Statistical Analysis by R
By
Sunil Kadam
d1=c(6,7,5,7,7,8,7,6,9,7,4,10,6,8,8,9,5,6,4,8)
table(d1)
sort(d1)
table(d1)
cumsum(table(d1))
hist(d1)
mean(d1)
median(d1)
mode=names(table(d1))[table(d1)==max(table(d1))]
# Mean Deviation for d1
d1
length(d1)
m1=mean(d1)
m1
d1_mean_diff=c(abs(d1-m1))
d1_mean_diff
sum_md=sum(d1_mean_diff)
md=sum_md/length(d1)
md
# Calculation of Mean Deviation from Median
d1
m2=median(d1)
m2
m_diff_med=c(abs(d1-m2))
sum_m_diff_med=sum(m_diff_med)
md_median=sum_m_diff_med/length(d1)
md_median
calls=c(28,122,217,130,120,86,80,90,140,120,70,40,145,113,90,68,174,194,170,100,75,104,9
7,75,123,100,75,104,97,75,123,100,89,120,109)
range(calls)
low_val=0
high_val=240
step_val=40
x_breaks=seq(low_val,high_val,by=step_val)
cut(calls,break=x_breaks,right=FALSE)
I=cut(calls,break=x_breaks,right=FALSE)
y=table(I)
df=[Link](y)
df$cumf=cumsum(df$freq)
summary(df)
hist(calls)
I_mid=seq(low_val+step_val/2,high_val-step_val/2,step_val)
df$I_mid=I_mid
df
med1=80+step_val*(35/2-8)/14
mod1=80+step_val*(14-7)/(2*14-7-9)
sd(d1)
var(d1)
25
56
87
65
34
99
35
87
77
94
wt1=c(25,56,87,65,34,99,35,87,77,87)
table(wt1)
cumsum(table(wt1))
hist(wt1)
range(wt1)
l1=20
maxl2=100
step1=20
x_br1=seq(l1,maxl2,by=step1)
int1=cut(wt1,x_br1,right = FALSE)
Y1=table(int1)
df_wt$cumfq=cumsum(df_wt$Freq)
df_wt
mean(wt1)
median(wt1)
m1=names(table(wt1))[table(wt1)==max(table(wt1))]
m1
# Reading data from CSV files
d2=[Link]("[Link]")
d2
nrow(d2)
ncol(d2)
# Structure of CSV dataframe
str(t1)
# Calculations on CSV files records
max(d2$Age)
# Extracting records from data
a1=subset(d2,Age==max(d2$Age))
a1
a1=subset(d2,name=="sunil")
a1
a1=subset(d2,Age>=25)
a1
mean_age=mean(d2$Age)
mean_age
d2$Dept
subset(d2,Dept=="IT")
# Adding Records to existing data with rbind()
newd2=[Link](Roll_no=c(106,107),name=c("sana","bina"),Age=c(25,24),Dept=c("IT","HR"))
combine_d2=rbind(d2,newd2)
combine_d2
# installing libary MASS
library("MASS")
# one of file in MASS
ships
# Structure of file ships
str(ships)
# Analysis of ships
max(ships$incidents)
max(ships$service)
summary(ships$service)
# extracting field from ship to new variable
tys=c(ships$type)
tys
table(tys)
cumsum(table(tys))
table(yrs)
summary(yrs)
hist(yrs)