You are on page 1of 39

Discrete and Continuous Probability distributions

Lab - 6

S. Devi Yamini

August 3, 2020

August 3, 2020 1 / 22
LAB 6

AIM
Computing, plotting, and visualizing discrete and
continuous distributions and visualizing it.

August 3, 2020 2 / 22
Probability distributions

Discrete
Binomial distribution

August 3, 2020 3 / 22
Probability distributions

Discrete
Binomial distribution
Poisson distribution

August 3, 2020 3 / 22
Probability distributions

Discrete
Binomial distribution
Poisson distribution

Continuous
Normal distribution

August 3, 2020 3 / 22
BINOMIAL DISTRIBUTION

August 3, 2020 4 / 22
Binomial Distribution

Binomial probability
P(X = x) = xn p x q n−x , x = 0, 1, . . . , n


n - number of trials
x - number of successes
p - prob of success
q - prob of failure

August 3, 2020 5 / 22
Binomial Distribution

Binomial probability
P(X = x) = xn p x q n−x , x = 0, 1, . . . , n


n - number of trials
x - number of successes
p - prob of success
q - prob of failure

Mean= np
Variance= npq

August 3, 2020 5 / 22
Binomial distribution

To find P(X = x), the R-code is dbinom(x,n,p)

August 3, 2020 6 / 22
Binomial distribution

To find P(X = x), the R-code is dbinom(x,n,p)


To display the probabilities for all possible values of X , the R-code is
x =0:n
dbinom(x,n,p)

August 3, 2020 6 / 22
Binomial distribution

To find P(X = x), the R-code is dbinom(x,n,p)


To display the probabilities for all possible values of X , the R-code is
x =0:n
dbinom(x,n,p)
The cumulative distribution P(X ≤ x) is got by
pbinom(x,n,p,lower.tail=T)
Here lower.tail takes true because X covers the values from 0 to x

August 3, 2020 6 / 22
Binomial distribution

To find P(X = x), the R-code is dbinom(x,n,p)


To display the probabilities for all possible values of X , the R-code is
x =0:n
dbinom(x,n,p)
The cumulative distribution P(X ≤ x) is got by
pbinom(x,n,p,lower.tail=T)
Here lower.tail takes true because X covers the values from 0 to x
P(X > x) is got by pbinom(x,n,p,lower.tail=F)

August 3, 2020 6 / 22
Binomial distribution

To find P(X = x), the R-code is dbinom(x,n,p)


To display the probabilities for all possible values of X , the R-code is
x =0:n
dbinom(x,n,p)
The cumulative distribution P(X ≤ x) is got by
pbinom(x,n,p,lower.tail=T)
Here lower.tail takes true because X covers the values from 0 to x
P(X > x) is got by pbinom(x,n,p,lower.tail=F)
Plotting the binomial distribution:
x =0:n
y =dbinom(x,n,p)
plot(x,y ,type= “h”)

August 3, 2020 6 / 22
Binomial Distribution

Problem 1
For a random variable X following B(7, 41 ), (a) Compute the probability of
two successes, (b) Compute the binomial probabilities for the whole space
(c) Display those probabilities in a table (d) Plot the distribution.

August 3, 2020 7 / 22
Binomial Distribution

Problem 1
For a random variable X following B(7, 41 ), (a) Compute the probability of
two successes, (b) Compute the binomial probabilities for the whole space
(c) Display those probabilities in a table (d) Plot the distribution.
(a) dbinom(2, size= 7,prob= 41 )

August 3, 2020 7 / 22
Binomial Distribution

Problem 1
For a random variable X following B(7, 41 ), (a) Compute the probability of
two successes, (b) Compute the binomial probabilities for the whole space
(c) Display those probabilities in a table (d) Plot the distribution.
(a) dbinom(2, size= 7,prob= 41 )
[1] 0.3114624

August 3, 2020 7 / 22
Binomial Distribution

Problem 1
For a random variable X following B(7, 41 ), (a) Compute the probability of
two successes, (b) Compute the binomial probabilities for the whole space
(c) Display those probabilities in a table (d) Plot the distribution.
(a) dbinom(2, size= 7,prob= 41 )
[1] 0.3114624
(b) dbinom(0 : 7, 7, 14 )

August 3, 2020 7 / 22
Binomial Distribution

Problem 1
For a random variable X following B(7, 41 ), (a) Compute the probability of
two successes, (b) Compute the binomial probabilities for the whole space
(c) Display those probabilities in a table (d) Plot the distribution.
(a) dbinom(2, size= 7,prob= 41 )
[1] 0.3114624
(b) dbinom(0 : 7, 7, 14 )
(c) p = data.frame(0 : 7, dbinom(0 : 7, 7, 14 )
round(p, 4)

August 3, 2020 7 / 22
Binomial Distribution

Problem 1
For a random variable X following B(7, 41 ), (a) Compute the probability of
two successes, (b) Compute the binomial probabilities for the whole space
(c) Display those probabilities in a table (d) Plot the distribution.
(a) dbinom(2, size= 7,prob= 41 )
[1] 0.3114624
(b) dbinom(0 : 7, 7, 14 )
(c) p = data.frame(0 : 7, dbinom(0 : 7, 7, 14 )
round(p, 4)
(d) plot(0 : 7, dbinom(0 : 7, 7, 41 ), type = ’o’)

August 3, 2020 7 / 22
Binomial Distribution

Problem 2
If 10 % of the screws produced by an automatic machine are defective,
find the probability that out of 20 screws selected at random, there are (a)
exactly 2 defectives (b) At most 2 defectives (c) between 1 and 3
defectives ( inclusive)

August 3, 2020 8 / 22
Binomial Distribution

Problem 2
If 10 % of the screws produced by an automatic machine are defective,
find the probability that out of 20 screws selected at random, there are (a)
exactly 2 defectives (b) At most 2 defectives (c) between 1 and 3
defectives ( inclusive)
(a) dbinom(2, 20, 0.10)

August 3, 2020 8 / 22
Binomial Distribution

Problem 2
If 10 % of the screws produced by an automatic machine are defective,
find the probability that out of 20 screws selected at random, there are (a)
exactly 2 defectives (b) At most 2 defectives (c) between 1 and 3
defectives ( inclusive)
(a) dbinom(2, 20, 0.10)
(b) pbinom(2, 20, 0.10, lower .tail = T )

August 3, 2020 8 / 22
Binomial Distribution

Problem 2
If 10 % of the screws produced by an automatic machine are defective,
find the probability that out of 20 screws selected at random, there are (a)
exactly 2 defectives (b) At most 2 defectives (c) between 1 and 3
defectives ( inclusive)
(a) dbinom(2, 20, 0.10)
(b) pbinom(2, 20, 0.10, lower .tail = T )
(c) sum(dbinom(1 : 3, 20, 0.10))

August 3, 2020 8 / 22
Binomial Distribution

Problem 2
If 10 % of the screws produced by an automatic machine are defective,
find the probability that out of 20 screws selected at random, there are (a)
exactly 2 defectives (b) At most 2 defectives (c) between 1 and 3
defectives ( inclusive)
(a) dbinom(2, 20, 0.10)
(b) pbinom(2, 20, 0.10, lower .tail = T )
(c) sum(dbinom(1 : 3, 20, 0.10))
Compute the probability for at least 2 defectives

August 3, 2020 8 / 22
POISSON DISTRIBUTION

August 3, 2020 9 / 22
Problem 1:

1. Compute P(X=5) with Poisson parameter λ = 7


dpois(x=5,lambda=7)
OR
dpois(5,7)

2. Compute P(X=0), P(X=1),. . .,P(X=5)


dpois(0:5, 7)

3. Compute P(X≤ 5)
sum(dpois(0:5, 7))
OR
ppois(q=5, lambda=7, lower.tail=T)

4. Compute P(X¿5)
ppois(q=5, lambda=7, lower.tail=F)

August 3, 2020 10 / 22
Problem 2

Check the relationship between mean and variance in Poisson distribution


with λ = 4 and n = 100

R code
x = 0 : 100
p = dpois(x, 4)
mean = sum(x ∗ p)
var = sum(x 2 ∗ p) − (mean)2
mean
var

August 3, 2020 11 / 22
Problem 3

Compute the poisson probabilities and cumulative probabilities of the


values between 0 and 10 for the parameter 2 in a table (rounded upto 4
decimal places).

p=data.frame(0:10, dpois(0:10,2), ppois(0:10,2))


round(p,4)
p

August 3, 2020 12 / 22
Problem 4

If there are twelve cars crossing a bridge per minute on an average, find
the probability of having sixteen or more cars crossing the bridge in a
particular minute.

August 3, 2020 13 / 22
Problem 4

If there are twelve cars crossing a bridge per minute on an average, find
the probability of having sixteen or more cars crossing the bridge in a
particular minute.

ppois(15, lambda=12, lower.tail=F)

August 3, 2020 13 / 22
Problem 5

Compute the Binomial and Poisson probabilities using the data n = 8 and
λ = 2.4. Also plot the probabilities
Binomial
x =0:8
p=dbinom(x,8,0.3)
plot(x, p, type=”h”, main=”Pmf for binomial distribution”,col=2)

Poisson
x =0:8
p=dpois(x,2.4)
plot(x,p,type=”h”, main=”Pmf for Poisson distribution”,col=4)

August 3, 2020 14 / 22
Try these

Poisson distribution with parameter 2


How to obtain a sequence from 0 to 10
Calculate P(0), P(1),. . .,P(10) and make the output prettier
Find P(X≤ 6)
Sum all the probabilities
Find P(X¿6)
Make a table of first 11 poisson probs and make the output prettier
Plot the probabilities. Put some labels on both the axes and a title

August 3, 2020 15 / 22
NORMAL DISTRIBUTION

August 3, 2020 16 / 22
Problem 1

Create a sequence of numbers from -10 to 10 incremented


by 0.1. Let the mean=2.5, standard deviation=0.5.
Visualize the normal curve for the above sequence. Also
find the cummulative distribution function.
Code:
x=seq(-10,10,by=0.1)
y=dnorm(x, mean=2.5,sd=0.5)
plot(x,y,type=”l”)
y1=pnorm(x,mean=2.5,sd=0.5)
plot(x,y1)

August 3, 2020 17 / 22
Problem 2

Create a sequence of 200 numbers with x=-3 to 3.


Visualize the standard normal curve with mean=0 and
sd=1
Code:
x=seq(-3,3,length=200)
y=dnorm(x,mean=0,sd=1)
plot(x,y,type=”l”)

August 3, 2020 18 / 22
Problem 3

Find the area to the left of 0, given a sequence from -3 to


3 follows Normal distribution wtih mean=0 and sd=1
Code:
x=seq(-3,3,length=200)
y=dnorm(x,mean=0,sd=1)
plot(x,y,type=”l”)
x=seq(-3,0,length=100)
y=dnorm(x,0,1)
polygon(c(-3,x,0),c(0,y,0),col=”red”)
pnorm(0,mean=0,sd=1)

August 3, 2020 19 / 22
Problem 4

For Problem 3, find the area to the left of 1. (First draw


the image and then compute)
Code:
x=seq(-3,3,length=200)
y=dnorm(x,mean=0,sd=1)
plot(x,y,type=”l”)
x=seq(-3,1,length=100)
y=dnorm(x,0,1)
polygon(c(-3,x,1),c(0,y,0),col=”blue”)
pnorm(1,mean=0,sd=1)

August 3, 2020 20 / 22
Problem 5

Compute the area between x=1 and 2 for Problem 3.


Code:
x=seq(-3,3,length=200)
y=dnorm(x,mean=0,sd=1)
plot(x,y,type=”l”)
x=seq(1,2,length=100)
y=dnorm(x,0,1)
polygon(c(1,x,2),c(0,y,0),col=”red”)
pnorm(2,mean=0,sd=1)-pnorm(1,mean=0,sd=1)
0.1359

August 3, 2020 21 / 22
Problem 6
Find the Quantile( or Percentile) when area is given. That
is find the value of x corresponding to 40%
x = seq(−3, 3, length = 200)
y = dnorm(x, mean = 0, sd = 1)
plot(x, y , type = ”l”)
qnorm(0.40, mean = 0, sd = 1)
−0.2533
x = seq(−3, −0.2533, length = 100)
y = dnorm(x, mean = 0, sd = 1)
polygon(c(−3, x, −0.2533), c(0, y , 0), col = 4)
text(−1, 0.2, “0.40”)
The last command prints 40% at the position
x = −1,y = 0.2. August 3, 2020 22 / 22

You might also like