#View(LungCapData)            
str(LungCapData)           
## 'data.frame':    725 obs. of  6 variables:
##  $ LungCap  : num  6.47 10.12 9.55 11.12 4.8 ...
##  $ Age      : num  6 18 16 14 5 11 8 11 15 11 ...
##  $ Height   : num  62.1 74.7 69.7 71 56.9 58.7 63.3 70.4 70.5 59.2 ...
##  $ Smoke    : chr  "no" "yes" "no" "no" ...
##  $ Gender   : chr  "male" "female" "female" "male" ...
##  $ Caesarean: chr  "no" "no" "yes" "no" ...
glimpse(LungCapData)        
## Rows: 725
## Columns: 6
## $ LungCap   <dbl> 6.475, 10.125, 9.550, 11.125, 4.800, 6.225, 4.950, 7.325, 8.…
## $ Age       <dbl> 6, 18, 16, 14, 5, 11, 8, 11, 15, 11, 19, 17, 12, 10, 10, 13,…
## $ Height    <dbl> 62.1, 74.7, 69.7, 71.0, 56.9, 58.7, 63.3, 70.4, 70.5, 59.2, …
## $ Smoke     <chr> "no", "yes", "no", "no", "no", "no", "no", "no", "no", "no",…
## $ Gender    <chr> "male", "female", "female", "male", "male", "female", "male"…
## $ Caesarean <chr> "no", "no", "yes", "no", "no", "no", "yes", "no", "no", "no"…
skimr::skim(LungCapData)
Data summary
Name LungCapData
Number of rows 725
Number of columns 6
_______________________
Column type frequency:
character 3
numeric 3
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
Smoke 0 1 2 3 0 2 0
Gender 0 1 4 6 0 2 0
Caesarean 0 1 2 3 0 2 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
LungCap 0 1 7.86 2.66 0.51 6.15 8.0 9.8 14.68 ▁▃▇▆▁
Age 0 1 12.33 4.00 3.00 9.00 13.0 15.0 19.00 ▃▅▇▇▇
Height 0 1 64.84 7.20 45.30 59.90 65.4 70.3 81.80 ▁▅▇▇▂

Análisis univariado de variables numéricas

#LUNG CAP
summary(LungCapData)
##     LungCap            Age            Height         Smoke          
##  Min.   : 0.507   Min.   : 3.00   Min.   :45.30   Length:725        
##  1st Qu.: 6.150   1st Qu.: 9.00   1st Qu.:59.90   Class :character  
##  Median : 8.000   Median :13.00   Median :65.40   Mode  :character  
##  Mean   : 7.863   Mean   :12.33   Mean   :64.84                     
##  3rd Qu.: 9.800   3rd Qu.:15.00   3rd Qu.:70.30                     
##  Max.   :14.675   Max.   :19.00   Max.   :81.80                     
##     Gender           Caesarean        
##  Length:725         Length:725        
##  Class :character   Class :character  
##  Mode  :character   Mode  :character  
##                                       
##                                       
## 
summary(LungCapData$LungCap)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.507   6.150   8.000   7.863   9.800  14.675
#ANALITICO
shapiro.test(LungCapData$LungCap)
## 
##  Shapiro-Wilk normality test
## 
## data:  LungCapData$LungCap
## W = 0.99305, p-value = 0.001886
#GRAFICO

hist(LungCapData$LungCap)

LungCapData %>%
  ggplot(aes(x = LungCap)) + 
  geom_histogram(bins = 10, color = "#FF5733", alpha = 0.6) + 
  theme_ipsum() +
 labs(x = "Capacidad pulmonar")

boxplot(LungCapData$LungCap , col = "blue")

qqnorm(LungCapData$LungCap)
qqline(LungCapData$LungCap, col = "blue", lwd = 3)

par(mfrow = c(1, 1))

LungCapData %>% 
  ggplot(aes(LungCap)) + 
  geom_density()

ggplot(LungCapData, aes(x=LungCap, fill = Gender)) +
  geom_density(alpha=0.3) + 
  scale_x_continuous(limits = c(0, 15))

#AGE

#ANALITICO
shapiro.test(LungCapData$Age)
## 
##  Shapiro-Wilk normality test
## 
## data:  LungCapData$Age
## W = 0.97231, p-value = 0.0000000001763
#GRAFICO

hist(LungCapData$Age)

LungCapData %>%
  ggplot(aes(x = Age)) + 
  geom_histogram(bins = 10, color = "#FF5733", alpha = 0.6) + 
  theme_ipsum() +
 labs(x = "Edad")

boxplot(LungCapData$Age , col = "blue")

qqnorm(LungCapData$Age)
qqline(LungCapData$Age, col = "blue", lwd = 3)

par(mfrow = c(1, 1))

LungCapData %>% 
  ggplot(aes(Age)) + 
  geom_density()

ggplot(LungCapData, aes(x=Age, fill = Gender)) +
  geom_density(alpha=0.3) + 
  scale_x_continuous(limits = c(0, 20))

#HEIGHT

#ANALITICO
shapiro.test(LungCapData$Height)
## 
##  Shapiro-Wilk normality test
## 
## data:  LungCapData$Height
## W = 0.99027, p-value = 0.0001006
#GRAFICO

hist(LungCapData$Height)

LungCapData %>%
  ggplot(aes(x = Height)) + 
  geom_histogram(bins = 10, color = "#FF5733", alpha = 0.6) + 
  theme_ipsum() +
 labs(x = "Altura")

boxplot(LungCapData$Height , col = "blue")

qqnorm(LungCapData$Height)
qqline(LungCapData$Height, col = "blue", lwd = 3)

par(mfrow = c(1, 1))

LungCapData %>% 
  ggplot(aes(Height)) + 
  geom_density()

ggplot(LungCapData, aes(x=Height, fill = Gender)) +
  geom_density(alpha=0.3) + 
  scale_x_continuous(limits = c(40, 90))

# Análisis univariado de variables categóricas

# SMOKE

table(LungCapData$Smoke) 
## 
##  no yes 
## 648  77
prop.table(table(LungCapData$Smoke))  
## 
##        no       yes 
## 0.8937931 0.1062069
chisq.test(table(LungCapData$Smoke)) 
## 
##  Chi-squared test for given probabilities
## 
## data:  table(LungCapData$Smoke)
## X-squared = 449.71, df = 1, p-value < 0.00000000000000022
# GRAFICO
table(LungCapData$Smoke)
## 
##  no yes 
## 648  77
barplot(table(LungCapData$Smoke), col = rainbow(3))

ggplot(data = LungCapData, aes(x = Smoke)) + 
  geom_bar() + 
  xlab("Fumadores") + 
  ylab("Pacientes")

ggplot(data = LungCapData, aes(x = Smoke)) + 
  geom_bar(color = 'darkslategray', fill = 'steelblue') + 
  xlab("Fumadores") + 
  ylab("Pacientes") + 
  ggtitle("Gráfico de Barras")

LungCapData %>% 
  plot_frq(Smoke) 

#GENDER

table(LungCapData$Gender) 
## 
## female   male 
##    358    367
prop.table(table(LungCapData$Gender))  
## 
##    female      male 
## 0.4937931 0.5062069
chisq.test(table(LungCapData$Gender)) 
## 
##  Chi-squared test for given probabilities
## 
## data:  table(LungCapData$Gender)
## X-squared = 0.11172, df = 1, p-value = 0.7382
# GRAFICO
table(LungCapData$Gender)
## 
## female   male 
##    358    367
barplot(table(LungCapData$Gender), col = rainbow(3))

ggplot(data = LungCapData, aes(x = Gender)) + 
  geom_bar() + 
  xlab("Género") + 
  ylab("Pacientes")

ggplot(data = LungCapData, aes(x = Gender)) + 
  geom_bar(color = 'darkslategray', fill = 'steelblue') + 
  xlab("Género") + 
  ylab("Pacientes") + 
  ggtitle("Gráfico de Barras")

LungCapData %>% 
  plot_frq(Gender)

#Caesarean

table(LungCapData$Caesarean) 
## 
##  no yes 
## 561 164
prop.table(table(LungCapData$Caesarean))  
## 
##        no       yes 
## 0.7737931 0.2262069
chisq.test(table(LungCapData$Caesarean)) 
## 
##  Chi-squared test for given probabilities
## 
## data:  table(LungCapData$Caesarean)
## X-squared = 217.39, df = 1, p-value < 0.00000000000000022
# GRAFICO
table(LungCapData$Caesarean)
## 
##  no yes 
## 561 164
barplot(table(LungCapData$Caesarean), col = rainbow(3))

ggplot(data = LungCapData, aes(x = Caesarean)) + 
  geom_bar() + 
  xlab("Nacidos por cesárea") + 
  ylab("Pacientes")

ggplot(data = LungCapData, aes(x = Caesarean)) + 
  geom_bar(color = 'darkslategray', fill = 'steelblue') + 
  xlab("Nacidos por cesárea") + 
  ylab("Pacientes") + 
  ggtitle("Gráfico de Barras")

LungCapData %>% 
  plot_frq(Caesarean)

# Análisis bivariado entre capacidad pulmonar y edad

cor.test(LungCapData$LungCap, LungCapData$Age, method = "pearson")
## 
##  Pearson's product-moment correlation
## 
## data:  LungCapData$LungCap and LungCapData$Age
## t = 38.476, df = 723, p-value < 0.00000000000000022
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.7942660 0.8422217
## sample estimates:
##       cor 
## 0.8196749
ggplot(LungCapData, aes(x = LungCap, y = Age, color = Gender)) +
  geom_point() +
  labs(title = "Relación entre capacidad pulmonar y edad",
       x = "Capacidad pulmonar",
       y = "Edad") +
  theme_minimal()

library(GGally)
## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2
ggpairs(LungCapData, columns = c("LungCap", "Age"),
        aes(color = Gender, alpha = 0.5)) + 
  theme_minimal()

# Análisis bivariado entre capacidad pulmoanr y género

wilcox.test(LungCapData$LungCap ~ LungCapData$Gender)
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  LungCapData$LungCap by LungCapData$Gender
## W = 53624, p-value = 0.00001864
## alternative hypothesis: true location shift is not equal to 0
ggplot(LungCapData, aes(x = LungCap, y = Gender, color = Smoke)) +
  geom_point() +
  labs(title = "Relación entre capacidad pulmonar y género",
       x = "Capacidad pulmonar",
       y = "Género") +
  theme_minimal()

library(GGally)
ggpairs(LungCapData, columns = c("LungCap", "Gender"),
        aes(color = Gender, alpha = 0.5)) + 
  theme_minimal()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Análisis bivariado entre hábito tabáquico y género

chisq.test(LungCapData$Gender, LungCapData$Smoke)
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  LungCapData$Gender and LungCapData$Smoke
## X-squared = 1.7443, df = 1, p-value = 0.1866
ggplot(LungCapData, aes(x = Gender, fill = Smoke)) +
  geom_bar () +
  labs(title = "Relación entre género y hábito tabáquico",
       x = "Género",
       y = "Hábito tabáquico") +
  theme_minimal()

library(gtsummary)
glimpse(LungCapData)
## Rows: 725
## Columns: 6
## $ LungCap   <dbl> 6.475, 10.125, 9.550, 11.125, 4.800, 6.225, 4.950, 7.325, 8.…
## $ Age       <dbl> 6, 18, 16, 14, 5, 11, 8, 11, 15, 11, 19, 17, 12, 10, 10, 13,…
## $ Height    <dbl> 62.1, 74.7, 69.7, 71.0, 56.9, 58.7, 63.3, 70.4, 70.5, 59.2, …
## $ Smoke     <chr> "no", "yes", "no", "no", "no", "no", "no", "no", "no", "no",…
## $ Gender    <chr> "male", "female", "female", "male", "male", "female", "male"…
## $ Caesarean <chr> "no", "no", "yes", "no", "no", "no", "yes", "no", "no", "no"…
LungCapData %>% 
  tbl_summary()
Characteristic N = 7251
LungCap 8.00 (6.15, 9.80)
Age 13.0 (9.0, 15.0)
Height 65 (60, 70)
Smoke 77 (11%)
Gender
    female 358 (49%)
    male 367 (51%)
Caesarean 164 (23%)
1 Median (Q1, Q3); n (%) 
LungCapData %>% 
  select(Age, Gender, LungCap, Height, Smoke, Caesarean)  %>% 
  tbl_summary()
Characteristic N = 7251
Age 13.0 (9.0, 15.0)
Gender
    female 358 (49%)
    male 367 (51%)
LungCap 8.00 (6.15, 9.80)
Height 65 (60, 70)
Smoke 77 (11%)
Caesarean 164 (23%)
1 Median (Q1, Q3); n (%)