MATH F113

(Probability and Statistics)

Chandra Shekhar
Associate Professor

Department of Mathematics
BITS Pilani, Pilani Campus, Rajasthan 333 031
Email: [email protected]
Mobile: 9414492349
Chandra Shekhar MATH F113 (Probability and Statistics)
What have you covered?

In Lecture 17
Nomal Distribution
Standard Normal Distribution

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Exercise: X is normally distributed

and the mean of X is 12 and standard
deviation is 4.
Find
P (X ≥ 20), P (X ≤ 20), P (0 ≤ X ≤ 12)
Find x0 where P (X > x0) = 0.24
Find x0 and x1, where
P (x0 < X < x1) = 0.50 and
P (X > x1) = 0.25
Chandra Shekhar MATH F113 (Probability and Statistics)
Normal Distribution (Cont...)

Exercise: In a distribution exactly

normal, 7% of the items are under
35 and 89% are under 63. What are
the mean and standard deviation of
the distribution?

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Solution:
X ∼ N (µ, σ)
P (X < 35) = 0.07, P (X < 63) = 0.89
35 − µ
P (Z < z1) = 0.07 where z1 =
σ
63 − µ
P (Z < z2) = 0.89 where z2 =
σ
From table, z1 = −1.48, z2 = 1.23.
µ = 50.3, σ = 10.33

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Exercise: If the skulls are classi-

fied as A, B, C according as length-
breadth index is under 75, between
75 and 80, or over 80, find approxi-
mately the mean and standard devi-
ation of a series in which A are 58%,
B are 38% and C are 4%.

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Solution:
X ∼ N (µ, σ)
P (X < 75) = 0.58, P (X > 80) = 0.04
75 − µ
P (Z < z1) = 0.58 where z1 = ... etc
σ
z1 = 0.2, z2 = 1.75

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Exercise 43/pp.146: Let X de-

note the time in hours needed to lo-
cate and correct a problem in the
software that governs the timing of
traffic lights in the downtown area of
a large city. Assume X is normally
distributed with mean 10 hours and
variance 9.

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

(a) Find the probability that the next

problem will require at most 15 hours
to find and correct.
(b) The fastest 5% of repairs take at
most how many hours to complete?

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Exercise 41/4.4/pp.146:
Most galaxies take the form of a flat-
tened disc, with the major part of
the light coming from this very thin
fundamental plane. The degree of
flattening differs from galaxy to galaxy.
In the milky way Galaxy most gases
are concentrated near the center of
the fundamental plane.
Chandra Shekhar MATH F113 (Probability and Statistics)
Normal Distribution (Cont...)

Let X denote the perpendicular dis-

tance from this center to a gaseous
mass. Let X is normally distributed
with mean 0 and standard deviation
100 parsecs
(a) Sketch a graph of the density for
X. Indicate on this graph the proba-
bility that a gaseous mass is located
within 200 parsecs of the center of
the fundamental plane. Find this prob-
ability. Chandra Shekhar MATH F113 (Probability and Statistics)
Normal Distribution (Cont...)

(b) Approximately, what percentage

of the gaseous masses are located more
than 250 parsecs from the center of
the plane?
(c) What distance has the property
that 20% of the gaseous masses are
at least this far from the fundamen-
tal plane?

Chandra Shekhar MATH F113 (Probability and Statistics)

Normal Distribution (Cont...)

Exercise: Let X ∼ N (µ, σ2) if σ2 =

µ2, (µ > 0) express
P (X < −µ|X < µ)
in terms of cumulative distribution
function of N (0, 1)

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution

Log Normal Distribution The

positive random variable X is said
to have a log normal distribution, if
loge X is normally distributed. That
is,
loge X ∼ N (µ, σ)

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

In probability and statistics, the log-

normal distribution is the single tailed
probability distribution of any ran-
dom variable whose logarithm is nor-
mally distributed.
If Y is a random variable with a nor-
mal distribution, then X = exp(Y )
has a log normal distribution; like-
wise, if X is log normally distributed,
then log(X) is normally distributed.
Chandra Shekhar MATH F113 (Probability and Statistics)
Log Normal Distribution (Cont...)

Log Normal Distribution: The

PDF is
1 (ln x−µ)2
−
f (x; µ, σ) = √ e 2σ2 ; x>0
2πσx
The CDF is
 
1 1 ln x − µ
F (x) = + erf √
2 2 σ 2

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Remark: The moment generating

function for log normal does not ex-
ist.
The mean is
2 /2
E(X) = eµ+σ
and the variance is
 2  2
V ar(X) = e − 1 e2µ+σ
σ

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Hence,
 
1 V ar(X)
µ = ln(E(X)) − ln 1 +
2 (E(X))2
 
V ar(X)
σ 2 = ln +1
(E(X))2

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Exercise 45/pp.146 Let X be nor-

mal with mean µ and variance σ 2.
Let G denote the cumulative distri-
bution for Y = eX and let F denote
the cumulative distribution for X. Then,
G(y) = F (ln y)
and
G0(y) = F 0(ln y)/y

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

G(y) = P (Y ≤ y) = P (eX ≤ y)
= P (X ≤ ln y)
Now X ∼ N (µ, σ). Therefore,
G(y) = P (X ≤ ln y)
Zln y (x−µ)2
1 −
√ e 2σ 2 dx µ, x ∈ (−∞, ∞) σ > 0
2πσ
−∞

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

or,
Zy (ln y−µ)2
1 −
G(y) = √ e 2σ 2 d(ln y)
2πσ
0

µ, x ∈ (−∞, ∞) y, σ > 0
where y = ex
Zy (ln y−µ)2
1 −
G(y) = √ e 2σ 2 d(ln y) = F (ln y)
2πσ
0
Chandra Shekhar MATH F113 (Probability and Statistics)
Log Normal Distribution (Cont...)

Hence show that the density for Y is

given by
1 (ln y−µ)2
−
g(y) = √ e 2σ2 ,
2πσy
µ ∈ (−∞, ∞), y, σ > 0
Zy (ln y−µ)2
1 −
G(y) = √ e 2σ2 d(ln y) = F (ln y)
2πσ
0
g(y) = G0(y) = F 0(ln y)/y

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Exercise 46/pp.147 Let Y denote

the diameter in millimeters of sty-
rofoam pellets used in packing. As-
sume that Y has a log-normal distri-
bution with parameter µ = 0.8, σ =
0.1.
(i) Find the probability that a ran-
domly selected pellet has a diameter
that exceeds 2.7 mm
Chandra Shekhar MATH F113 (Probability and Statistics)
Log Normal Distribution (Cont...)

(ii) Between what two values will Y

fall with probability approximately
0.95?
Solution: (i)
P (Y > 2.7) = P (Z > (ln 2.7 − 0.8)/0.1)
= 1 − F (1.93)
(ii) We need to find y1 and y2 such
that
P (y1 < Y < y2) = 0.95
Chandra Shekhar MATH F113 (Probability and Statistics)
Log Normal Distribution (Cont...)

Find symmetric to mean

 
ln y1 − 0.8 ln y2 − 0.8
P )<Z< = 0.95
0.1 0.1
(ln y1−0.8)/0.1 = z0.975 = −1.96, y1 = 1.829
(ln y2 − 0.8)/0.1 = z0.025 = 1.96, y2 = 2.707

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Exercise: If log10 X is normally dis-

tributed with mean 4 and variance
4, find

P (1.202 < X < 83180000)

(Given, log10 1202 = 3.08, log10 8318 = 3.92)

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Solution: Since, log X is an increas-

ing function of X, we have
P (1.202 < X < 83180000)
= P (log10 1.202 < log10 X < log10 83180000)
= P (0.08 < log10 X < 7.92)
= P (0.08 < Y < 7.92)
where
Y = log10 X ∼ N (4, 2)

Chandra Shekhar MATH F113 (Probability and Statistics)

Log Normal Distribution (Cont...)

Required Probability
= P (0.08 < Y < 7.92)
= P (−1.96 < Z < 1.96)
= 2P (0 < Z < 1.96) = 0.95

Chandra Shekhar MATH F113 (Probability and Statistics)