setwd("C:/Users/Leo Tolstoy/Downloads")
titanic.df<-read.csv(paste("Titanic Data.csv",sep=""))
View(titanic.df)
TASK 3a Use R to count the total number of passengers on board the Titanic.
str(titanic.df)
## 'data.frame': 889 obs. of 8 variables:
## $ Survived: int 0 1 1 1 0 0 0 0 1 1 ...
## $ Pclass : int 3 1 3 1 3 3 1 3 3 2 ...
## $ Sex : Factor w/ 2 levels "female","male": 2 1 1 1 2 2 2 2 1 1 ...
## $ Age : num 22 38 26 35 35 29.7 54 2 27 14 ...
## $ SibSp : int 1 1 0 1 0 0 0 3 0 1 ...
## $ Parch : int 0 0 0 0 0 0 0 1 2 0 ...
## $ Fare : num 7.25 71.28 7.92 53.1 8.05 ...
## $ Embarked: Factor w/ 3 levels "C","Q","S": 3 1 3 3 3 2 3 3 3 1 ...
Therefore 889 total passengers
TASK 3b Use R to count the number of passengers who survived the sinking of the Titanic.
mytable<-with(titanic.df,table(Survived))
mytable
## Survived
## 0 1
## 549 340
TASK 3c Use R to measure the percentage of passengers who survived the sinking of the Titanic.
prop.table((mytable))*100
## Survived
## 0 1
## 61.75478 38.24522
TASK 3d Use R to count the number of first-class passengers who survived the sinking of the Titanic.
mytable <- xtabs(~ Survived+Pclass, data=titanic.df)
mytable
## Pclass
## Survived 1 2 3
## 0 80 97 372
## 1 134 87 119
TASK 3e Use R to measure the percentage of first-class passengers who survived the sinking of the Titanic.
prop.table(mytable, 2)*100
## Pclass
## Survived 1 2 3
## 0 37.38318 52.71739 75.76375
## 1 62.61682 47.28261 24.23625
TASK 3f Use R to count the number of females from First-Class who survived the sinking of the Titanic
mytable <- xtabs(~ Survived+Pclass+Sex, data=titanic.df)
mytable
## , , Sex = female
##
## Pclass
## Survived 1 2 3
## 0 3 6 72
## 1 89 70 72
##
## , , Sex = male
##
## Pclass
## Survived 1 2 3
## 0 77 91 300
## 1 45 17 47
TASK 3g Use R to measure the percentage of survivors who were female
mytable <- xtabs(~ Survived+Sex, data=titanic.df)
prop.table(mytable,1)*100
## Sex
## Survived female male
## 0 14.75410 85.24590
## 1 67.94118 32.05882
TASK 3h Use R to measure the percentage of females on board the Titanic who survived
mytable <- xtabs(~ Survived+Sex, data=titanic.df)
prop.table(mytable,2)*100
## Sex
## Survived female male
## 0 25.96154 81.10919
## 1 74.03846 18.89081
TASK 3i Run a Pearson’s Chi-squared test to test the following hypothesis:
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.
mytable <- xtabs(~Survived+Sex, data=titanic.df)
addmargins(mytable)
## Sex
## Survived female male Sum
## 0 81 468 549
## 1 231 109 340
## Sum 312 577 889
chisq.test(mytable)
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: mytable
## X-squared = 258.43, df = 1, p-value < 2.2e-16