Unit - Ii

TWO DIMENSIONAL
RANDOM VARIABLES
IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS /UNIT–

II/PPT/VER1.2
1
SYLLABUS:
Joint Distributions – Marginal and

Conditional Distributions – Functions of two
dimensional random variables – Regression
Curve – Correlation.
IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

/UNIT–II/PPT/VER1.2
2
TWO - DIMENSIONAL R.V.
Let S be the sample space. Let X = X(s)

and Y = Y(s) be two functions each assigning a
real number to each outcome s є S. Then (X,Y)
is a two – dimensional random variable.
The range of the two - dimensional r.v. (X,Y) is
R( X ,Y ) = {( x, y) : x Î Rx , y Î Ry } Ì R 2

3
Two Dimensional R.V. are of two types:
1. Two dimensional Discrete R.V.
2. Two dimensional Continuous R.V.
Two Dimensional Discrete R.V.:
If the possible values of (X,Y) are finite or countably infinite,

then (X,Y) is called a two – dimensional discrete r.v. When
(X,Y) is a two- dimensional discrete r.v. the possible values of
(X,Y) may be represented as (xi ,yj), I = 1,2, … n,… , j =
1,2,…m, …
Two Dimensional Continuous R.V.:
If (X,Y) can assume all values in a specified region R in the

XY plane (X,Y) is called a two dimensional continuous r.v.
/UNIT–II/PPT/VER1.2 4
Joint Distributions - Marginal and Conditional Distributions
Joint Probability distribution of two random variables

X and Y
Two Dimensional Discrete Random Variables
Marginal Probability Mass function(p.m.f)
Conditional Distribution
PROBLEMS

Two Dimensional Continuous Random Variables
Marginal Probability Density function (p.d.f)
Conditional Distribution
Cummulative Distribution [Discrete & Continuous]
Independent Random Variables [Discrete & Continuous]
PROBLEMS
IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND 6

STATISTICS /UNIT–II/PPT/VER1.2
Joint Probability distribution of two random
variables X and Y
We define the probability of joint event ( X  x, Y  y) which

is a function of the numbers x and y by a joint probability
distribution function and denoted by
F( X ,Y ) ( x, y ) = P( X £ x, Y £ y )
FX ( x) = P( X £ x)
FY ( y ) = P(Y £ y )
IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND

STATISTICS /UNIT–II/PPT/VER1.2 7
Two Dimensional Discrete Random Variables
Joint Probability Mass Function of X and Y:
If (X,Y) is a two-dimensional discrete r.v. such that

P (x = xi ,y = yj) = pij , then pij is called the p.m.f or
simply the probability function of (X,Y) provided the
following conditions are satisfied.
 i  pij  0, for all i, j

 ii   pij  1
j i
The set of triples {xi ,yj ,pij} , i= 1,2,…, m,…, j = 1,2,…,

n,…, is called the joint probability distribution of (X,Y).

Marginal Probability Distribution:
The individual probability distribution of a random variable
is referred to as its marginal Probability distribution.
Marginal probability mass function of X:
If the joint probability distribution of two random variables
X and Y is given, Then Marginal probability mass function of X is
given by
f ( x )  p X ( xi )  p ( X  xi )
 p[ X  xi , Y  y j ] j  1, 2..m
 Pi .
Then Marginal probability mass function of Y is given by
f ( y )  pY ( y j )  p (Y  y j )
 p[ X  xi , Y  y j ] i  1, 2....n
 Pj .
Conditional Probability Distribution
If (X,Y) are discrete random variables then,

Conditional probability distribution of X given Y = yj
[ X  xi & Y  y j ] pij
p[ X  xi / Y  y j ]  p 
p[Y  y j ] p* j
Conditional probability distribution of Y given X = xi
[ X  xi & Y  y j ] pij
p[Y  y j / X  xi ]  p 
p[ X  xi ] pi*

Joint Probability Density Function:

11
Conditional Probability Distribution
If (X,Y) are continuous random variables then,

Conditional probability distribution of X given Y = yj
f ( x, y)
f ( x / y)  if f ( y)  0
f ( y)
Conditional probability distribution of Y given X = xi
f ( x, y )
f ( y / x)  if f ( x)  0
f ( x)

12
Cumulative Distribution Function
The cdf of a discrete r.v. (X,Y) can be written as

F X ,Y   x, y    p X ,Y   xi , y j 
xi  x y j  y
The cdf of a continuous r.v. (X,Y) can be written as

x y
F X ,Y   x, y     f  X ,Y   u , v  dudv
 
If F(X,Y) be the joint probability distribution function then the

joint probability density function f(x,y) is given by
¶ F ( x, y) 2
f ( x, y) =
¶ x¶ y
13
PROPERTIES OF DISTRIBUTION FUNCTION
1. F(-∞, -∞) = 0, F(-∞, y) = 0, F(x, -∞) = 0

2. F(-∞, ∞) = 1
3. 0 ≤ F(x, y) ≤ 1
4. F(x, y) is an increasing function of x and y.
(i.e.) if x1 < x2 and y1 < y2 then F(x1, y1) ≤ F(x2, y1) ≤ F(x2, y2)
and F(x1, y1) ≤ F(x1, y2) ≤ F(x2, y2)
5. F(x, y) is right continuous in each of its variates.
(i.e.)
lim F  x, y   F  a, y 
x a
lim F  x, y   F  x, b 
y b
6. P(a < X ≤ b, Y ≤ y) = F(b, y) - F(a, y)

7. P(X ≤ x, c < Y ≤ d) = F(x, d) - F(x, c)
8. If P(a < X ≤ b, c < Y ≤ d) = F(b, d) - F(a, d) + F(a, c) - F(b, c)

Independent Random Variables
Let X and Y be two random variables, discrete or

continuous, with the joint probability distribution f(x,y) and
marginal distribution g(x) and h(y) respectively, the random
variable X and Y are said to be statistically independent if and
only if
f(x, y)= g(x)h(y)
for all (x, y) within their independent random variable :
If (X,Y) are discrete then

pij  [ pi * ]*[ p* j ]
If (X,Y) are continuous then
f ( x, y)  f X ( x) * fY ( y)
15
PROBLEMS ON TWO DIMENSIONAL DISCRETE RANDOM
VARIABLES
PROBLEM 1:

PROBLEM 2:

22
STATISTICS /UNIT–II/PPT/VER1.2
PROBLEMS ON TWO DIMENSIONAL CONTINUOUS RANDOM
VARIABLES
PROBLEM 1:

25
26
PROBLEM 2:

29
FUNCTIONS OF TWO DIMENSIONAL R.V.:

Problems on two dimensional random variables :

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS 33
Regression:
It is a mathematical measure of the average relationship between
two or more variables in terms of the original limits of the data.
Lines of Regression:
The line of regression of y on x is

y
y y r (x  x )
x
The line of regression of x on y is
x
xx r ( y  y)
y

Note: Both the lines of regression pass through
Regression Coefficients:
Y
r  bYX
Regression Coefficients of y on x is X

Regression Coefficients of x on y is r X  bXY
Y
Angle between the regression lines:
Y
The slopes of the regression lines are m1  r
X
1 Y
m2 
r X
If ө is the angle between the regression lines, then

 x y 1  r 2 
tan   2
 x   y2  r 
Problems on Regression:

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS /UNIT–
II/PPT/VER1.2 39
40
CORRELATION
Correlation:
If the two variables vary such that the change in one
variable affect the change in the other variable. The variable
are said to be correlated.
Eg: There exist some relationship between height and

weight of the person.
Correlation Coefficient:
It is the parameter which measures the strength and
direction of a relationship between two variables

To define the Covariance, we need to describe the expected
value of a function of two random variables g(X,Y)
Expected Values of a Two - Dimensional R.V.:
If (X,Y) is a two-dimensional r.v. with joint probability

mass function pij, then
E{g  X , Y }   g  xi , y j  pij
j i
If (X,Y) is a two-dimensional continuous r.v. with joint pdf fx,y),

then  
E{g  X , Y }    g  x, y  f  x, y dxdy
 

Covariance :
It is defined as the useful measure to study the relationship between
the variables.
Cov(X,Y) = E (XY) – E(X) E(Y)
Note:
If X and Y are independent , then Cov[x,y] = 0
If X and Y are independent ,then E[xy] = E[x] E[y]
Variance:
If X and Y are random variables ,then

var  x    x 2
var  y    y 2

Results :
1) Cov [ax,by] = ab cov [x,y]
2) Var [X+Y] = Var [x] + Var [y] + 2 Cov [X,Y]
3) Cov [X+a,Y+b] = Cov [X,Y]
4) Var [aX+b] = a2 Var [x]
Types of Correlation :
1) Positive and Negative
2) Simple, Partial and Multiple
3) Linear and Non - Linear
1) Positive Correlation: If the two variables deviate in the same

direction (ie) if the increase (decrease) of one variable results
in the corresponding increase (decrease) of the other variable
Eg: Correlation between rainfall and production are positive

Negative Correlation:
If the two variables deviate in the opposite direction. (i.e.) if the
increase (decrease) of one variable results in the corresponding decrease
(increase) of the other variable.
Eg: Correlation between Price of a commodity and its demand are
negative
2) Simple, Partial and Multiple Correlation:

If only two variables are considered for correlation Analysis it
is called simple correlation.
Eg: Height and Weight of students in a class.
If two or more variables are considered for correlation

Analysis ,it is called Multiple Correlation.
Eg: In the study of relationship between the yield of rice ,both the
amount of rainfall and usage of fertilizers are considered.

3) Linear and Non-Linear Correlation:
If the amount of change in one variable tends to bear
the constant ratio to the amount of change in the other
variable, then the correlation is said to be linear.
If the amount of change in one variable does not bear

the constant ratio to the amount of change in the other
variable, then the correlation is said to be Non-linear or
Curvilinear.
Eg: If rainfall is more then the production of rice would not

necessarily be doubled.

y y y
x x x
(a) Positive (b) Strong (c) Perfect

positive positive
Scatter Plots
51
y y y
x x x
(d) Negative (e) Strong (f) Perfect

negative negative
Scatter Plots
y
y
x x
(g) No Correlation (h) Nonlinear Correlation
Scatter Plots
53
 Measures the relative strength of the linear
relationship between two variables
 Unit-less
 Ranges between –1 and 1
 The closer to –1, the stronger the negative linear relationship
 The closer to 1, the stronger the positive linear relationship
 The closer to 0, the weaker any positive linear relationship

Y Y Y
X X X
r = -1 r = -.6 r=0
Y
Y
Y
X X
r = +1 r = +.3 r=0 X
55
Results:
The value of a correlation coefficient ranges between -1 and 1.
Two Independent Random variables are said to be uncorrelated.
When X and Y are independent ,then cov(X,Y)=0
-1 ≤ r ≤ 1
If r > 0 we have a Positive correlation
If r < 0 we have a Negative correlation
If r = 0 we have No correlation

KARL PEARSON’S CO-EFFICIENT OF
CORRELATION:
It measures the strength of the linear

relationship between the variables. Correlation
Coefficient between two random variables X and Y
is usually denoted by r(X,Y) and defined as
cov( X , Y )
r( X ,Y ) 
 x . y

57
If (xi ,yi) i =1,2,…,n is the bivariate distribution, then
cov( X , Y ) 
 XY
 XY
n
X
 x
Y
 y
n n
( X 2 )  ( X ) 2
x 
n
( Y 2 )  (Y ) 2
y 
n
where n is the no of items in the given data.

59
60
RANK CORRELATION :
Let us suppose that a group of n individuals are

arranged in order of merit in possession of two
characteristic A and B. These ranks will, in general, be
different.
Spearman’s Rank Correlation Coefficient is given by

n
6 di 2
r  1 i 1
where d i  xi  yi
n(n  1)2

Problems based on Rank Correlation :
Find the rank correlation coefficient between the following

data.
Rank in X 1 2 3 4 5 6 7
Rank in Y 4 3 1 2 6 5 7

62
Solution:
X Y di  xi  yi d i2
1 4 -3 9
2 3 -1 1 6 * 20
r  1
3 1 2 4 7(49  1)
4 2 2 4
120
5 6 -1 1  1
6 5 1 1
336
7 7 0 0  0.6429
d 0 d
2
i i  20
Rank correlation coefficient is given by

n
6 di 2
r  1 i 1
where d i  xi  yi
n(n  1) 2

Repeated Ranks:
If there is more than one item with the same value in the
series, then the usual method cannot be used, so common
ranks are given to repeated ranks are given the following
Correction is made in the correction formula.
In the correlation formula, we add a factor to where m is

the number of items and item is repeated. This correction
factor is to be added for each repeated value.

64
Problems on Repeated ranks
Find the rank correlation coefficient from the following data
X 68 64 75 50 64 80 75 40 55 64
Y 62 58 68 45 81 60 68 48 50 70
Solution:
X Y Rank X Rank Y
(xi) (yi)
di  xi  yi di 2
68 62 4 5 -1 1
64 58 6 7 -1 1
75 68 2.5 3.5 -1 1
50 45 9 10 -1 1
64 81 6 1 5 25
80 60 1 6 -5 25
75 68 2.5 3.5 -1 1
40 48 10 9 1 1
55 50 8 8 0 0
64 70 6 2 4 16
d 0 d
2
i i  72

65
In X series
so common rank 2.5 is given for each 75.
so common rank 6 is given for each 64
so common rank 3.5 is given for each 68
m = 10
(6)(72)
  1  0.564
(10)(99)
Repeated value Positions Average
ranks
75 2&3 (2+3)/2=2.5
64 5,6&7 (5+6+7)/3=6
68 3&4 (3+4)/2=3.5


Unit - Ii

Uploaded by

Copyright:

Available Formats

Unit - Ii

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Unit - Ii

Uploaded by

Copyright:

Available Formats

TWO DIMENSIONAL

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS /UNIT–

Joint Distributions – Marginal and

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

Let S be the sample space. Let X = X(s)

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

Two Dimensional Discrete R.V.:

If the possible values of (X,Y) are finite or countably infinite,

Two Dimensional Continuous R.V.:

If (X,Y) can assume all values in a specified region R in the

Joint Probability distribution of two random variables

Marginal Probability Mass function(p.m.f)

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

Marginal Probability Density function (p.d.f)

Cummulative Distribution [Discrete & Continuous]

Independent Random Variables [Discrete & Continuous]

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND 6

We define the probability of joint event ( X  x, Y  y) which

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND

Joint Probability Mass Function of X and Y:

If (X,Y) is a two-dimensional discrete r.v. such that

 i  pij  0, for all i, j

The set of triples {xi ,yj ,pij} , i= 1,2,…, m,…, j = 1,2,…,

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

If (X,Y) are discrete random variables then,

Conditional probability distribution of Y given X = xi

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

If (X,Y) are continuous random variables then,

Conditional probability distribution of Y given X = xi

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

The cdf of a discrete r.v. (X,Y) can be written as

The cdf of a continuous r.v. (X,Y) can be written as

If F(X,Y) be the joint probability distribution function then the

1. F(-∞, -∞) = 0, F(-∞, y) = 0, F(x, -∞) = 0

6. P(a < X ≤ b, Y ≤ y) = F(b, y) - F(a, y)

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

Let X and Y be two random variables, discrete or

If (X,Y) are discrete then

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

The line of regression of y on x is

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS 36

If ө is the angle between the regression lines, then

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND

Eg: There exist some relationship between height and

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

Expected Values of a Two - Dimensional R.V.:

If (X,Y) is a two-dimensional r.v. with joint probability

If (X,Y) is a two-dimensional continuous r.v. with joint pdf fx,y),

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND STATISTICS

If X and Y are random variables ,then

IFETCE/H&S- II/MATHS/MATHIVADHANA/IYEAR/ M.E.(CSE)/I-SEM/MA7155/APPLIED PROBABILITY AND

1) Positive Correlation: If the two variables deviate in the same