Caso práctico. Crear datos inventados con R de 15 hombres y 15 mujeres

# Fijar la semilla para reproducibilidad
set.seed(123)
# Crear identificadores únicos
ID <- 1:30
# Generar 15 "M" (hombres) y 15 "F" (mujeres)
Genero <- rep(c("M", "F"), each = 15)
# Generar edades entre 18 y 60 años
Edad <- sample(18:60, 30, replace = TRUE)
# Asignar aleatoriamente un tratamiento (A o B)
Tratamiento <- sample(c("A", "B"), 30, replace = TRUE)
# Generar peso en kg (Hombres: 60-100, Mujeres: 50-90)
Peso <- ifelse(Genero == "M", runif(15, 60, 100), runif(15, 50, 90))
# Generar estatura en cm (Hombres: 160-190, Mujeres: 150-175)
Estatura <- ifelse(Genero == "M", runif(15, 160, 190), runif(15, 150, 175))
# Crear el data frame
datos <- data.frame(ID, Edad, Genero, Tratamiento, Peso, Estatura)
# Mostrar los primeros registros

Resultados A

head(datos)

ID Edad Genero Tratamiento Peso Estatura 1 1 48 M B 85.16885 169.9847 2 2 32 M B 88.40730 174.6584 3 3 31 M A 60.02499 188.6342 4 4 20 M A 79.01266 174.4871 5 5 59 M A 68.80476 186.7105 6 6 60 M A 75.19266 187.4331

Resultados B. Información estadística sobre los datos

summary(datos, c(Edad, Genero, Tratamiento, Peso, Estatura))
kable(summary(datos, c(Edad, Genero, Tratamiento, Peso, Estatura)))
Edad Genero Tratamiento Peso Estatura
Min. :20.00 Length:30 Length:30 Min. :53.74 Min. :152.3
1st Qu.:31.00 Class :character Class :character 1st Qu.:64.20 1st Qu.:160.5
Median :42.50 Mode :character Mode :character Median :74.63 Median :166.7
Mean :40.23 NA NA Mean :73.44 Mean :169.2
3rd Qu.:51.00 NA NA 3rd Qu.:83.71 3rd Qu.:174.6
Max. :60.00 NA NA Max. :91.53 Max. :188.6

Resultados C.Crear variable IMC

datos$IMC <- datos$Peso / ( (datos$Estatura / 100) ^ 2 )
ID Edad Genero Tratamiento Peso Estatura IMC
1 48 M B 85.16885 169.9847 29.47549
2 32 M B 88.40730 174.6584 28.98072
3 31 M A 60.02499 188.6342 16.86907
4 20 M A 79.01266 174.4871 25.95196
5 59 M A 68.80476 186.7105 19.73699
6 60 M A 75.19266 187.4331 21.40340
7 54 M B 84.51084 178.2620 26.59467
8 31 M A 74.07192 172.3207 24.94472
9 42 M A 64.44542 164.4128 23.84079
10 43 M B 69.74478 188.0590 19.72075
11 44 M A 86.72222 169.0369 30.35062
12 22 M A 76.70587 161.8216 29.29244
13 44 M A 91.52783 188.4318 25.77773
14 45 M A 64.11459 181.6179 19.43746
15 26 M B 77.39571 164.2688 28.68181
16 46 F B 89.39828 163.7321 33.34736
17 52 F A 85.72204 173.8523 28.36167
18 25 F B 85.45876 164.6371 31.52835
19 43 F A 57.00211 160.1128 22.23510
20 24 F A 55.22783 166.1973 19.99447
21 59 F B 76.12408 157.9955 30.49527
22 26 F B 63.74066 157.6930 25.63254
23 36 F A 76.27033 155.4942 31.54476
24 53 F A 62.81493 159.2372 24.77272
25 31 F B 57.50764 174.6055 18.86296
26 34 F A 81.29177 153.8551 34.34180
27 60 F A 53.74380 152.2761 23.17741
28 56 F A 68.67116 153.5477 29.12647
29 29 F A 70.46022 167.2502 25.18899
30 32 F B 73.99956 165.4814 27.02282

Resultados D. Crear dos ficheros independientes para hombres y mujeres

datos_m<- subset(datos, Genero == "M")
datos_m<- subset(datos, Genero == "F")
kable(datos_m)
kable(datos_f)
ID Edad Genero Tratamiento Peso Estatura IMC
1 48 M B 85.16885 169.9847 29.47549
2 32 M B 88.40730 174.6584 28.98072
3 31 M A 60.02499 188.6342 16.86907
4 20 M A 79.01266 174.4871 25.95196
5 59 M A 68.80476 186.7105 19.73699
6 60 M A 75.19266 187.4331 21.40340
7 54 M B 84.51084 178.2620 26.59467
8 31 M A 74.07192 172.3207 24.94472
9 42 M A 64.44542 164.4128 23.84079
10 43 M B 69.74478 188.0590 19.72075
11 44 M A 86.72222 169.0369 30.35062
12 22 M A 76.70587 161.8216 29.29244
13 44 M A 91.52783 188.4318 25.77773
14 45 M A 64.11459 181.6179 19.43746
15 26 M B 77.39571 164.2688 28.68181
ID Edad Genero Tratamiento Peso Estatura IMC
16 16 46 F B 89.39828 163.7321 33.34736
17 17 52 F A 85.72204 173.8523 28.36167
18 18 25 F B 85.45876 164.6371 31.52835
19 19 43 F A 57.00211 160.1128 22.23510
20 20 24 F A 55.22783 166.1973 19.99447
21 21 59 F B 76.12408 157.9955 30.49527
22 22 26 F B 63.74066 157.6930 25.63254
23 23 36 F A 76.27033 155.4942 31.54476
24 24 53 F A 62.81493 159.2372 24.77272
25 25 31 F B 57.50764 174.6055 18.86296
26 26 34 F A 81.29177 153.8551 34.34180
27 27 60 F A 53.74380 152.2761 23.17741
28 28 56 F A 68.67116 153.5477 29.12647
29 29 29 F A 70.46022 167.2502 25.18899
30 30 32 F B 73.99956 165.4814 27.02282

Ejercicio E. Fusionar dos conjuntos de datos (hombres y mujeres)

fusion<- rbind(datos_m, datos_f)
kable(fusion)
ID Edad Genero Tratamiento Peso Estatura IMC
1 48 M B 85.16885 169.9847 29.47549
2 32 M B 88.40730 174.6584 28.98072
3 31 M A 60.02499 188.6342 16.86907
4 20 M A 79.01266 174.4871 25.95196
5 59 M A 68.80476 186.7105 19.73699
6 60 M A 75.19266 187.4331 21.40340
7 54 M B 84.51084 178.2620 26.59467
8 31 M A 74.07192 172.3207 24.94472
9 42 M A 64.44542 164.4128 23.84079
10 43 M B 69.74478 188.0590 19.72075
11 44 M A 86.72222 169.0369 30.35062
12 22 M A 76.70587 161.8216 29.29244
13 44 M A 91.52783 188.4318 25.77773
14 45 M A 64.11459 181.6179 19.43746
15 26 M B 77.39571 164.2688 28.68181
16 46 F B 89.39828 163.7321 33.34736
17 52 F A 85.72204 173.8523 28.36167
18 25 F B 85.45876 164.6371 31.52835
19 43 F A 57.00211 160.1128 22.23510
20 24 F A 55.22783 166.1973 19.99447
21 59 F B 76.12408 157.9955 30.49527
22 26 F B 63.74066 157.6930 25.63254
23 36 F A 76.27033 155.4942 31.54476
24 53 F A 62.81493 159.2372 24.77272
25 31 F B 57.50764 174.6055 18.86296
26 34 F A 81.29177 153.8551 34.34180
27 60 F A 53.74380 152.2761 23.17741
28 56 F A 68.67116 153.5477 29.12647
29 29 F A 70.46022 167.2502 25.18899
30 32 F B 73.99956 165.4814 27.02282