Task 2b

Load and review the Titanic Dataset

titanic.df <- read.csv(paste("Titanic Data.csv", sep=""))
View(titanic.df)

Task 3a

Count the total number of passengers on board the Titanic

count_OB <- nrow(titanic.df)
count_OB
## [1] 889

Task 3b

count the number of passengers who survived the sinking of the Titanic

count_sur <- sum(titanic.df$Survived == 1)
count_sur
## [1] 340

Task 3c

Measure the percentage of passengers who survived the sinking of the Titanic

per_sur <- (count_sur/count_OB) * 100
per_sur
## [1] 38.24522

Task 3d

Count the number of first-class passengers who survived the sinking of the Titanic

mytable <- xtabs(~ Pclass+Survived, data=titanic.df)
mytable
##       Survived
## Pclass   0   1
##      1  80 134
##      2  97  87
##      3 372 119

Task 3e

Measure the percentage of first-class passengers who survived the sinking of the Titanic

prop.table(mytable, 1) * 100
##       Survived
## Pclass        0        1
##      1 37.38318 62.61682
##      2 52.71739 47.28261
##      3 75.76375 24.23625

Task 3f

Count the number of females from First-Class who survived the sinking of the Titanic

mytable1 <- xtabs(~ Pclass+Sex+Survived, data=titanic.df)
mytable1
## , , Survived = 0
## 
##       Sex
## Pclass female male
##      1      3   77
##      2      6   91
##      3     72  300
## 
## , , Survived = 1
## 
##       Sex
## Pclass female male
##      1     89   45
##      2     70   17
##      3     72   47

Task 3g

Measure the percentage of survivors who were female

mytable2 <- xtabs(~ Survived+Sex, data=titanic.df)
mytable2
##         Sex
## Survived female male
##        0     81  468
##        1    231  109
prop.table(mytable2, 1) * 100
##         Sex
## Survived   female     male
##        0 14.75410 85.24590
##        1 67.94118 32.05882

Task 3h

Measure the percentage of females on board the Titanic who survived

prop.table(mytable2, 2) * 100
##         Sex
## Survived   female     male
##        0 25.96154 81.10919
##        1 74.03846 18.89081

Task 3i

Pearson’s Chi-squared test for hypothesis testing.

Hypothesis: The proportion of females onboard who survived the sinking of the Titanic was higher than the proportion of males onboard who survived the sinking of the Titanic.

addmargins(mytable2)
##         Sex
## Survived female male Sum
##      0       81  468 549
##      1      231  109 340
##      Sum    312  577 889
chisq.test(mytable2)
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  mytable2
## X-squared = 258.43, df = 1, p-value < 2.2e-16