Continuous Distributions

A continuous distribution is often represented by a curve, and the

area under the curve represents probability. Some examples:

f(x)

Uniform f(x)

Normal
x

Exponential

x
Normal Distribution

Characteristics
 Continuous random variable distribution.
 Mean µ and Standard deviation σ.
 Symmetrical or Bell- shaped distribution.
 Mean, Median and Mode are equal.
 Area under the Normal Curve is one.
 X~ N (µ , σ ): Mean = µ; Standard Deviation = σ
𝟏 𝟏 𝒙−𝜇 𝟐
−𝟐 𝝈
𝒇 𝑿 = 𝒆 ; −∞ < 𝑋 < ∞
𝟐𝝅 𝝈
From Normal to Standard Normal
𝑋− 𝜇
Z= ; Z = Standard Normal Random Variable
𝜎

2
Normal Distribution

P(X) > 0
𝑃 𝑋 =1

-∞ 𝝻= 𝑀𝑑 = 𝑀𝑜 +∞

-∞ < X < ∞

3
Standard Normal Distribution

Characteristics
 Continuous random variable distribution
 Mean 0 and Standard deviation 1.
 Symmetrical or Bell- shaped distribution.
 Mean, Median and Mode are equal.
 Area under the Standard Normal Curve is one.
 Z~ S.D.N (0 , 1 ): Mean = 0; Standard Deviation = 1
𝟏 𝟏
−𝟐 𝒁 𝟐
𝒇 𝒁 = 𝒆 ; −∞ < 𝑍 < ∞
𝟐𝝅
Mean of the Sample Mean = 𝛍𝐱
𝛔
Standard Deviation of the Sample Mean or Standard Error =
𝐧
𝛔
𝒙 ~ N (𝛍𝐱 , )
𝐧

4
Standard Normal Distribution

P(Z > 0) = 0.5

P(Z > 0) = P(Z< 0) = 0.5
P(Z < 0)= 0.5 P(Z > 0) + P(Z< 0) = 0.5+ 0.5 =1

P(Z< -3)
P(Z>3)= P(Z < -3)

-∞ …… − 4 − 3 − 2 − 1 𝝻=0 1 2 3 4………… +∞

P(-1 < Z < 0) P(0< Z< 1)

-∞< Z< ∞

5
Symmetry
 Because the normal distribution is symmetric, the right and left
tails have the same area:

Z 𝑎 −𝑎 Z

𝑃 𝑍 > 𝑎 = 𝑃 𝑍 < −𝑎
Complement

 The two sides of the distribution must have areas that total 1:

-a 𝑎

𝑃 𝑍 > 𝑎 = 1 − 𝑃 𝑍 < −𝑎
Two Bounds

 We can simplify the probability that 𝑍 is between two numbers

using a difference:

𝑎 𝑏
𝑎 𝑏

𝑃 𝑎<𝑍<𝑏 =
𝑃 𝑍 <𝑏 −𝑃 𝑍 <𝑎
𝑎 𝑏
Two Bounds - Alternative

 …or we can think of it as the complement of two tails:

𝑎 𝑏
𝑎 𝑏

𝑃 𝑎<𝑍<𝑏 =
1−𝑃 𝑍 <𝑎 −𝑃 𝑍 >𝑏
𝑎 𝑏
10
Example 4.5 (Pg- 4- 9)

X~ N (µ , σ ) Mean = µ = 3
Standard Deviation = σ = 0.5
𝑋−𝜇 4−𝜇 4−3
P(X < 4) = P( < ) = P(Z< ) = P(Z < 2) = 1- P(Z > 2)
𝜎 𝜎 0.5
= 1- P(Z < -2), (⸪Symmetric)
P(Z<2)
P(Z> 2) = 1- 0.0228= 0.9772

-3 -2 -1 0 1 2 3
Z 0.00 0.01 0.02
Z 0.0 0.5 0.4960 0.4920
P(Z<-2)
-0.01 0.4602 0.4562 0.4552
……. ……. …….. ……
-2.0 0.0228 0.0222 0.0217

11
Example 4.6 (Pg- 4- 10)
X~ N (µ , σ )
Mean = µ = 25
Standard Deviation = σ = 4
(a) P(between X= 25 and X= 32)= P(25<X < 32)
25−𝜇 𝑋−𝜇 32−𝜇 25−25 32−25
= P( < < ) = P( <Z< )
𝜎 𝜎 𝜎 4 4
P(0<Z<1.75) = P(0< Z <1.75)
P(Z< -1.75) =(0.5- P(Z > 1.75))
P(Z>1.75)
= 0.5- P(Z < -1.75), (⸪Symmetric)
= 0.5- 0.0401= 0.4599
-3 -2 -1 0 1 2 3

12
Example 4.6 (Pg- 4- 10)
X~ N (µ , σ )
Mean = µ = 25
Standard Deviation = σ = 4
(b) P(between X= 18 and X= 34)= P(18<X < 34)
18−𝜇 𝑋−𝜇 34−𝜇 18−25 34−25
= P( < < ) = P( <Z< )
𝜎 𝜎 𝜎 4 4
P(-1.75<Z<2.25) = P(-1.75< Z < 2.25)
P(Z<-1.75) =(1- (P(Z < - 1.75)+ P(Z > 2.25))
P(Z>2.25)
=(1- (P(Z < - 1.75)+ P(Z < - 2.25))
(⸪Symmetric)
-3 -2 -1 0 1 2 3
= 1- (0.0401+0.0122)
Z = 0.9477

13
Example 4.7 (Pg- 4- 11)
Let, X = Number of assembly time
X~ N (µ , σ )
Mean = µ = 55 minutes
Standard Deviation = σ = 4 minutes
P(assembly time which will finish the job before the company closes
for the day)= P(the assembly time is less than or equal 60 minutes)
P(0< Z <1.25) 𝑋−𝜇 60− 𝜇
= P(X ≤ 60) = P( ≤ )
P(Z< -1.25) 𝜎 𝜎
P(Z>1.25) 60−55
= P(Z ≤ ) = P(Z ≤ 1.25)
4
= 1- P(Z > 1.25)
-3 -2 -1 0 1 2 3
= 1- P(Z< - 1.25) = 1- 0.1056
Z
= 0.8944
Exercises: Pg-4-13; No.8(a, b, c), 11(a, c), 12(a, c)
14
Exercise 9(a); (Pg- 4- 13)
Let, X = Monthly salary
X~ N (µ , σ )
Mean = µ = $2500
Standard Deviation = σ = $150
𝑋−𝜇 2600− 𝜇
P(salary is more than $2,600)= P(X > 2600) = P( > )
𝜎 𝜎
P(Z<-0.67) P(Z>0.67) 2600−2500
= P(Z > ) = P(Z > 0.67)
150

= P(Z< - 0.67)
Z = 0.2514
…… (-0.67) … 0 ...(0.67)….

Exercise 9(b); (Pg- 4- 13)-----?

( more than) = (or more)

15
Exercise (Pg: 5-4; No. 1); (Chapter 5)
Let, X =Annual Bonus
X~ N (µ , σ )
Mean = µ = $800
Standard Deviation = σ = $120
n= 15
𝜎
𝑥 ~N 𝛍𝐱 ,
𝑛
Mean = 𝛍𝐱 = 𝜇 = $800
𝜎 120
Standard Deviation = = = $ 30.98
𝑛 15

16
Exercise (Pg: 5-4; No. 2)
Let, X =Weight of each chocolate bar
X~ N (µ , σ )
Mean = µ = 32.2 gram
Standard Deviation = σ = 0.3 gram
(a) P(Weight of each chocolate bar will weigh less than 32 gran)
𝑋−𝜇 32− 𝜇 32−32.2
= P(X < 32) = P( < ) = P(Z < )
𝜎 𝜎 0.3

P(-0.67)
= P(Z < -0.67)
= 0.2514

-0.67 0
Z

Exercise: (b); skip

17
Example (1)
Selected sample of customers 75 comes from non- normal
distribution with population mean of 25 and population of standard
deviation of 5 . Find the given below:
(i) Mean of the given sample
(ii) Standard deviation of the given sample.

𝜎
n= 75 (n> 25); large sample 𝑥 ~N 𝛍𝐱 ,
𝑛
Mean = 𝛍𝐱 = 𝜇 = 25
𝜎 5
Standard Deviation = = = 0.5774
𝑛 75

18
Mean and Standard Deviation of Sample Mean which
comes from Normal Distribution
Random Variable X follows Normal Distribution with Mean µ
an Standard Deviation σ;
 X~ N (µ , σ )

Mean of the Sample Random Variable X follows Normal

𝛔
Distribution with Mean 𝛍𝐱 and Standard Deviation ;
𝐧
𝛔
 𝒙 ~ N (𝛍𝐱 , )
𝐧

Exercise (Pg: 5-4; No. 2)

19
Estimation (Chapter 6)

 Point Estimation
 Interval Estimation

Point Estimation: A parameter is estimated by a statistic.

To estimate
Using A Statistic A Parameter

Interval Estimation: A parameter is estimated between two stated

limits with statistic.

To estimate
Using Confidence Limits A Parameter
20
Estimation (Continued.)
Parameter: Characteristics of a population
Statistic: Characteristics of a sample

Sample Statistic or Population Parameter

Statistic or Parameter
Mean 𝒙 µ

Standard Deviation s σ

Correlation Coefficient r 𝞺

Proportion p 𝛑

21
Example
 A researcher conducts a survey of 50 households and the average
interview time per household is 52 minutes and standard deviation
of interview time is 11.31 minutes. Suppose that the interview
times are normally distributed and find the point estimate mean of
interview time.
Point estimate mean interview time = 𝒙 = 52 minutes.
Exercise
According to a survey, the mean annual salary of 100 managers at
major companies is $80, 720 and standard deviation is $11, 200.
Suppose that the annual salary is normally distributed and determine
the point estimate of average salary.

22
Estimation (Continued.)
Confidence Interval: A parameter is estimated between two stated
limits with statistics at confidence level (1- α)
100%.
(1- α) 100% = 99%, 95%, 90% etc.

Confidence Limits of Statistic at (1- α) 100% Confidence Level

Lower Confidence Limit < A Parameter < Upper Confidence Limit
(minimum statistic) (maximum statistic)
Lower Confidence Limit = A Statistic – {Reliability Factor ×
Standard Error}
Upper Confidence Limit = A Statistic + {Reliability Factor ×
Standard Error}

23
Estimation (Continued.)
Where;
Reliability Factor × Standard Error = Error or within value of a
Parameter and statistic
Reliability Factor = Z α/2
α = Significance Level
(1- α) 100% = Confidence Level = 90%, 95%, 99%, etc.
α (1- α) 100% Z α/2

1% = 0.01 99% 2.575 (𝑍∝ = 𝑍0.005 )

2

5%= 0.05 95% 1.960 (𝑍∝ = 𝑍0.025 )

2

10%= 0.1 90% 1.645 (𝑍∝ = 𝑍0.05 )

2

24
Estimation (Continued.)
Confidence Limits for a Population Mean at (1- α) 100%
Confidence Level
Lower Confidence Limit < µ < Upper Confidence Limit

𝝈
Lower Confidence Limit = 𝒙 − 𝒁∝ ×
𝟐 𝒏

𝝈
Upper Confidence Limit = 𝒙 + 𝒁 × ∝
𝟐 𝒏

Note: If n is large (n >25); σ is unknown, σ = s

Where;
µ = Population Mean
n= sample size
25
Estimation (Continued.)
σ = Population Standard Deviation
s = Sample Standard Deviation
𝒙 = Sample Mean
𝒁∝ = Reliability Factor
𝟐
𝝈
= Standard Error of the Mean
𝒏
𝝈
𝒁∝ × = Error or within value= E (Margin of Error)
𝟐 𝒏
Finding Sample Size for estimation of Population Mean:
𝒁𝟐∝ 𝝈𝟐
𝟐
n=
𝑬𝟐
Note: If n ≥ 30 and σ is unknown; σ = s.
26
Example(Pg: 6-3)
n = 36 (n >25)
𝒙 = $ 48.4
σ = s = $ 4.5

Confidence Level = (1- 𝝰 )100% = 90%

∴ 1- 𝝰 = 0.9
∴ 𝝰 = 1- 0.9 =0.1
∝ 0.1
= = 0.05
2 2
𝑍∝ = 𝑍0.05 = 1.645
2

27
Example (Pg: 6-3); (Continued.)
𝝈
Lower Confidence Limit = 𝒙 − 𝒁 × ∝
𝟐 𝒏
𝟒.𝟓
= 48.4 - 1.645 × = $ 47.17
𝟑𝟔

𝝈
Upper Confidence Limit = 𝒙 + 𝒁∝ ×
𝟐 𝒏
𝟒.𝟓
= 48.4 + 1.645 × = $ 49.63
𝟑𝟔

90% confidence interval for population mean is between

$ 47.16 and $ 49.64.

28
Exercise (Pg: 6-5, NO.2)
(a.) n = 34 (n >25)
𝒙 = 88
σ = s =6.3
Confidence Level = (1- 𝝰 )100% = 99%
∴ 1- 𝝰 = 0.99
∴ 𝝰 = 1- 0.99 =0.01
∝ 0.01
= = 0.005
2 2
𝑍∝ = 𝑍0.005 =2.575
2

29
Example (Pg: 6-3); (Continued.)
𝝈
Lower Confidence Limit = 𝒙 − 𝒁 × ∝
𝟐 𝒏
𝟔.𝟑
= 88- 2.575 × = 85. 22
𝟑𝟒
𝝈
Upper Confidence Limit = 𝒙 + 𝒁 × ∝
𝟐 𝒏
𝟔.𝟑
= 88+ 2.575 × = 90.78
𝟑𝟒

99% confidence interval for population mean (𝝻) is between

85. 22 and 90.78.
(b.) n= 100, ?

30
Exercise (Pg: 6-5, NO.3)
(a.) n = 100 (n >25)
𝒙 = $80,720
σ = s =$11, 200
Confidence Level = (1- 𝝰 )100% = 95%
∴ 1- 𝝰 = 0.95
∴ 𝝰 = 1- 0.95 =0.05
∝ 0.05
= = 0.025
2 2
𝑍∝ = 𝑍0.025 =1.96
2

31
Example (Pg: 6-3); (Continued.)
𝝈
Lower Confidence Limit = 𝒙 − 𝒁 × ∝
𝟐 𝒏
11,200
= 80, 720 - 1.96 × = $ 78524.8
100
𝝈
Upper Confidence Limit = 𝒙 + 𝒁 × ∝
𝟐 𝒏
11,200
= 80, 720 + 1.96 × = $ 82915.2
100
99% confidence interval for population mean (𝝻) is between $
78524.8 and $ 82915.2.
(b.) n= 200 females ?

Exercises: Pg- (6-5); (No. 3, (a), (b))

32
Hypothesis Testing

Hypothesis: A statistical hypothesis is a statement which may or

may not be true about the value of one or more
population parameters.
Null Hypothesis: H0: A tentative assumption made about the value
of population parameters. It includes a
statement of equality.(at least, at most, not
more than, not less than, etc..)
Alternative Hypothesis: H1: will accept that if the sample data
provide us with evidence that the H0:
is false.
Hypothesis Testing: A procedure based on sample data and
probability theory used to determine whether
the H0: is a reasonable statement and should
not be rejected, or is unreasonable and should
be rejected.
33
Two Types of Error
α = significance level = probability of occurring type I error

Type I Error = α= P( H0 : is rejected/ H0: is true)

Type II Error = β = P( H0 : is accepted/ H0: is false)

Actual Situation
Decision 𝑯𝟎 : is True 𝑯𝟎 : is False

Do not reject 𝑯𝟎 : Correct Decision Type II Error or β

Reject 𝑯𝟎 : Type I Error or α Correct Decision

34
Hypothesis Testing (Continued.)

Hypothesis Testing for Parameter (Parametric Testing)

One – Tailed Test (One-sided Test): investigates whether a sample

value is significantly greater than (or less than) an
assumed population value at a given level of
significance. The test uses an area in one tail of
normal curve.

Two- Tailed Test (Two- sided Test): investigates whether a sample

value is significantly differently from an assumed
population value and so uses areas in both tails of the
normal curve.

35
Hypothesis Testing (Continued.)
Hypothesis Testing for One Population Mean (𝝁)
Steps Two- Tailed Test One-Tailed Test
Right- Tailed Test Left- Tailed Test
1. Hypotheses
Null Hypothesis H0: µ=µ0 µ ≤ µ0 µ ≥ µ0
Alternative Hypothesis H1: µ≠µ0 µ > µ0 µ < µ0
Where: µ0= Hypothesized Population Mean
2. Test Statistic
Note: If n> 25 and σ is
𝑿−𝝁𝟎 unknown, σ = s
Z= 𝝈
𝒏
Where;
𝑿= sample mean
σ= Population Standard Deviation
n= sample size

3. Critical Value: K= ±𝑍𝛼 K = Zα K = - Zα

2

4. Decision Rule: 𝑍 ≥ 𝐾; 𝑅𝑒𝑗𝑒𝑐𝑡 𝐻0 𝑍 ≥ 𝐾; 𝑅𝑒𝑗𝑒𝑐𝑡 𝐻0 𝑍 ≤ 𝐾; 𝑅𝑒𝑗𝑒𝑐𝑡 𝐻0

Otherwise Accept 𝐻0 Otherwise Accept 𝐻0 Otherwise Accept 𝐻0
5. Decision
6. Conclusion
36
Sign for the Hypotheses
Two-tailed One- Tailed Test
Test
Left- tailed test Right- tailed
Test
Sign for the = ≥ ≤
Null
Hypothesis
(𝑯𝟎 : )
Sign for the ≠ < >
Alternative ∝
∝ ∝
Hypotheses 2
2 ∝
(𝑯𝟏 : )
Rejection
Region In both tails Left Right
37
Critical Value (K)
Two-tailed One- Tailed Test
Test
Significance K = ±𝒁𝜶 Left- tailed test Right- tailed Test
Level ∝ 𝟐
K =−𝐙∝ 𝐊 = +𝐙∝
1% = 0.01 ±𝟐. 𝟓𝟕𝟓 -2.33 +2.33

5% = 0.05 ±𝟏. 𝟗𝟔 -1.645 1.645

10%= 0.1 ±𝟏. 𝟔𝟒𝟓 Reject 𝑯𝟎 : -1.28 +1.28

(Rejection Reject 𝑯𝟎 :
Region) (Rejection
Reject 𝑯𝟎 : Region)
(Rejection
Region)
−𝑍𝛼 +𝑍𝛼 −𝑍𝛼
2 2 +𝑍𝛼
38
Decision Rule
One- Tailed Test
Two-tailed Test
Left- tailed test Right- tailed Test
𝒁 ≥ 𝐊 ; 𝐑𝐞𝐣𝐞𝐜𝐭 𝑯𝟎 : Z ≤ 𝐊 ; 𝐑𝐞𝐣𝐞𝐜𝐭 𝑯𝟎 : Z ≥ 𝐊 ; 𝐑𝐞𝐣𝐞𝐜𝐭 𝑯𝟎 :
Otherwise Accept 𝑯𝟎 : Otherwise Accept 𝑯𝟎 : Otherwise Accept 𝑯𝟎 :
( 𝒁 < 𝐊) (Z > K) (𝐙 < 𝐊 )
∝
;
Rejection
2 ∝;
∝ Area
;
Rejection Rejection
2 ∝; Rejection
Area Area Area

K = -𝑍𝛼 K=+𝑍𝛼 𝐾 = −𝑍∝ 𝐾 = +𝑍∝

2 2

39
Example
The expected diameter of a batch of cables is 2 cm. A quality control
inspector takes a sample of 64 cables and find that the sample has a
mean diameter of 1.94 cm and standard deviation of 0.4 cm. Test
whether the manufacturing process is now producing cables with a
diameter is the same or not 2 cm at 1%level of significance.
Hypotheses
Null Hypothesis: The mean diameter is same as the previous
diameter.
𝐻0 : 𝜇 = 2 cm
Alternative Hypothesis: The mean diameter is not same as the
previous diameter.
𝐻1 : 𝜇 ≠ 2 cm

Mean = Expectation of X= E(X)= 𝜇, Variance of X=V(X)= 𝝈𝟐

40
Example (Continued.)
Test Statistic
n = 64 (n > 25)
𝒙 = 1.94 cm
𝝁𝟎 = 2 cm
𝝈 = s = 0.4 cm
𝑿−𝝁𝟎 1.94 −𝟐
Z= 𝝈 = 𝟎.𝟒 = -1.2
𝒏 𝟔𝟒

Critical Value
𝐾 = 𝑍𝛼 ; (∝) = 0.01
2

𝐾 = 𝑍0.01 = 𝑍0.005 = 2.57

2

41
Example (Continued.)
Decision Rule
𝑍 ≥ 𝐾; Reject H0
Otherwise Accept 𝐻0
( 𝑍 <K)
Decision
Z = -1.2
𝑍 = 1.2
K = 𝑍0.01 = 𝑍0.005 = 2.57
2
1.2 < 2.57
∴ 𝑍 <K; Accept H0
Conclusion
H0 : The mean diameter is 2 cm.
𝐻0 : 𝜇 ≠ 2 cm
Exercise: Pg- No. 1.

42
Example
The mean balance of checking accounts at a bank on December 2019
was $850. A random sample of 50 checking accounts taken recently
from the bank gave a mean balance of $775 with a standard
deviation of $230. Assume that the balances of all checking accounts
at this bank are normally distributed. Using the 5% level of
significance, can you conclude that the mean balance is $850 ?
Hypotheses
Null Hypothesis: The mean balance of 2019, December was $850.
𝐻0 : 𝜇 = $850

Alternative Hypothesis: The mean balance of 2019 was not $850.

𝐻1 : 𝜇 ≠ $850

43
Example (Continued.)
Test Statistic
n = 50 (n > 25)
𝒙 = $775
𝝁𝟎 = $850
𝝈 = s = $230
𝑿−𝝁𝟎 775 −850
Z= 𝝈 = 230 = -2.31
𝒏
𝟓𝟎
Critical Value
𝐾 = 𝑍𝛼 ; (∝) = 0.05
2

𝐾 = 𝑍0.05 = 𝑍0.025 = 1.96

2

44
Example (Continued.)
Decision Rule
𝑍 ≥ 𝐾 ; Reject H0
Otherwise Accept 𝐻0
( 𝑍 <K)
Decision
𝑍 = 2.31
K= 𝑍0.05 = 𝑍0.025 = 1.96
2

2.31 > 1.96

∴ 𝑍 > K; Reject H0 ; Accept H1
Conclusion
H0 : The mean balance is not $850.
𝐻1 : 𝜇 ≠ $850
45