library(lsm)      # Para descargar una base de datos
library(dplyr)
## 
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(moments)  # Para hallar las medidas de forma
library(e1071)
## 
## Adjuntando el paquete: 'e1071'
## The following objects are masked from 'package:moments':
## 
##     kurtosis, moment, skewness
library(ggplot2)
## 
## Adjuntando el paquete: 'ggplot2'
## The following object is masked from 'package:e1071':
## 
##     element

Data frame

Ahora utilizaremos el conjunto de datos survey del paquete lsm. Es un data frame con 800 observaciones y 66 variables.

datosCompleto <- lsm::survey

Visualizando una parte de la información.

En este trabajo estaremos visualizando solo una parte de los datos.

head(datosCompleto)        #A) Por defecto, solo las primeras 6 observaciones 
## # A tibble: 6 × 66
##   Observation ID       Gender Like    Age Smoke Height Weight   BMI School SES  
##         <dbl> <chr>    <chr>  <chr> <dbl> <chr>  <dbl>  <dbl> <dbl> <chr>  <chr>
## 1           1 SB11201… Female TV     21.4 No      1.58     75  30.0 Priva… Medi…
## 2           2 SB11201… Male   Netw…  21.1 Yes     1.6      80  31.2 Public High 
## 3           3 SB11201… Male   Netw…  20.9 Yes     1.5      64  28.4 Priva… High 
## 4           4 SB11201… Male   TV     18.4 Yes     1.53     49  20.9 Public Low  
## 5           5 SB11201… Female TV     16.6 Yes     1.78     82  25.9 Priva… High 
## 6           6 SB11201… Female Netw…  16.0 No      1.65     80  29.4 Public Low  
## # ℹ 55 more variables: Enrollment <chr>, Score <dbl>, MotherHeight <chr>,
## #   MotherAge <dbl>, MotherCHD <dbl>, FatherHeight <chr>, FatherAge <dbl>,
## #   FatherCHD <dbl>, Status <chr>, SemAcum <dbl>, Exam1 <dbl>, Exam2 <dbl>,
## #   Exam3 <dbl>, Exam4 <dbl>, ExamAcum <dbl>, Definitive <dbl>, Expense <dbl>,
## #   Income <dbl>, Gas <dbl>, Course <chr>, Law <chr>, Economic <chr>,
## #   Race <chr>, Region <chr>, EMO1 <dbl>, EMO2 <dbl>, EMO3 <dbl>, EMO4 <dbl>,
## #   EMO5 <dbl>, GOAL1 <chr>, GOAL2 <chr>, GOAL3 <chr>, Pre_STAT1 <dbl>, …
head(datosCompleto, 3)     #B) Solo las primeras 3 observaciones 
## # A tibble: 3 × 66
##   Observation ID       Gender Like    Age Smoke Height Weight   BMI School SES  
##         <dbl> <chr>    <chr>  <chr> <dbl> <chr>  <dbl>  <dbl> <dbl> <chr>  <chr>
## 1           1 SB11201… Female TV     21.4 No      1.58     75  30.0 Priva… Medi…
## 2           2 SB11201… Male   Netw…  21.1 Yes     1.6      80  31.2 Public High 
## 3           3 SB11201… Male   Netw…  20.9 Yes     1.5      64  28.4 Priva… High 
## # ℹ 55 more variables: Enrollment <chr>, Score <dbl>, MotherHeight <chr>,
## #   MotherAge <dbl>, MotherCHD <dbl>, FatherHeight <chr>, FatherAge <dbl>,
## #   FatherCHD <dbl>, Status <chr>, SemAcum <dbl>, Exam1 <dbl>, Exam2 <dbl>,
## #   Exam3 <dbl>, Exam4 <dbl>, ExamAcum <dbl>, Definitive <dbl>, Expense <dbl>,
## #   Income <dbl>, Gas <dbl>, Course <chr>, Law <chr>, Economic <chr>,
## #   Race <chr>, Region <chr>, EMO1 <dbl>, EMO2 <dbl>, EMO3 <dbl>, EMO4 <dbl>,
## #   EMO5 <dbl>, GOAL1 <chr>, GOAL2 <chr>, GOAL3 <chr>, Pre_STAT1 <dbl>, …

Ahora visualizaremos la estructura, la cual tiene enformación sobre el tipo de objeto, el numero de filas y columna, junto con informacion adicional.

str(datosCompleto)   #A) Estructura de los datos
## tibble [800 × 66] (S3: tbl_df/tbl/data.frame)
##  $ Observation : num [1:800] 1 2 3 4 5 6 7 8 9 10 ...
##  $ ID          : chr [1:800] "SB11201910010435" "SB11201910004475" "SB11201910011427" "SB11201910041975" ...
##  $ Gender      : chr [1:800] "Female" "Male" "Male" "Male" ...
##  $ Like        : chr [1:800] "TV" "Network" "Network" "TV" ...
##  $ Age         : num [1:800] 21.4 21.1 20.9 18.4 16.6 ...
##  $ Smoke       : chr [1:800] "No" "Yes" "Yes" "Yes" ...
##  $ Height      : num [1:800] 1.58 1.6 1.5 1.53 1.78 1.65 1.73 1.53 1.64 1.52 ...
##  $ Weight      : num [1:800] 75 80 64 49 82 80 90 55 50 78 ...
##  $ BMI         : num [1:800] 30 31.2 28.4 20.9 25.9 ...
##  $ School      : chr [1:800] "Private" "Public" "Private" "Public" ...
##  $ SES         : chr [1:800] "Medium" "High" "High" "Low" ...
##  $ Enrollment  : chr [1:800] "Credit" "Scholarship" "Scholarship" "Credit" ...
##  $ Score       : num [1:800] 81 78 77 70 68 65 54 50 36 35 ...
##  $ MotherHeight: chr [1:800] "Short_M" "Normal_M" "Normal_M" "Tall_M" ...
##  $ MotherAge   : num [1:800] 41 45 45 45 46 46 47 48 48 48 ...
##  $ MotherCHD   : num [1:800] 0 0 0 0 1 0 0 0 0 1 ...
##  $ FatherHeight: chr [1:800] "Normal_F" "Short_F" "Tall_F" "Short_F" ...
##  $ FatherAge   : num [1:800] 40 43 44 45 45 46 46 48 48 49 ...
##  $ FatherCHD   : num [1:800] 1 1 1 2 1 1 1 1 1 1 ...
##  $ Status      : chr [1:800] "Distinguished" "Distinguished" "Distinguished" "Regular" ...
##  $ SemAcum     : num [1:800] 4.25 2.8 4.15 3.2 3.45 2.75 2.7 4.35 4.3 2.8 ...
##  $ Exam1       : num [1:800] 1.5 2.3 3.4 2.5 3.1 3.8 5 4 2.5 2.4 ...
##  $ Exam2       : num [1:800] 5 4.9 3.6 4.2 3.5 4.4 3 2.3 3.3 2.6 ...
##  $ Exam3       : num [1:800] 5 3.7 2 5 5 4.2 3.5 4.6 3.8 4.3 ...
##  $ Exam4       : num [1:800] 4.5 3.3 1.9 2.5 3 5 3.6 4.3 1.9 5 ...
##  $ ExamAcum    : num [1:800] 16 14.2 10.9 14.2 14.6 17.4 15.1 15.2 11.5 14.3 ...
##  $ Definitive  : num [1:800] 4 3.55 2.73 3.55 3.65 ...
##  $ Expense     : num [1:800] 48.9 72.1 85.2 56.6 64.6 63 40.8 65.4 37.3 63 ...
##  $ Income      : num [1:800] 1.61 2.07 2.84 1.55 2.32 2.1 1.69 2.18 1.71 2.1 ...
##  $ Gas         : num [1:800] 27.4 24.2 22.3 23.1 27.3 ...
##  $ Course      : chr [1:800] "Face-to-Face" "Virtual" "Face-to-Face" "Virtual" ...
##  $ Law         : chr [1:800] "Agree" "Agree" "Agree" "Agree" ...
##  $ Economic    : chr [1:800] "Regular" "Good" "Regular" "Bad" ...
##  $ Race        : chr [1:800] "Ethnic" "Ethnic" "Ethnic" "Ethnic" ...
##  $ Region      : chr [1:800] "North" "Center" "North" "Center" ...
##  $ EMO1        : num [1:800] 1 4 3 4 2 3 2 3 4 2 ...
##  $ EMO2        : num [1:800] 2 4 1 2 1 1 4 1 2 2 ...
##  $ EMO3        : num [1:800] 2 1 3 3 2 4 2 4 3 3 ...
##  $ EMO4        : num [1:800] 1 2 3 1 4 2 3 2 1 1 ...
##  $ EMO5        : num [1:800] 4 1 2 2 2 2 1 1 2 2 ...
##  $ GOAL1       : chr [1:800] "Strongly agree" "Undecided" "Agree" "Agree" ...
##  $ GOAL2       : chr [1:800] "Agree" "Disagree" "Disagree" "Undecided" ...
##  $ GOAL3       : chr [1:800] "Strongly agree" "Disagree" "Agree" "Strongly agree" ...
##  $ Pre_STAT1   : num [1:800] 2 1 5 4 1 4 4 2 2 2 ...
##  $ Pre_STAT2   : num [1:800] 4 1 1 3 4 1 2 3 3 5 ...
##  $ Pre_STAT3   : num [1:800] 2 1 3 1 1 5 4 3 3 2 ...
##  $ Pre_STAT4   : num [1:800] 5 1 1 2 2 3 2 3 2 4 ...
##  $ Post_STAT1  : num [1:800] 4 5 5 3 5 2 3 3 2 5 ...
##  $ Post_STAT2  : num [1:800] 5 1 2 2 3 3 2 3 2 3 ...
##  $ Post_STAT3  : num [1:800] 2 3 3 4 3 5 5 4 5 4 ...
##  $ Post_STAT4  : num [1:800] 2 3 3 5 4 4 3 5 5 1 ...
##  $ Pre_IDARE1  : chr [1:800] "Quite a bit" "Quite a bit" "Quite a bit" "Little" ...
##  $ Pre_IDARE2  : chr [1:800] "Little" "Little" "Little" "Nothing" ...
##  $ Pre_IDARE3  : chr [1:800] "Quite a bit" "A lot" "Quite a bit" "Quite a bit" ...
##  $ Pre_IDARE4  : chr [1:800] "Quite a bit" "Nothing" "Quite a bit" "Quite a bit" ...
##  $ Pre_IDARE5  : chr [1:800] "Little" "Quite a bit" "Little" "Nothing" ...
##  $ Post_IDARE1 : chr [1:800] "A lot" "A little" "Nothing" "Quite a bit" ...
##  $ Post_IDARE2 : chr [1:800] "A lot" "Nothing" "Quite a bit" "A little" ...
##  $ Post_IDARE3 : chr [1:800] "A little" "Quite a bit" "Nothing" "A lot" ...
##  $ Post_IDARE4 : chr [1:800] "Quite a bit" "A lot" "Nothing" "Quite a bit" ...
##  $ Post_IDARE5 : chr [1:800] "A lot" "Quite a bit" "Nothing" "A lot" ...
##  $ PSICO1      : chr [1:800] "Frequently" "Frequently" "Sometimes" "Almost always" ...
##  $ PSICO2      : chr [1:800] "Almost always" "Sometimes" "Sometimes" "Frequently" ...
##  $ PSICO3      : chr [1:800] "Frequently" "Sometimes" "Sometimes" "Frequently" ...
##  $ PSICO4      : chr [1:800] "Almost always" "Frequently" "Frequently" "Almost never" ...
##  $ PSICO5      : chr [1:800] "Almost always" "Frequently" "Sometimes" "Sometimes" ...

Ahora vamos a explorar los nombres de las tamaños.

length(datosCompleto)   #A) Revisando número de variables del objeto
## [1] 66
dim(datosCompleto)      #B Muestra las dimensiones del objeto.
## [1] 800  66
ncol(datosCompleto)     #C) Muestra el número de columnas del objeto.
## [1] 66
nrow(datosCompleto)     #D) Muestra el número de filas del objeto.
## [1] 800

Ahora vamos a filtrar información de la base de datos. Por ejemplo: Un data frame que contenga solo las observaciones de 1 a 4, con las columnas 2 a 5.

Muestra1 <- datosCompleto[1:10,2:7]       # A) Un nuevo data frame 
Muestra1
## # A tibble: 10 × 6
##    ID               Gender Like      Age Smoke Height
##    <chr>            <chr>  <chr>   <dbl> <chr>  <dbl>
##  1 SB11201910010435 Female TV       21.4 No      1.58
##  2 SB11201910004475 Male   Network  21.1 Yes     1.6 
##  3 SB11201910011427 Male   Network  20.9 Yes     1.5 
##  4 SB11201910041975 Male   TV       18.4 Yes     1.53
##  5 SB11201910013623 Female TV       16.6 Yes     1.78
##  6 SB11201910038122 Female Network  16.0 No      1.65
##  7 SB11201910037905 Female TV       19.3 Yes     1.73
##  8 SB11201910038140 Female TV       18.6 Yes     1.53
##  9 SB11201910038005 Female TV       17.0 Yes     1.64
## 10 SB11201910037919 Male   TV       19.7 Yes     1.52

Tipos de variables

str(datosCompleto)   #A) Estructura de los datos
## tibble [800 × 66] (S3: tbl_df/tbl/data.frame)
##  $ Observation : num [1:800] 1 2 3 4 5 6 7 8 9 10 ...
##  $ ID          : chr [1:800] "SB11201910010435" "SB11201910004475" "SB11201910011427" "SB11201910041975" ...
##  $ Gender      : chr [1:800] "Female" "Male" "Male" "Male" ...
##  $ Like        : chr [1:800] "TV" "Network" "Network" "TV" ...
##  $ Age         : num [1:800] 21.4 21.1 20.9 18.4 16.6 ...
##  $ Smoke       : chr [1:800] "No" "Yes" "Yes" "Yes" ...
##  $ Height      : num [1:800] 1.58 1.6 1.5 1.53 1.78 1.65 1.73 1.53 1.64 1.52 ...
##  $ Weight      : num [1:800] 75 80 64 49 82 80 90 55 50 78 ...
##  $ BMI         : num [1:800] 30 31.2 28.4 20.9 25.9 ...
##  $ School      : chr [1:800] "Private" "Public" "Private" "Public" ...
##  $ SES         : chr [1:800] "Medium" "High" "High" "Low" ...
##  $ Enrollment  : chr [1:800] "Credit" "Scholarship" "Scholarship" "Credit" ...
##  $ Score       : num [1:800] 81 78 77 70 68 65 54 50 36 35 ...
##  $ MotherHeight: chr [1:800] "Short_M" "Normal_M" "Normal_M" "Tall_M" ...
##  $ MotherAge   : num [1:800] 41 45 45 45 46 46 47 48 48 48 ...
##  $ MotherCHD   : num [1:800] 0 0 0 0 1 0 0 0 0 1 ...
##  $ FatherHeight: chr [1:800] "Normal_F" "Short_F" "Tall_F" "Short_F" ...
##  $ FatherAge   : num [1:800] 40 43 44 45 45 46 46 48 48 49 ...
##  $ FatherCHD   : num [1:800] 1 1 1 2 1 1 1 1 1 1 ...
##  $ Status      : chr [1:800] "Distinguished" "Distinguished" "Distinguished" "Regular" ...
##  $ SemAcum     : num [1:800] 4.25 2.8 4.15 3.2 3.45 2.75 2.7 4.35 4.3 2.8 ...
##  $ Exam1       : num [1:800] 1.5 2.3 3.4 2.5 3.1 3.8 5 4 2.5 2.4 ...
##  $ Exam2       : num [1:800] 5 4.9 3.6 4.2 3.5 4.4 3 2.3 3.3 2.6 ...
##  $ Exam3       : num [1:800] 5 3.7 2 5 5 4.2 3.5 4.6 3.8 4.3 ...
##  $ Exam4       : num [1:800] 4.5 3.3 1.9 2.5 3 5 3.6 4.3 1.9 5 ...
##  $ ExamAcum    : num [1:800] 16 14.2 10.9 14.2 14.6 17.4 15.1 15.2 11.5 14.3 ...
##  $ Definitive  : num [1:800] 4 3.55 2.73 3.55 3.65 ...
##  $ Expense     : num [1:800] 48.9 72.1 85.2 56.6 64.6 63 40.8 65.4 37.3 63 ...
##  $ Income      : num [1:800] 1.61 2.07 2.84 1.55 2.32 2.1 1.69 2.18 1.71 2.1 ...
##  $ Gas         : num [1:800] 27.4 24.2 22.3 23.1 27.3 ...
##  $ Course      : chr [1:800] "Face-to-Face" "Virtual" "Face-to-Face" "Virtual" ...
##  $ Law         : chr [1:800] "Agree" "Agree" "Agree" "Agree" ...
##  $ Economic    : chr [1:800] "Regular" "Good" "Regular" "Bad" ...
##  $ Race        : chr [1:800] "Ethnic" "Ethnic" "Ethnic" "Ethnic" ...
##  $ Region      : chr [1:800] "North" "Center" "North" "Center" ...
##  $ EMO1        : num [1:800] 1 4 3 4 2 3 2 3 4 2 ...
##  $ EMO2        : num [1:800] 2 4 1 2 1 1 4 1 2 2 ...
##  $ EMO3        : num [1:800] 2 1 3 3 2 4 2 4 3 3 ...
##  $ EMO4        : num [1:800] 1 2 3 1 4 2 3 2 1 1 ...
##  $ EMO5        : num [1:800] 4 1 2 2 2 2 1 1 2 2 ...
##  $ GOAL1       : chr [1:800] "Strongly agree" "Undecided" "Agree" "Agree" ...
##  $ GOAL2       : chr [1:800] "Agree" "Disagree" "Disagree" "Undecided" ...
##  $ GOAL3       : chr [1:800] "Strongly agree" "Disagree" "Agree" "Strongly agree" ...
##  $ Pre_STAT1   : num [1:800] 2 1 5 4 1 4 4 2 2 2 ...
##  $ Pre_STAT2   : num [1:800] 4 1 1 3 4 1 2 3 3 5 ...
##  $ Pre_STAT3   : num [1:800] 2 1 3 1 1 5 4 3 3 2 ...
##  $ Pre_STAT4   : num [1:800] 5 1 1 2 2 3 2 3 2 4 ...
##  $ Post_STAT1  : num [1:800] 4 5 5 3 5 2 3 3 2 5 ...
##  $ Post_STAT2  : num [1:800] 5 1 2 2 3 3 2 3 2 3 ...
##  $ Post_STAT3  : num [1:800] 2 3 3 4 3 5 5 4 5 4 ...
##  $ Post_STAT4  : num [1:800] 2 3 3 5 4 4 3 5 5 1 ...
##  $ Pre_IDARE1  : chr [1:800] "Quite a bit" "Quite a bit" "Quite a bit" "Little" ...
##  $ Pre_IDARE2  : chr [1:800] "Little" "Little" "Little" "Nothing" ...
##  $ Pre_IDARE3  : chr [1:800] "Quite a bit" "A lot" "Quite a bit" "Quite a bit" ...
##  $ Pre_IDARE4  : chr [1:800] "Quite a bit" "Nothing" "Quite a bit" "Quite a bit" ...
##  $ Pre_IDARE5  : chr [1:800] "Little" "Quite a bit" "Little" "Nothing" ...
##  $ Post_IDARE1 : chr [1:800] "A lot" "A little" "Nothing" "Quite a bit" ...
##  $ Post_IDARE2 : chr [1:800] "A lot" "Nothing" "Quite a bit" "A little" ...
##  $ Post_IDARE3 : chr [1:800] "A little" "Quite a bit" "Nothing" "A lot" ...
##  $ Post_IDARE4 : chr [1:800] "Quite a bit" "A lot" "Nothing" "Quite a bit" ...
##  $ Post_IDARE5 : chr [1:800] "A lot" "Quite a bit" "Nothing" "A lot" ...
##  $ PSICO1      : chr [1:800] "Frequently" "Frequently" "Sometimes" "Almost always" ...
##  $ PSICO2      : chr [1:800] "Almost always" "Sometimes" "Sometimes" "Frequently" ...
##  $ PSICO3      : chr [1:800] "Frequently" "Sometimes" "Sometimes" "Frequently" ...
##  $ PSICO4      : chr [1:800] "Almost always" "Frequently" "Frequently" "Almost never" ...
##  $ PSICO5      : chr [1:800] "Almost always" "Frequently" "Sometimes" "Sometimes" ...

Nominales o caracter

Codigo <- datosCompleto$ID     #B) Si es tipo caracter, es correcto)
Edad <- datosCompleto$Age      #C) Si es tipo caracter, es incorrecto (ver ejemplo 4) 
Sexo <- datosCompleto$Gender   #D) Si es tipo caracter, es incorrecto (ver ejemplo 5)

Numéricas

P1   <- datosCompleto$Exam1 #E) Numérica
P2   <- datosCompleto$Exam2 #F) Numérica
Edad <- datosCompleto$Age   #G) Numérica

Categórica o factor

Sexo <- as.factor(Sexo)  #H) Convirtiendo a factor
class(Sexo)              #I) Sale: "factor"
## [1] "factor"
str(Sexo)                #J) Sale: Factor w/ 2 levels "Female","Masculino": 1 2 2 2 1 1 1 1 1 2 ...
##  Factor w/ 2 levels "Female","Male": 1 2 2 2 1 1 1 1 1 2 ...
levels(Sexo)             #K) Sale: "Female"  "Masculino"
## [1] "Female" "Male"

Volviendo a la tabla:

Muestra1 <- datosCompleto[1:10,2:7]       # A) Un nuevo data frame 
Muestra1
## # A tibble: 10 × 6
##    ID               Gender Like      Age Smoke Height
##    <chr>            <chr>  <chr>   <dbl> <chr>  <dbl>
##  1 SB11201910010435 Female TV       21.4 No      1.58
##  2 SB11201910004475 Male   Network  21.1 Yes     1.6 
##  3 SB11201910011427 Male   Network  20.9 Yes     1.5 
##  4 SB11201910041975 Male   TV       18.4 Yes     1.53
##  5 SB11201910013623 Female TV       16.6 Yes     1.78
##  6 SB11201910038122 Female Network  16.0 No      1.65
##  7 SB11201910037905 Female TV       19.3 Yes     1.73
##  8 SB11201910038140 Female TV       18.6 Yes     1.53
##  9 SB11201910038005 Female TV       17.0 Yes     1.64
## 10 SB11201910037919 Male   TV       19.7 Yes     1.52

Interpretación

La tabla contiene información de 10 estudiantes y presenta seis variables: ID, Gender, Like, Age, Smoke y Height.

Gender: de los 10 estudiantes, 6 son mujeres y 4 son hombres. Like: 7 estudiantes prefieren TV, mientras que 3 prefieren Network. Age: los estudiantes tienen edades entre 16,0 y 21,4 años. El estudiante de mayor edad tiene 21,4 años y el menor 16,0 años. Smoke: 8 estudiantes indican que sí fuman, mientras que 2 indican que no. Height: las alturas van desde 1,50 m hasta 1,78 m. La persona más alta mide 1,78 m y la más baja 1,50 m.

En conjunto, la muestra está compuesta principalmente por mujeres, estudiantes que prefieren la televisión y personas que reportan fumar. Además, las edades corresponden a un grupo de estudiantes jóvenes, aproximadamente entre los 16 y 21 años.