titanic analysis

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

##     Survived          Pclass          Sex           Age       
##  Min.   :0.0000   Min.   :1.000   female:312   Min.   : 0.40  
##  1st Qu.:0.0000   1st Qu.:2.000   male  :577   1st Qu.:22.00  
##  Median :0.0000   Median :3.000                Median :29.70  
##  Mean   :0.3825   Mean   :2.312                Mean   :29.65  
##  3rd Qu.:1.0000   3rd Qu.:3.000                3rd Qu.:35.00  
##  Max.   :1.0000   Max.   :3.000                Max.   :80.00  
##      SibSp            Parch             Fare         Embarked
##  Min.   :0.0000   Min.   :0.0000   Min.   :  0.000   C:168   
##  1st Qu.:0.0000   1st Qu.:0.0000   1st Qu.:  7.896   Q: 77   
##  Median :0.0000   Median :0.0000   Median : 14.454   S:644   
##  Mean   :0.5242   Mean   :0.3825   Mean   : 32.097           
##  3rd Qu.:1.0000   3rd Qu.:0.0000   3rd Qu.: 31.000           
##  Max.   :8.0000   Max.   :6.0000   Max.   :512.329

sum(Titanic)#total no. of passengers

## [1] 2201

summary(titanic.df$Survived)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.0000  0.0000  0.3825  1.0000  1.0000

sum(titanic.df$Survived)

## [1] 340

mytable <- with(titanic.df, table(Survived)) 
prop.table(mytable)

## Survived
##         0         1 
## 0.6175478 0.3824522

prop.table(mytable)*100 

## Survived
##        0        1 
## 61.75478 38.24522

library(vcd)

## Loading required package: grid

View(Titanic)
mytable <- xtabs(~ Survived+Sex+Class, data=Titanic)
ftable(mytable) 

##                 Class 1st 2nd 3rd Crew
## Survived Sex                          
## No       Male           2   2   2    2
##          Female         2   2   2    2
## Yes      Male           2   2   2    2
##          Female         2   2   2    2

margin.table(mytable,c(1,3))

##         Class
## Survived 1st 2nd 3rd Crew
##      No    4   4   4    4
##      Yes   4   4   4    4

margin.table(mytable,1) 

## Survived
##  No Yes 
##  16  16

margin.table(mytable, 2)

## Sex
##   Male Female 
##     16     16

addmargins(mytable) 

## , , Class = 1st
## 
##         Sex
## Survived Male Female Sum
##      No     2      2   4
##      Yes    2      2   4
##      Sum    4      4   8
## 
## , , Class = 2nd
## 
##         Sex
## Survived Male Female Sum
##      No     2      2   4
##      Yes    2      2   4
##      Sum    4      4   8
## 
## , , Class = 3rd
## 
##         Sex
## Survived Male Female Sum
##      No     2      2   4
##      Yes    2      2   4
##      Sum    4      4   8
## 
## , , Class = Crew
## 
##         Sex
## Survived Male Female Sum
##      No     2      2   4
##      Yes    2      2   4
##      Sum    4      4   8
## 
## , , Class = Sum
## 
##         Sex
## Survived Male Female Sum
##      No     8      8  16
##      Yes    8      8  16
##      Sum   16     16  32

mtable <- xtabs(~ Sex+Survived, data=Titanic) 
addmargins(mtable) 

##         Survived
## Sex      No Yes Sum
##   Male    8   8  16
##   Female  8   8  16
##   Sum    16  16  32

chisq.test(mtable)

## 
##  Pearson's Chi-squared test
## 
## data:  mtable
## X-squared = 0, df = 1, p-value = 1