat$height),
     main = "Altura",
     xlab = "Altura (cm)",
     col = "lightpink", lwd = 2)

boxplot(bodyfat$age,
        main = " Edad",
        ylab = "años", col = "lightyellow")

#Apartado_c
ggplot(bodyfat, aes(x = fat)) +
  geom_histogram(binwidth = 0.02, fill = "lightblue", color = "black") +
  labs(title = "Distribución % de grasa corporal",
       x = "% de grasa corporal",
       y = "Frecuencia") +
  theme_minimal()

#Aquí observarmos la distribuición de la variable 'fat' en la muestra donde la mayoría de individuos están entre el 10%-25% de grasa.

ggplot(bodyfat, aes(x = age)) +
  geom_histogram(binwidth = 0.2, fill = "lightgreen", color = "black") +
  labs(title = "Edad",
       x = "Edad (años)",
       y = "Frecuencia") +
  theme_minimal()

#Aquí observarmos la distribuición de la variable 'age' en la muestra donde sigue una distribución normal, siendo los individuos entre 40-60 los más frecuentes en el dataset.

#Apartado_d
ggplot(bodyfat, aes(x = weight, y = fat)) +
  geom_point(color = "black", size = 2) +
  geom_smooth(method = "lm", se = TRUE, color = "darkorange") +
  labs(title = "Relación entre peso y porcentaje de grasa corporal",
       x = "Peso (kg)",
       y = "% de grasa corporal") +
  theme_minimal()
## `geom_smooth()` using formula = 'y ~ x'

#Observamos una relación positiva entre los individuos de mayor peso y su % de grasa corporal. La línea azul representa la regresión y la sombra el intervalo de confianza.

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.