Sie sind auf Seite 1von 31

Lecture 3 of 5

10.3 Normal Distribution

a)

2
Identify the normal distribution, N ( , )

b)

Standardize the normal random variables

c)

Determine the mean and variance of normal distribution


problems

Normal Distribution
The normal distribution is the most important continuous
distribution in statistic. Examples of measurements which
follow the normal distribution are

Times taken to walk 1 km by 100 students


Height of school children aged between 7 to 8 years old
Weights of babies born in the year 2000 in Penang
Length of steel rods which are produced by a factory.

Normal Distribution
For a normally distributed variable X with mean and
standard deviation , the probability density function can
be written as
1
f ( x) =
e
2

1 x 2

< x <

If a continuous random variable X has a normal distribution


with mean and variance 2 we write this as :
X ~ N ( , 2 )
Mean , E ( X ) =
Variance , Var ( X ) = 2

Normal Distribution
f (x)

x
= mean = median = mode
Characteristics of Normal Distribution :
a)
b)
c)
d)
e)

bell shaped
the curve is symmetrical about the mode, median, mean
x can range in the value from to +
the total area under the curve is 1
the curve never touches the x - axis ( asymptote )

1
f) the maximum value for f (x) is approximately (0 .4 )

Standard Normal Distribution


The equation for the normal distribution is quite difficult to
work with. Thus, the standard normal distribution is used.
f (x)

=0

Characteristics of a standard normal distribution :


a) = 0 and 2 = 1
b) We write as Z ~ N(0,1)

Standardizing the Variable X


To change a normal distribution into a standard
normal distribution, we use
X
Z=

Where Z is the standard normal random variable


Z ~ N(0,1) the standard normal distribution
1 x 2

1
f ( x) =
e
2
1
z2
1
f ( z) =
e2
2

< x <

< z <

How to use the Standard Normal Distribution tables


We can use the standard normal table which gives the upper
end area, that is P(Z > z) = Q(z) to determine probabilities
like P(Z < z) , P(z1< Z <z2), P(|Z| < z) and P(|Z| > z)
For negative values of z, we need to use the symmetrical
property of the normal curve. Examine the following
examples:

Example 1
a) P ( Z 0.5)
0.3085

0.5

P ( Z 0.5) = 0.3085

b) P ( Z 1.0)
0.1587

1.0

P ( Z 1.0) = 0.1587

c) P ( Z < 1.86) = P ( Z 1.86) = 0.0314

=
-1.86

0.0314

1.86

d) P (0 < Z < 2.2) = 0.5 P( Z 2.2)


= 0.5 0.0139
= 0.4861

=
0

2.2
0.4861

2.2

2.2

e) P (1.96 < Z < 0) = P (0 < Z < 1.96)


= 0.5 0.0250
= 0.4750
=

=
1.96

-1.96

1.96

0.4750

1.96

f) P ( Z > 1.2)

= 1 P ( Z > 1.2)
= 1 0.1151
= 0.8849

-1.2

0.8849

1.2

g) P ( Z > 1)

= P ( Z > 1 or Z < 1)
= P ( Z > 1 + Z < 1)
= P ( Z > 1 + Z > 1)
= 2 P ( Z > 1)
= 2(2.1587) = 0.3174

-1

1
+

h) P ( Z < 1)

= P (1 < Z < 1)
= 1 2 P ( Z > 1)
= 1 2(0.1587) = 0.6826

=
0
-1

Example 2
Find the following probabilities
a)
b)
c)
d)

P ( Z 2.12)
P ( Z > 0.951)
P ( Z < 1.25)
P ( Z < 1.052)

Solution:
a) P ( Z 2.12) = 0.0170
2.12

b) P ( Z > 0.951) = 1 P ( Z 0.951)


= 1 0.1711
= 0.8289

-0.951

Solution:
c) P ( Z < 1.25) = P ( Z 1.25)
= 0.1056

-1.25

1.25

d) P ( Z < 1.052)
= 1 P ( Z 1.052)
= 1 0.1469
= 0.8531

1.052

Example 3
Find the following probabilities
a)
b)
c)
d)

P (0.50 < Z < 2.50)


P (2.05 < Z < 0.45)
P (0.422 < Z < 1.345)
P (0 < Z < 0.42)

Solution:
a) P (0.50 < Z < 2.50)
= P ( Z 0.50) P ( Z 2.50)
0.5 2.5

= 0.3085 0.00621
= 0.30229
b) P (2.05 < Z < 0.45)
= P ( Z 0.45) P ( Z 2.05)
= 0.3264 0.0202
= 0.3062

-2.05

-0.45 0.45 2.05

Solution:
c) P (0.42 < Z < 1.345)
= 1 P ( Z 0.42) P ( Z 1.345)
= 1 0.3372 0.0885
= 0.5743

d) P (0.42 < Z < 0)


= P (0 < Z < 0.42)
= P ( Z 0) P ( Z 0.42)
= 0.5 0.3372
= 0.1628

1.345

-0.42

-0.42

Example 4
Find the values of a

a) P ( Z > a ) = 0.3594
b) P ( Z < a ) = 0.0985
c) P (0.3 < Z < a ) = 0.0269
d) P (0.5 < Z < a ) = 0.5321
e) P (a < Z < a ) = 0.7062

Solution:
0.3594

a) P ( Z > a ) = 0.3594
a = 0.36

b) P ( Z < a ) = 0.0985
P ( Z a ) = 0.0985
a = 1.29
a = 1.29

0.0985

0.0985

-a

c) P (0.3 < Z < a ) = 0.0269


less than half
P ( Z a ) P ( Z 0.3) = 0.0269
P ( Z a ) 0.3821 = 0.0269
P ( Z a ) = 0.0269 + 0.3821
P ( Z a ) = 0.409
a = 0.23

Therefore, a = 0.23
0.0269

0.0269

-0.3

-a

0.3

d) P (0.5 < Z < a ) = 0.5321


1 P ( Z a ) P ( Z 0.5) = 0.5321
more than half

1 P ( Z a ) 0.3085 = 0.5321
P ( Z a ) = 1 0.3085 0.5321
P ( Z a ) = 0.1594
a =1

=
-0.5

+
a

0.5

e) P ( a < Z < a ) = 0.7062


1 2 P ( Z a ) = 0.7062
1 0.7062
P( Z a) =
2
P ( Z a ) = 0.1469
Therefore, a = 1.05 and a = 1.05

0.7062

-a

Calculating the probabilities of a Normal


Random Variable

Example 5
1. Let X ~ N (25,36). Find the following probabilities
a) P ( X > 28)
b) P ( X < 30)
c) P (23 < X < 27)
d) P ( X 25 < 12)
2. If X ~ N (50,9), find the value of k if P ( X > k ) = 0.2546

Solution:
X
Z=

X ~ N (25,36)
X 25
=
~ N (0,1)
6

X 25 28 25
a) P ( X > 28) = P
>

6
6
X 25
= P
> 0.5
6

0.3085

= P(Z > 0.5)


= 0.3085

0.5

Solution:
X
Z=

X ~ N (25,36)
X 25
=
~ N (0,1)
6

X 25 30 25
b) P ( X < 30) = P
<

6
6
X 25

= P
< 0.8333
6

= P(Z < 0.8333)


= 1 P(Z > 0.8333)
= 1 0.2033

= 0.7967

0.83

Solution:
X
Z=

X ~ N (25,36)
X 25
=
~ N (0,1)
6

23 25 X 25 27 25
c) P (23 < X < 27) = P
<
<

6
6
6

= P( 0.33 < Z < 0.33)


= 1 2 P(Z > 0.33)
= 1 2(0.3707)
= 0.2586

-0.33

0.33

Solution:
X
Z=

X ~ N (25,36)
X 25
=
~ N (0,1)
6

d) P ( X 25 < 12) = P (12 < X 25 < 12)


= P (13 < X 25 < 37)
13 25 X 25 37 25
= P
<
<

6
6
6
= P( 2 < Z < 2 )
= 1 2 P(Z > 2 )
= 1 2(0.0228)
= 0.9544

-2

X ~ N (50,9)

Solution:
X
Z=

X 50
=
~ N (0,1)
3

2. P ( X > k ) = 0.2546
X 50 k 50

P
>
= 0.2546
3
3
k 50

P Z >
= 0.2546
3

k 50

Let Q
= 0.2546
3
From tables, Q(0.66) = 0.2546
k 50
Then
= 0.66
3
k = 51.98

0.2546

0.66

Das könnte Ihnen auch gefallen