titanic=read.csv("
dim(titanic)
head(titanic)
tail(titanic)
titanic=na.omit(titanic)
dim(titanic)
attach(titanic)
plot(Fare~Age)
titanic[Fare>400,]
cor(Fare,Age)
summary(Age)
hist(Age)
hist(Age,nclass=70)
# Compare the survival rate between gender
table(Survived, Sex)
table(Age,Sex)
hist(Age[Sex=='male'],nclass=70)
hist(Age[Sex=='female'],nclass=70)
summary(Age[Sex=='male'])
summary(Age[Sex=='female'])
age.m=Age[Sex=='male']
age.f=Age[Sex=='female']
xb1=mean(age.m)
xb2=mean(age.f)
s1=sd(age.m)
s2=sd(age.f)
n1=length(age.m)
n2=length(age.f)
#Questions:
#1.How many passengers are there in the original Titanic data set including missing information on some variables?
#2.How many passengers are there with full information, i.e., no missing information on any variable?
#From here on use the Titanic data set with full passenger information.
#3.Find the mean Age, and mean Fare.
#4.Find the standard deviation of Age, and standard deviation of Fare.
#5.Interpret the meaning of the standard deviation of Age.
#6.What percent of male survived?
#7.What percent of female survived?
#8.How many male passenger 50 years or older?
#9.What percent of male passenger 50 years or older survived?
#10.Find the average age of male passenger 50 years or older.
#11.Find the average fare male passenger 50 years or older paid.
#12.How many people paid a fare more than 100?
#13.How many male passenger 50 years or older paid a fare more than 100?
#14.How many passenger 50 years or older paid a fare more than 100?
#15.How many passenger 50 years or older paid a fare more than 100 survived?
#16.How many passenger 50 years or older paid a fare more than 100 do not survived?
#17.What percent of passenger 50 years or older paid a fare more than 100 do not survived?
#18.What percent of male passenger 50 years or older paid a fare more than 100 do not survived?
#19.How many total Sibling and Spouse for all passenger 50 years or older paid a fare more than 100 who do not survived?
#20.Tabulate the Embarked locations for all passenger 50 years or older paid a fare more than 100 who do not survived.
# ANSWER SOLUTION FOR THE ABOVE:
#1.How many passengers are there in the original Titanic data set including missing information on some variables?
891
#2.How many passengers are there with full information, i.e., no missing information on any variable?
714
#From here on use the Titanic data set with full passenger information.
#3.Find the mean Age, and mean Fare.
mean(Age)
mean(Fare)
#4.Find the standard deviation of Age, and standard deviation of Fare.
sd(Age)
sd(Fare)
#5.Interpret the meaning of the standard deviation of Age.
The average deviation of all 714 Ages from the mean(Age) of 29.69
#6.What percent of male survived?
sum(Sex=='male' & Survived==1)/sum(Sex=='male')
#7.What percent of female survived?
sum(Sex=='female' & Survived==1)/sum(Sex=='female')
#8.How many male passenger 50 years or older?
sum(Sex=='male' & Age>=50)
#9.What percent of male passenger 50 years or older survived?
sum(Sex=='male' & Age>=50 & Survived==1)/sum(Sex=='male' & Age>=50)
#10.Find the average age of male passenger 50 years or older.
mean(Age[Sex=='male' & Age>=50])
#11.Find the average fare male passenger 50 years or older paid.
mean(Fare[Sex=='male' & Age>=50])
#12.How many people paid a fare more than 100?
sum(Fare>100)
#13.How many male passenger 50 years or older paid a fare more than 100?
sum(Sex=='male' & Age>=50 & Fare>100)/sum(Sex=='male' & Age>=50)
#14.How many passenger 50 years or older paid a fare more than 100?
sum(Age>=50 & Fare>100)
#15.How many passenger 50 years or older paid a fare more than 100 survived?
sum(Age>=50 & Fare>100 & Survived==1)/sum(Age>=50 & Fare>100)
#16.How many passenger 50 years or older paid a fare more than 100 do not survived?
sum(Age>=50 & Fare>100 & Survived==0)/sum(Age>=50 & Fare>100)
#17.What percent of passenger 50 years or older paid a fare more than 100 do not survived?
sum(Age>=50 & Fare>100 & Survived==0)/sum(Age>=50 & Fare>100)
#18.What percent of male passenger 50 years or older paid a fare more than 100 do not survived?
sum(Sex=='male' & Age>=50 & Fare>100 & Survived==0)/sum(Sex=='male' & Age>=50 & Fare>100)
#19.How many total Sibling and Spouse for all passenger 50 years or older paid a fare more than 100 who do not survived?
sum(SibSp[Age>=50 & Fare>100 & Survived==0])
#20.Tabulate the Embarked locations for all passenger 50 years or older paid a fare more than 100 who do not survived.
table(Embarked[Age>=50 & Fare>100 & Survived==0])