Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 224

Statistics for Management II

By: Nejat A.
Objectives

 To familiarize students about the use and application of


various statistical tools in the field of managerial decision
making.
 To enable students make valid inference from data.
 To enable students to construct and test different types of
hypothesis.
 To enable students to find correlation between variables.
 How to apply the statistical tests in the preparation of
research report.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 2


artment (HU)
…Objectives

 The application of statistics in every areas of activities in


business and industry such as production, financial analysis,
distribution, market research, manpower planning.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 3


artment (HU)
Contents

 Chapter 1 - Sampling and Sampling Distributions

 Chapter 2 - Statistical Estimations

 Chapter 3 - Hypothesis Testing

 Chapter 4 - Chi-Square Distributions

 Chapter 5 - Analysis Of Variance

 Chapter 6 - Regression and Correlation

05/05/2024 By: Nejat A. - Lecturer of Management Dep 4


artment (HU)
Chapter One

Sampling and Sampling


Distribution
Sampling

 Population - the collection of all the elements of interest.


 Sampling - a process used in statistical analysis in which a
predetermined number of observations are taken from a
larger population.
 It is selecting sampler (or part of the items) from populations.
 Sampled population - population from which sample drawn.
 Frame - list of elements that sample selected from.
 Parameter - characteristics of a population.
 Statistic - numerical characteristics of a sample.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 6


artment (HU)
Why Sampling?

 If the population is very large

 When quick results required

 To avoid destruction

 Cost consideration

 Sometimes samples are important for accuracy

05/05/2024 By: Nejat A. - Lecturer of Management Dep 7


artment (HU)
Sampling and Non-sampling Errors

 Sampling Error: a statistical error to which an analyst exposes


a model simply because he or she is working with sample
data rather than population or census data.
 Non-Sampling Error: A statistical error caused by human
error to which a specific statistical analysis is exposed.
 These errors can include data entry errors, biased questions
in a questionnaire, biased processing/decision making,
inappropriate analysis conclusions and false information
provided by respondents.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 8


artment (HU)
Types of Sampling

 Probability Sampling: is sampling when all items (i.e., each


element) in the population have a chance of being chosen in
the sample.
 Non-probability sampling: is a sampling methodology where
personal knowledge and opinion play major role in
identifying which elements of the population are to be
included in the sample.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 9


artment (HU)
Probability Sampling

 Simple Random Sampling

 Systematic Sampling

 Stratified Sampling

 Cluster Sampling

05/05/2024 By: Nejat A. - Lecturer of Management Dep 10


artment (HU)
Simple Random Sampling

 It is selecting samples so that each element in the population


has an equal chance or the same probability of being
included in the sample.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 11


artment (HU)
Systematic Sampling

 It is a type of probability sampling method in which sample


members from a larger population are selected according to a
random starting point but with a fixed, periodic interval. This
interval, called the sampling interval (K), is calculated by
dividing the population size by the desired sample size.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 12


artment (HU)
…Systematic Sampling

 It is a type of probability sampling method in which sample


members from a larger population are selected according to a
random starting point but with a fixed, periodic interval. This
interval, called the sampling interval (K), is calculated by
dividing the population size by the desired sample size.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 13


artment (HU)
Stratified Sampling

 It is a sampling in which the population is divided in to strata


and random sample is taken from the elements in each
stratum.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 14


artment (HU)
Cluster Sampling

 It is a sampling method in which the entire population of the


study is divided into externally, homogeneous but internally,
heterogeneous groups called clusters.
 After identifying the clusters, certain clusters are chosen
using simple random sampling while the others remain
unrepresented in a study.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 15


artment (HU)
…Cluster Sampling

 It is a sampling method in which the entire population of the


study is divided into externally, homogeneous but internally,
heterogeneous groups called clusters.
 After identifying the clusters, certain clusters are chosen
using simple random sampling while the others remain
unrepresented in a study.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 16


artment (HU)
Non-probability Sampling

 Convenience/Incidental Sampling

 Quota Sampling

 Judgmental/ Purposive Sampling

 Snowball Sampling

05/05/2024 By: Nejat A. - Lecturer of Management Dep 17


artment (HU)
Convenience Sampling

 It is where the researcher includes people who are easy to


reach.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 18


artment (HU)
Quota Sampling

 It is a method where a researcher selects a sample group to


represent some specific characteristics of the population.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 19


artment (HU)
Purposive Sampling

 It is a form of non-probability sampling in which researchers


rely on their own judgment when choosing members of the
population to participate in their surveys.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 20


artment (HU)
Snowball Sampling

 It is a recruitment technique in which research participants


are asked to assist researchers in identifying other potential
subjects.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 21


artment (HU)
Sampling Distribution

 Types of Distribution:
 Frequency Distribution
 Normal (Gaussian) Distribution
 Probability Distribution
 Poisson Distribution
 Binomial Distribution
 Sampling Distribution
 t distribution
 F distribution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 22


artment (HU)
What is Sampling Distribution?

 Sampling is defined as the process of selecting a number of


observations (subjects) from all the observations (subjects)
from a particular group or population.
 Sampling distribution is defined as the frequency distribution
of the statistic for many samples.
 It is the distribution of means and is also called the sampling
distribution of the mean.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 23


artment (HU)
Features of Sampling Distribution

 The 4 features of sampling distribution include:


 The statistic of interest (Proportion, SD, or Mean)
 Random selection of sample
 Size of the random sample (very important)
 The characteristics of the population being sampled.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 24


artment (HU)
…Features of Sampling Distribution

 Central Limit Theorem


 When random samples of size is taken from a population,
the distribution of sample means will approach the normal
distribution.
 When the Sampling distribution of the mean has sample
sizes of 30 or more then it is said to be normally
distributed.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 25


artment (HU)
…Features of Sampling Distribution

 Z Score (Standard Score)

Where, is the sample mean


μ is the mean of the sampling distribution
is the SE of the sampling distribution
n is sample size

05/05/2024 By: Nejat A. - Lecturer of Management Dep 26


artment (HU)
Sampling Distribution of

 Sampling distribution of the :- is the probability distribution


of the sample mean.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 27


artment (HU)
Illustration 1

 Suppose that a population has five elements (N = 5) 3, 6, 9,


12 and 15. If we draw samples of 3 (n = 3).

 Formulate sampling distribution of

 Estimate population mean

 Estimate mean of the distribution

 Compute the standard deviation

05/05/2024 By: Nejat A. - Lecturer of Management Dep 28


artment (HU)
Solution

 Nʗn = 5ʗ3 = 10

 List down all possible samples

3,6,9 3,12,15
3,6,12 6,9,12
3,6,15 6,9,15
3,9,12 6,12,15
3,9,15 9,12,15

05/05/2024 By: Nejat A. - Lecturer of Management Dep 29


artment (HU)
…Solution

Sample Mean ()
3,6,9 6
3,6,12 7
3,6,15 8
3,9,12 8
3,9,15 9
3,12,15 10
6,9,12 9
6,9,15 10
6,12,15 11
9,12,15 12
90

05/05/2024 By: Nejat A. - Lecturer of Management Dep 30


artment (HU)
…Solution

Sample Mean () Probability P()


6 0.1
7 0.1
8 0.2
9 0.2
10 0.2
11 0.1
12 0.1

05/05/2024 By: Nejat A. - Lecturer of Management Dep 31


artment (HU)
…Solution

 Population Mean ()

 Mean of Sampling Distribution ()

05/05/2024 By: Nejat A. - Lecturer of Management Dep 32


artment (HU)
…Solution

 Standard Deviation of Sampling Distribution ()

05/05/2024 By: Nejat A. - Lecturer of Management Dep 33


artment (HU)
Illustration 2

 The average life time of a light bulb is 3000 hours with a


standard deviation of 696 hours. A sample of 36 bulbs is
taken.
a) What are the expected value and standard deviation of
sampling distribution of ?
b) What is the probability that the average life time in the
sample will be between 2670.56 and 2809.76 hours?
c) What is the probability that the average life time in the
sample will be equal to or greater than 3219.24 hours?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 34


artment (HU)
…Illustration 2

d) What is the probability that the average life time in the


sample will be equal to or less than 3180.96 hours?
e) How large of a sample needs to be taken to provide a
0.01 probability that the average life time in the
sample will be equal to or greater than 3219.24 hours?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 35


artment (HU)
Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 36


artment (HU)
…Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 37


artment (HU)
…Solution

e)
2.33

n=54.71=55

05/05/2024 By: Nejat A. - Lecturer of Management Dep 38


artment (HU)
Sampling Distribution of ()

05/05/2024 By: Nejat A. - Lecturer of Management Dep 39


artment (HU)
Illustration

 In the study of annual family expenditures for general health


care, two populations were surveyed with the following
results:
 Population 1: = 40, = $346
 Population 2: = 35, = $300
 If the variance of the populations = 2800 and = 3250, what is
the probability of obtaining sample results () as large as
those shown, if there is no difference in the means of the
two populations?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 40


artment (HU)
Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 41


artment (HU)
Sampling Distribution of

 Sampling distribution of the :- is the probability distribution


of the sample proportion.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 42


artment (HU)
Illustration 1

 Consider a population of N = 5 given numbers 3, 6, 9, 12, &


15.

 Let’s take even numbers, the proportion of even numbers is


2/5 = 0.4. Consider a samples of size 3 (n = 3).

Formulate sampling distribution of

05/05/2024 By: Nejat A. - Lecturer of Management Dep 43


artment (HU)
Solution

 Nʗn = 5ʗ3 = 10

 List down all possible samples

3,6,9 3,12,15
3,6,12 6,9,12
3,6,15 6,9,15
3,9,12 6,12,15
3,9,15 9,12,15

05/05/2024 By: Nejat A. - Lecturer of Management Dep 44


artment (HU)
…Solution

Sample Proportion()
3,6,9
3,6,12
3,6,15
3,9,12
3,9,15
3,12,15
6,9,12
6,9,15
6,12,15
9,12,15

05/05/2024 By: Nejat A. - Lecturer of Management Dep 45


artment (HU)
…Solution

Sample Probability P()


Proportion()
0.1
0.6
0.3

05/05/2024 By: Nejat A. - Lecturer of Management Dep 46


artment (HU)
Illustration 2

 A new soft drink is being market tested. It is estimated that


60% of consumers will like the new drink. A sample of 96
taste-tested the new drink.
a) Determine the standard error of the proportion
b) What is the probability that equal to or more than 70.4%
of consumers will indicate they like the drink?
c) What is the probability that equal to or more than 30% of
consumers will indicate they do not like the drink?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 47


artment (HU)
Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 48


artment (HU)
Sampling Distribution of ()

05/05/2024 By: Nejat A. - Lecturer of Management Dep 49


artment (HU)
Illustration

 10% of machines produced by Company A are defective and


5% of those produced by Company B are defective. A random
sample of 250 machines is taken from Company A and a
random sample of 300 machines is taken from Company B.
 What is the probability that the difference in sample
proportion is less than or equal to 0.02?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 50


artment (HU)
Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 51


artment (HU)
End of Chapter One
Chapter Two

Statistical Estimation
Statistical Inference

 Statistical Inference is the procedure where inference about


a population is made on the basis of the results obtained
from a sample drawn from that population.
 This can be achieved by:
 Estimation
 Hypothesis testing

05/05/2024 By: Nejat A. - Lecturer of Management Dep 54


artment (HU)
Estimation

 It is a procedure where inference about the population is


made on the basis of the result obtained a sample drown
from that population.
 The objective of estimation is to determine the approximate
of a population parameter on the basis of a sample statistic.
 E.g. the sample mean () is employed to estimate the
population mean (μ).

05/05/2024 By: Nejat A. - Lecturer of Management Dep 55


artment (HU)
…Estimation

 Estimation - is the process of using statistics as estimates of


parameters. It is any procedure where sample information is
used to estimate/predict the numerical value of some
population parameter.
 Estimator - refers to any sample statistic that is used to
estimate a population parameter. E.g. for μ and for P.
 Estimate - is a specific numerical value of our estimator. E.g.
9, 2, 5.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 56


artment (HU)
Types of Estimation

 There are two types of estimators:

 Point Estimator

 Interval Estimator

05/05/2024 By: Nejat A. - Lecturer of Management Dep 57


artment (HU)
Point Estimation

 It is a single numerical value obtained from a random sample


used to estimate the corresponding population parameter.
 Sample mean () is the best point estimate for population
mean (μ).
 Sample standard déviation (S) is the best point estimate for
population standard déviation (σ).
 Sample proportion () is best point estimate for population
proportion P.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 58


artment (HU)
Interval Estimation

 It consists of two numerical values defining an interval within


which lies the unknown parameter we want to estimate with
a specified degree of confidence (CL).
 The values depend on the confidence level which is equal to
1-α (α is the probability of error)
 The interval estimate may be expressed as:

Estimator ± Reliability coefficient X standard error

05/05/2024 By: Nejat A. - Lecturer of Management Dep 59


artment (HU)
Reliability Coefficient

 The reliability coefficient is the value of corresponding to the


confidence level.

Confidence level α -value Z-value


90% 10% 1.645
95% 5% 1.96
99% 1% 2.58

05/05/2024 By: Nejat A. - Lecturer of Management Dep 60


artment (HU)
Confidence Interval of μ

 The confidence interval for population mean is affected by:

 The population distribution, i.e., whether the population is


normally distributed or not.

 The standard deviation, i.e., whether σ is known or not.

 The sample size, i.e., whether the sample size (n) is large or
not.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 61


artment (HU)
…Confidence Interval of μ

 The confidence interval for population mean is affected by:

 The population distribution, i.e., whether the population is


normally distributed or not.

 The standard deviation, i.e., whether σ is known or not.

 The sample size, i.e., whether the sample size (n) is large or
not.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 62


artment (HU)
Illustration

 The vice president of operations for Ethio Telecom is in the


process of developing a strategic management plan. He
believes that the ability to estimate the length of the average
phone call on the system is important. He takes a random
sample of 60 calls from the company records and finds that
the mean sample length for a call is 4.26 minutes.
 Past history for these types of calls has shown that the
population standard deviation for call length is about 1.1
minutes. Assuming that the population is normally
distributed and he wants to have a 95% confidence, help him
in estimating the population mean.
05/05/2024 By: Nejat A. - Lecturer of Management Dep 63
artment (HU)
Solution

 Given: n = 60 calls
= 4.26 minutes
σ = 1.1 minutes
CL = 0.95
 Step 1: = = = 0.142

 Step 2: α = 1 – CL = 1 – 0.95 = 0.05

= = 0.025

05/05/2024 By: Nejat A. - Lecturer of Management Dep 64


artment (HU)
…Solution

 Step 3: = = 1.96
 Step 4: μ = ( )
= 4.26 1.96 0.142
= 4.26 0.28
3.98 4.54
 Step 5: Conclusion: the vice president of Ethio-Telecom can
be can be 95% confident that the average length of a call for a
population is between 3.98 and 4.54 minutes.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 65


artment (HU)
If σ is Unknown, n Large

μ=( )

=( )

05/05/2024 By: Nejat A. - Lecturer of Management Dep 66


artment (HU)
Illustration

 Suppose that a car rental firm in Addis wants to estimate the


average number of miles traveled by each of its cars rented. A
random sample of 110 cars rented reveals that the sample
means travel distance per day is 85.5 miles, with a sample
standard deviation of 19.3 miles. Compute a 99% confidence
interval to estimate.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 67


artment (HU)
Solution

 Given: n = 110 rented cars


= 85.5 miles
S = 19.3 miles
CL = 0.99
 Step 1: = = = 1.84
 Step 2: α = 1 – CL = 1 – 0.99 = 0.01
= = 0.005

05/05/2024 By: Nejat A. - Lecturer of Management Dep 68


artment (HU)
…Solution

 Step 3: = = 2.58
 Step 4: μ = ( )
= 85.5 2.58 1.84
= 85.5 4.747
80.753 90.247
 Step 5: Conclusion: we state with 99% confidence that the
average distance traveled by rented cars lies between 80.753
and 90.247 miles.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 69


artment (HU)
Interval Estimation of P

P=( )

=( )

05/05/2024 By: Nejat A. - Lecturer of Management Dep 70


artment (HU)
Illustration

 Recently, a study of 87 randomly selected companies with


telemarketing operation was completed. The study revealed
that 39% of the sampled companies had used telemarketing
to assist them in order processing. Using this information
estimate the population proportion of telemarketing
companies who use their telemarketing operation to assist
them in order processing taking a 95% confidence level.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 71


artment (HU)
Solution

 Given: n = 87 companies
= 0.39
= 0.61
CL = 0.95
 Step 1: = = = 0.0523
 Step 2: α = 1 – CL = 1 – 0.95 = 0.05
= = 0.025

05/05/2024 By: Nejat A. - Lecturer of Management Dep 72


artment (HU)
…Solution

 Step 3: = = 1.96
 Step 4: P = ( )
= 0.39 1.96 0.0523
= 0.39 0.1025
0.2875 0.4925
 Step 5: Conclusion: we state with 95% confidence that the
proportion of companies which use telemarketing to assist
order processing lies between 0.2875 and 0.4925.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 73


artment (HU)
Interval Estimation of (- )

- = (- )

= (- )

05/05/2024 By: Nejat A. - Lecturer of Management Dep 74


artment (HU)
Illustration

 Greystone Department Stores, Inc., operates two stores in


Buffalo, New York: One is in the inner city and the other is in a
suburban shopping center. The regional manager noticed that
products that sell well in one store do not always sell well in
the other. The manager believes this situation may be
attributable to differences in customer demographics at the
two locations. Customers may differ in age, education,
income, and so on. The manager investigated the data below:

05/05/2024 By: Nejat A. - Lecturer of Management Dep 75


artment (HU)
…Illustration

Inner City Store Suburban Store


Sample Size = 36 = 49
Sample Mean = 40 = 35
Pop. Stand. =9 = 10

 Formulate interval estimation of (- )

05/05/2024 By: Nejat A. - Lecturer of Management Dep 76


artment (HU)
Solution

-=
=
=( )
0.94 ≤ (- ) ≤ 9.06
 Thus, the margin of error is 4.06 and 95% confidence interval
estimate of the difference between the two population
means is 0.94 years and 9.06 years.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 77


artment (HU)
Determining the Sample Size

 Sample size for estimating population mean ()

05/05/2024 By: Nejat A. - Lecturer of Management Dep 78


artment (HU)
Illustration 1

 A gasoline service station shows a standard deviation of Birr


6.25 for the changes made by the credit card customers.
Assume that the station’s management would like to estimate
the population mean gasoline bill for its credit card customers
to be within ± Birr 1.00.
 For a 95% confidence level, how large a sample would be
necessary?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 79


artment (HU)
Solution

 Given: = 1.00, = 6.25 and CL = 95%

= 150.6

151

05/05/2024 By: Nejat A. - Lecturer of Management Dep 80


artment (HU)
Illustration 2

 Ethio Travels and Tours PLC would like to estimate the mean
amount of money spent by a tourist to be within Birr 100
with 95% confidence.
 If the amount of money spent by tourist is considered to be
normally distributed with a standard deviation of Br 200,
what sample size would be necessary for the PLC to meet
their objective in estimating this mean amount?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 81


artment (HU)
Solution

 Given: = 100, = 200 and CL = 95%

= 15.35

16

05/05/2024 By: Nejat A. - Lecturer of Management Dep 82


artment (HU)
Determining the Sample Size

 Sample size for estimating population proportion ()

05/05/2024 By: Nejat A. - Lecturer of Management Dep 83


artment (HU)
Illustration

 Suppose that a production facility purchases a particular


component parts in large lots from a supplier. The production
manager wants to estimate the proportion of defective parts
received from this supplier. She believes that the proportion
of defects is no more than 0.2 and wants to be with in 0.02 of
the true proportion of defects with a 90% level of confidence.
 How large a sample should she take?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 84


artment (HU)
Solution

 Given: = 0.02, = 0.2 and CL = 90%

= 1082.41

1083

05/05/2024 By: Nejat A. - Lecturer of Management Dep 85


artment (HU)
End of Chapter Two
Chapter Three

Hypothesis Testing
Basic Concepts

 A statistical hypothesis is an assumption about a population


parameter. This assumption may or may not be true.
 Hypothesis testing refers to the formal procedures used by
statisticians to accept or reject statistical hypotheses.
 There are two types of statistical hypotheses:
 Null Hypothesis (): the hypothesis that sample
observations result purely from chance.
 Alternative Hypothesis ( or ): the hypothesis that sample
observations are influenced by some non-random causes.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 88


artment (HU)
Steps in Hypothesis Testing

 State the hypotheses - this involves stating the null and


alternative hypotheses. The hypotheses are stated in such a
way that they are mutually exclusive. That is, if one is true,
the other must be false.
 Formulate an analysis plan - the analysis plan describes how
to use sample data to evaluate the null hypothesis. The
evaluation often focuses around a single test statistic.
 Analyze sample data - find the value of the test statistic
(mean score, proportion, z-score, t-score, etc.) described in
the analysis plan.
 Interpret results - apply the decision rule described in the
analysis plan. If the value of the test statistic is unlikely, based
on the null hypothesis, reject the null hypothesis.
05/05/2024 By: Nejat A. - Lecturer of Management Dep 89
artment (HU)
Errors in Hypothesis Testing

 Type I error: occurs when the researcher rejects a null


hypothesis when it is true. The probability of committing a
Type I error is called the significance level. This probability is
also called alpha, and is often denoted by 𝜶.
 Type II error: occurs when the researcher fails to reject a null
hypothesis that is false. The probability of committing a Type
II error is called Beta, and is often denoted by β.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 90


artment (HU)
Decision Rules in Hypothesis

 P-value:

05/05/2024 By: Nejat A. - Lecturer of Management Dep 91


artment (HU)
…Decision Rules in Hypothesis

 Region of acceptance:

05/05/2024 By: Nejat A. - Lecturer of Management Dep 92


artment (HU)
One-Tailed and Two-Tailed Tests

Mathematical Symbols of Type of Test


Left One Tailed Test
Right One Tailed Test
Two Tailed Test

05/05/2024 By: Nejat A. - Lecturer of Management Dep 93


artment (HU)
…One-Tailed and Two-Tailed Tests

05/05/2024 By: Nejat A. - Lecturer of Management Dep 94


artment (HU)
Hypothesis Testing of μ

05/05/2024 By: Nejat A. - Lecturer of Management Dep 95


artment (HU)
Illustration 1

 A packaging device is set to fill detergent powder packets


with a mean weight of 5kg. The standard deviation is known
to be 0.01 kg. These are known to drift upwards over a
period of time due to machine fault, which is not tolerable. A
random sample of 100 packets is taken and weighed.
 This sample has a mean weight of 5.03kg and a standard
deviation of 0.21kg. Can we conclude that the mean weight
produced by the machine has increased? Use a 5% level of
significance.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 96


artment (HU)
Solution

 Given: = 100, = 5.03kg., = 0.21kg. and 𝜶 = 5%

 Step 1: : 𝝁 = 5

:𝝁>5

 Step 2: The appropriate test statistic is -test, because is large


at 100, even though 𝝈 is unknown.

= = = 1.645

05/05/2024 By: Nejat A. - Lecturer of Management Dep 97


artment (HU)
…Solution

 Decision rule: - Accept if

05/05/2024 By: Nejat A. - Lecturer of Management Dep 98


artment (HU)
…Solution

 Step 3: Sample data analysis


= =

=
 Step 4: Decision: since (𝟏.𝟒𝟐𝟖) is less than (𝟏.𝟔𝟒𝟓) accept ,
i.e. the mean weight does not increased.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 99


artment (HU)
Illustration 2

 Suppose the average breaking strength of steel rods is


specified to be 18.5 thousand lbs. For this a sample of 14 rods
was tested. The mean and standard deviation obtained were
17.85 and 1.955 respectively. Test the significance of
deviation through 5% level of significance.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 100


artment (HU)
Solution

 Given: = 14, = 17.85, = 1.955 and 𝜶 = 5%

 Step 1: : 𝝁 18.50

: 𝝁 18.50

 Step 2: The appropriate test statistic is -test, because is small


at 14 and 𝝈 is unknown.

= = = 2.16

05/05/2024 By: Nejat A. - Lecturer of Management Dep 101


artment (HU)
…Solution

 Decision rule: - Accept if is between -2.16 and +2.16

05/05/2024 By: Nejat A. - Lecturer of Management Dep 102


artment (HU)
…Solution

 Step 3: Sample data analysis


= =

=
 Step 4: Decision: since is less than accept , i.e. there is no
significance deviation of sample mean from the population
mean.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 103


artment (HU)
Hypothesis Testing of 𝑷

=
=

05/05/2024 By: Nejat A. - Lecturer of Management Dep 104


artment (HU)
Illustration

 Suppose a manufacturer claims that at least 95% of


equipment which he supplied to a factory conformed to the
specification. An examination of the sample of 200 pieces of
equipment revealed that 18 were faulty. Test the claim of the
manufacturer. α = 5%.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 105


artment (HU)
Solution

 Given: = 200, = 0.91 and 𝜶 = 5%

 Step 1:- : 0.95

: 0.95

 Step 2:- The appropriate test statistic is -test, because is large


at 200.

= = = -1.645

05/05/2024 By: Nejat A. - Lecturer of Management Dep 106


artment (HU)
…Solution

 Decision rule: - Accept if which is 1.645, else reject it.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 107


artment (HU)
…Solution

 Step 3: Sample data analysis


= =
=

=
 Step 4: Decision: since |-2.67| is greater than |-𝟏.𝟔𝟒𝟓| r.
Hence, we conclude that the proportion of equipment
conforming to the specifications is not 95 percent.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 108


artment (HU)
Hypothesis Testing of

05/05/2024 By: Nejat A. - Lecturer of Management Dep 109


artment (HU)
Illustration

 Do employees perform better at work with music playing?


The music was turned on during the working hours of a
business with 45 employees. There productivity level
averaged 5.2 with a standard deviation of 2.4. On a different
day the music was turned off and there were 40 workers. The
workers' productivity level averaged 4.8 with a standard
deviation of 1.2. What can we conclude at the 0.05 level of
significance?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 110


artment (HU)
Solution

 Given: = 45, = 40, = 5.2, = 4.8, = 2.4, = 1.2 and 𝜶 = 5%

 Step 1: :

 Step 2: The appropriate test statistic is -test.

= = = 1.645

05/05/2024 By: Nejat A. - Lecturer of Management Dep 111


artment (HU)
…Solution

 Decision rule: - Accept if

05/05/2024 By: Nejat A. - Lecturer of Management Dep 112


artment (HU)
…Solution

 Step 3: Sample data analysis

= 0.99
 Step 4: Decision: since (0.99) is less than (𝟏.𝟔𝟒𝟓) accept .

05/05/2024 By: Nejat A. - Lecturer of Management Dep 113


artment (HU)
Hypothesis Testing of

05/05/2024 By: Nejat A. - Lecturer of Management Dep 114


artment (HU)
Illustration

 Suppose that a company is considering two different


television advertisements for promotion of a new product.
Management believes that advertisement A is more effective
than advertisement B. Two test market areas with virtually
identical consumer characteristics are selected:
advertisement A is used in one area and advertisement B in
another area. In a random sample of 60 customers who saw
advertisement A, 18 had tried the product. In a random
sample 100 customers who saw advertisement B, 22 had
tried the product. Does this indicate that advertisement A is
more effective than advertisement B? Use α = 5%.
05/05/2024 By: Nejat A. - Lecturer of Management Dep 115
artment (HU)
Solution

 Given: = 60, = 100, = = 0.30, = = 0.22 and 𝜶 = 5%

 Step 1: :

 Step 2: The appropriate test statistic is -test.

= = = 1.645

05/05/2024 By: Nejat A. - Lecturer of Management Dep 116


artment (HU)
…Solution

 Decision rule: - Accept if

05/05/2024 By: Nejat A. - Lecturer of Management Dep 117


artment (HU)
…Solution

 Step 3: Sample data analysis

= 0.25

05/05/2024 By: Nejat A. - Lecturer of Management Dep 118


artment (HU)
…Solution

= 1.312
 Step 4: Decision: since (1.312) is less than (𝟏.𝟔𝟒𝟓) accept .

05/05/2024 By: Nejat A. - Lecturer of Management Dep 119


artment (HU)
End of Chapter Three
Chapter Four

Chi-square Test
Characteristics of the Chi-Square Distribution

… it is positively skewed
… it is non-negative
… it is based on degrees of freedom
…when the degrees of freedom change
a new distribution is created

05/05/2024 By: Nejat A. - Lecturer of Management Dep 122


artment (HU)
…Characteristics of the Chi-Square Distribution

df = 3

df = 5
df = 10

05/05/2024 By: Nejat A. - Lecturer of Management Dep 123


artment (HU)
Areas of Application

 Test for independence between two variables

 Testing for the equality of several proportions

 Goodness of fit tests (Binomial, Poisson and Normal)

05/05/2024 By: Nejat A. - Lecturer of Management Dep 124


artment (HU)
Test for Independence Between Two Variables

 To analyze the frequencies of two variables with multiple


categories to determine whether the two variables are
independent.
 Whether employee absenteeism is independent of job
satisfaction.
 Whether product preference is independent of gender.
 Whether favorite sport is independent of nationality.
 Whether type of financial investment is independent of
geographic region.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 125


artment (HU)
Illustration

 A company planning a TV advertising campaign and wants to


determine which TV shows its target audience watches.
Thereby to know whether the choice of TV program an
individual watches is independent of the individuals income.
The table supporting this is shown below. Use a 5% level of
significance and the null hypothesis.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 126


artment (HU)
…Illustration

Income Type of TV Show


Basketball Movie News Total
Low 143 70 37 250
Medium 90 67 43 200
High 17 13 20 50
Total 250 150 100 500

05/05/2024 By: Nejat A. - Lecturer of Management Dep 127


artment (HU)
Solution

 Step 1:- State


 : Choice of TV program an individual watches is
independent of the individuals income
 : Income and Choice of TV program are not independent
 Step 2:- Decision Rule
 The appropriate test statistic is - test

 Reject , if is greater than 9.488

05/05/2024 By: Nejat A. - Lecturer of Management Dep 128


artment (HU)
…Solution

 Step 3:- Sample Data Analysis

Type of TV Show
Income Basketball Movie News Total

Low 143 70 37 250


Medium 90 67 43 200
High 17 13 20 50
Total 250 150 100 500

05/05/2024 By: Nejat A. - Lecturer of Management Dep 129


artment (HU)
…Solution

 Step 3:- Sample Data Analysis

Type of TV Show
Income Basketball Movie News Total

Low 250
Medium 200
High 50
Total 250 150 100 500
05/05/2024 By: Nejat A. - Lecturer of Management Dep 130
artment (HU)
…Solution

 Step 3:- Sample Data Analysis

Type of TV Show
Income Basketball Movie News Total

Low 125 75 50 250


Medium 75 60 40 200
High 25 15 10 50
Total 250 150 100 500
05/05/2024 By: Nejat A. - Lecturer of Management Dep 131
artment (HU)
…Solution

Type of TV Show
Income Basketball Movie News Total

Low 143 70 37 250


Medium 90 67 43 200
High 17 13 20 50
Total 250 150 100 500
Type of TV Show
Income Basketball Movie News Total

Low 125 75 50 250


Medium 75 60 40 200
High 25 15 10 50
05/05/2024
TotalBy: Nejat A. - Lecturer250
of Management Dep
150 100 500132
artment (HU)
…Solution

= 21.174
 Step 4:- Since (9.488) is less than (21.174), reject , i.e.
income and Choice of TV program are not independent.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 133


artment (HU)
Testing for the Equality of Several Proportions

 The population proportions are not equal to the


hypothesized values.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 134


artment (HU)
Illustration

 Ethio Plastic Factory sells its products in three primary colors:


red, blue, and yellow. The marketing manager feels that
customers have no color preference for the product. To test
this hypothesis the manager set up a test in which 120
purchases were given equal opportunity to buy the product in
each of the three colors. The results were that 60 bought red,
20 bought blue, and 40 bought yellow. Test the marketing
manager’s null hypothesis, using α=0.05.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 135


artment (HU)
Solution

 Step 1:- State

 Step 2:- Decision Rule


 The appropriate test statistic is - test

 Reject , if is greater than 5.99

05/05/2024 By: Nejat A. - Lecturer of Management Dep 136


artment (HU)
…Solution

 Step 3:- Sample Data Analysis

Class

Rad 60 40 400 10.00


Blue 20 40 400 10.00
Yellow 40 40 0 0.00
Total 20

05/05/2024 By: Nejat A. - Lecturer of Management Dep 137


artment (HU)
…Solution

 Step 4:- Since (5.99) is less than (20), reject . This means that
customers do have clolor preference.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 138


artment (HU)
Goodness-of-Fit Tests

 It can be used to decide whether a particular probability


distribution, such as the binomial, poisson or normal, is the
appropriate distribution.
 Null hypothesis: In Chi-Square goodness of fit test, the null
hypothesis assumes that there is no significant difference
between the observed and the expected value.
 Alternative hypothesis: In Chi-Square goodness of fit test, the
alternative hypothesis assumes that there is a significant
difference between the observed and the expected value.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 139


artment (HU)
Binomial Goodness-of-Fit Tests

05/05/2024 By: Nejat A. - Lecturer of Management Dep 140


artment (HU)
Illustration

 Mrs. Tsion, Saleswoman for MOON Paper Company, has five


accounts to visit per day. It is suggested that sales by Mrs.
Tsion may be described by the binomial distribution, with the
probability of selling each account being 0.4.
 Given the following frequency distribution of Mrs. Tsion’s
number of sales per day, can we conclude that the data do in
fact follow the binomial distribution? Use the 0.05
significance level.

No. sales per day 0 1 2 3 4 5


Frequency 10 41 60 20 6 3

05/05/2024 By: Nejat A. - Lecturer of Management Dep 141


artment (HU)
Solution

 Step 1:- State

 Step 2:- Decision Rule


 The appropriate test statistic is - test

 Reject , if is greater than 9.488

05/05/2024 By: Nejat A. - Lecturer of Management Dep 142


artment (HU)
…Solution

 Step 3:- Sample Data Analysis


Sales Prob.
per day

0 .0778 10 10.892 0.7957 0.0731


1 .2592 41 36.288 22.2029 0.6119
2 .3456 60 48.384 134.9315 2.7888
3 .2304 20 32.256 150.2095 4.6567
4&5 .0870 9 12.18 10.1124 0.8302
Total 8.9607
05/05/2024 By: Nejat A. - Lecturer of Management Dep 143
artment (HU)
…Solution

 Step 4:- Since (9.488) is greater than (8.9607), accept . This


means that the data are well described by the Binomial
distribution with

05/05/2024 By: Nejat A. - Lecturer of Management Dep 144


artment (HU)
Poisson Goodness-of-Fit Test


05/05/2024 By: Nejat A. - Lecturer of Management Dep 145


artment (HU)
Illustration

 It is hypothesized that the number of breakdowns per month


of a computer system at a major university follows a Poisson
distribution with μ = 2. The data below show the observed
number of breakdowns per month during a sample of 100
months. Use a 5% level of significance and test the null
hypothesis.

Breakdowns 0 1 2 3 4 5

Observed freq. 14 20 34 22 5 5

05/05/2024 By: Nejat A. - Lecturer of Management Dep 146


artment (HU)
Solution

 Step 1:- State

 Step 2:- Decision Rule


 The appropriate test statistic is - test

 Reject , if is greater than 11.07

05/05/2024 By: Nejat A. - Lecturer of Management Dep 147


artment (HU)
…Solution

 Step 3:- Sample Data Analysis

05/05/2024 By: Nejat A. - Lecturer of Management Dep 148


artment (HU)
…Solution

 Step 3:- Sample Data Analysis



Sales
Prob.
per day
0 .1353 14 13.53 0.2209 0.0163
1 .2707 20 27.07 49.9849 1.8465
2 .2707 34 27.07 48.0249 1.7741
3 .1804 22 18.04 15.6816 0.8693
4 .0902 5 9.02 16.1604 1.7916
5 .0527 5 5.27 0.0729 0.0138
Total 6.3117
05/05/2024 By: Nejat A. - Lecturer of Management Dep 149
artment (HU)
Solution

 Step 4:- Since (11.07) is greater than (6.3117), accept . This


means that the number of breakdowns per month of
computer system at the University follows a Poisson
distribution with

05/05/2024 By: Nejat A. - Lecturer of Management Dep 150


artment (HU)
Normality Goodness-of-Fit Test

 the observed frequency distribution matches to normal


distribution with the given
 the observed frequency distribution don’t match to
normal distribution with the given

05/05/2024 By: Nejat A. - Lecturer of Management Dep 151


artment (HU)
Illustration

 Suppose that Mr. Paulos developed an overall attitude scale


to determine how his company’s employees feel toward their
company. In theory the scores can vary from 0 to 50. Mr.
Paulos pretests his measurement instrument on a randomly
selected group of 100 employees. He tallies the scores and
summarizes them into six categories as shown below.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 152


artment (HU)
…Illustration

Score
fo
category
10 - 15 11
…Are these pretest scores
15 - 20 14 approximately normally
20 – 25 24 distributed with μ = 24.9
and σ = 7.194? Use α =
25 - 30 28 0.05.
30 - 35 13
35 - 40 10

05/05/2024 By: Nejat A. - Lecturer of Management Dep 153


artment (HU)
Solution

 Step 1:- State

 Step 2:- Decision Rule


 The appropriate test statistic is - test

 Reject , if is greater than 11.07

05/05/2024 By: Nejat A. - Lecturer of Management Dep 154


artment (HU)
…Solution

 Step 3:- Sample Data Analysis


05/05/2024 By: Nejat A. - Lecturer of Management Dep 155


artment (HU)
…Solution

 Step 3:- Sample Data Analysis


Score For category 10-15 Probability
fo 0.48077
category
10 - 15 11 -0.41621
Expected Probability
15 - 20 14
For category 15-20 Probability
20 – 25 24
0.41621
25 - 30 28 -0.25175
30 - 35 13 Expected Probability

35 - 40 10

05/05/2024 By: Nejat A. - Lecturer of Management Dep 156


artment (HU)
…Solution

Score For category 20-25 Probability


fo 0.25175
category
10 - 15 11 +0.00399
Expected Probability
15 - 20 14
For category 25-30 Probability
20 – 25 24
-0.00399
25 - 30 28 +0.26115
30 - 35 13 Expected Probability

35 - 40 10

05/05/2024 By: Nejat A. - Lecturer of Management Dep 157


artment (HU)
…Solution

Score For category 30-35 Probability


fo
category -0.26115
10 - 15 11 +0.41924
15 - 20 14 Expected Probability
20 – 25 24 For category 35-40 Probability
25 - 30 28 -0.41924
30 - 35 13 +0.48214
Expected Probability
35 - 40 10

05/05/2024 By: Nejat A. - Lecturer of Management Dep 158


artment (HU)
…Solution

Category Prob.
< 10 0.01923 1.923
10 – 15 0.06456 6.456 8.379
15 – 20 0.16446 16.446 16.446
20 – 25 0.25574 25.574 25.574
25 – 30 0.25716 25.716 25.716
30 – 35 0.15809 15.809 15.809
35 – 40 0.06290 6.290 8.076
> 40 0.01786 1.786

05/05/2024 By: Nejat A. - Lecturer of Management Dep 159


artment (HU)
…Solution

Sales
per day
10 – 15 11 8.379 6.8696 0.8199
15 – 20 14 16.446 5.9829 0.3638
20 – 25 24 25.574 2.4775 0.0964
25 – 30 28 25.716 5.2167 0.2029
30 – 35 13 15.809 7.8905 0.4991
35 – 40 10 8.076 3.7018 0.4584
Total 2.4409

05/05/2024 By: Nejat A. - Lecturer of Management Dep 160


artment (HU)
…Solution

 Step 4:- Since (11.07) is greater than (2.4409), accept . This


means that the attitude are normally distributed with

05/05/2024 By: Nejat A. - Lecturer of Management Dep 161


artment (HU)
End of Chapter Four
Chapter Five

ANOVA
One-Way ANOVA

 The one-way analysis of variance is used to test the claim that


three or more population means are equal.
 ANOVA process of computing of several variances is used to
test the equality of several means.
 This is an extension of the two independent samples t-test.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 164


artment (HU)
…One-Way ANOVA

 The null hypothesis is that the means are all equal

 The alternative hypothesis is that at least one of the means is


different

05/05/2024 By: Nejat A. - Lecturer of Management Dep 165


artment (HU)
F – Distribution

 It is a continuous probability distribution

 It is uni-modal

 It is a positively skewed distribution

 It has two parameters; pair of degrees of freedom, and

05/05/2024 By: Nejat A. - Lecturer of Management Dep 166


artment (HU)
…F – Distribution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 167


artment (HU)
Illustration

 The training director of a company is trying to evaluate three


different methods of training new employees. The first
method assigns each to an experienced employee for
individual help in the factory. The second method puts all
new employees in a training room separate from the factory,
and the third method uses training films and programmed
learning materials. The training director chooses 18 new
employees assigned at random to the three training methods
and records their daily production after they complete the
programs. Below are productivity measures for individuals
trained by each method.
05/05/2024 By: Nejat A. - Lecturer of Management Dep 168
artment (HU)
…Illustration

Method 1 Method 2 Method 3


At the 0.05 level of
45 59 41
significance, do the
40 43 37
three training
50 47 43
methods lead to
39 51 40
different levels of
53 39 52
44 49 37 productivity?

= 45.17 = 48.00 = 41.67 =44.94

= 30.17 = 47.60 = 31.07

05/05/2024 By: Nejat A. - Lecturer of Management Dep 169


artment (HU)
Solution

 Step 1:- State and

 Step 2:- Decision Rule


 The appropriate test statistic is -test

05/05/2024 By: Nejat A. - Lecturer of Management Dep 170


artment (HU)
…Solution

 Step 3:- Sample Data Analysis

05/05/2024 By: Nejat A. - Lecturer of Management Dep 171


artment (HU)
…Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 172


artment (HU)
…Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 173


artment (HU)
…Solution

 Step 4:- Decision: since, (3.68) r That is, there are differences
in the effects of the three training programs (methods) on
employee productivity.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 174


artment (HU)
Variance Test

 Hypothesis Testing of Population Variance: a procedure


which is cast-off to test whether an assumption about
population variance () is true or false (or acceptable or
reject).
 &
 &
 &

05/05/2024 By: Nejat A. - Lecturer of Management Dep 175


artment (HU)
Illustration

 The St. Louis Metro Bus Company wants to promote an


image of reliability by encouraging its drivers to maintain
consistent schedules. As a standard policy the company
would like arrival times at bus stops to have low variability. In
terms of the variance of arrival times, the company standard
specifies an arrival time variance of 4 or less when arrival
times are measured in minutes.
 Suppose that a random sample of 24 bus arrivals taken at a
downtown intersection provides a sample variance of = 4.9.
Formulate hypothesis testing to help the company whether
the arrival time population variance is excessive or not. =
0.05.
05/05/2024 By: Nejat A. - Lecturer of Management Dep 176
artment (HU)
Solution

 Step 1:- State

 Step 2:- Decision Rule


 The appropriate test statistic is -test

05/05/2024 By: Nejat A. - Lecturer of Management Dep 177


artment (HU)
…Solution

 Step 3:- Sample data analysis

 Step 4:- Decision


 Because (28.18) is less than (35.172), accept .

05/05/2024 By: Nejat A. - Lecturer of Management Dep 178


artment (HU)
Hypothesis Testing of ()

 Hypothesis testing of the difference between two population


variances: a procedure which is used to test whether two
population variances () are different or not.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 179


artment (HU)
Illustration

 Suppose Haramaya University has planned to purchase


service buses for the coming year and must select one of two
bus companies, the Mercedes Company or the Daewoo
Company. We will use the variance of the arrival/delivery
times as a primary measure of the quality of the bus service.
Low variance values indicate the more consistent and higher
quality service. If the variances of arrival times associated
with the two services are equal, HU administrators will select
the company offering the better financial terms.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 180


artment (HU)
…Illustration

 However, if the sample data on bus arrival times for the two
companies indicate a significant difference between the
variances, the administrators may want to give special
consideration to the company with the better or lower
variance service. A sample of 26 arrival times for the
Mercedes service provides a sample variance of 48 and a
sample of 16 arrival times for the Daewoo service provides a
sample variance of 20. Formulate hypothesis testing whether
there is a difference between services of companies. .

05/05/2024 By: Nejat A. - Lecturer of Management Dep 181


artment (HU)
Solution

 Step 1:- State


 Step 2:- Decision Rule


 The appropriate test statistic is -test

05/05/2024 By: Nejat A. - Lecturer of Management Dep 182


artment (HU)
…Solution

 Step 3:- Sample data analysis

 Step 4:- Decision


 Because (2.40) is greater than (2.28), r i.e., there is
significance difference between .

05/05/2024 By: Nejat A. - Lecturer of Management Dep 183


artment (HU)
End of Chapter Five
Chapter Six

Regression and Correlation


Simple Linear Regression

 Regression may be defined as the estimation or prediction of


the unknown value of one variable from the known values of
one or more variables.
 The variable whose values are to be estimated or predicted is
known as dependent or explained variable.
 The variable/s which are used in determining the value of the
dependent variable is/are called independent or predictor
variable/s.
 A mathematical equation that defines the relationship
between two variables is called regression equation.
 The line that gives the best estimate of one variable for any
given value of another variable is called regression line.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 186


artment (HU)
…Simple Linear Regression

 What is “Linear”?
 Remember: ?

05/05/2024 By: Nejat A. - Lecturer of Management Dep 187


artment (HU)
…Simple Linear Regression

Not Linear
 Linear

Y Y

x x
residuals

x residuals x

05/05/2024 By: Nejat A. - Lecturer of Management Dep 188


artment (HU)
…Simple Linear Regression

 Regression Equation:

05/05/2024 By: Nejat A. - Lecturer of Management Dep 189


artment (HU)
Curve Fitting

 Curve fitting, also known as regression analysis, is used to


find the "best fit" line or curve for a series of data points.
 Curve fitting examines the relationship between one or more
predictors (independent variables) and a response variable
(dependent variable), with the goal of defining a "best fit"
model of the relationship.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 190


artment (HU)
…Curve Fitting

05/05/2024 By: Nejat A. - Lecturer of Management Dep 191


artment (HU)
Least Squares Method

 The least squares method is a procedure for using sample


data to find the estimated regression equation.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 192


artment (HU)
Illustration

 Suppose data were collected from a sample of 10 Armand’s


Pizza restaurants. For the observation or restaurant in the
sample, is the size of the student population (in thousands)
and is the quarterly sales (in thousands of dollars). The
values of and for the 10 restaurants in the sample are
summarized below.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 193


artment (HU)
…Illustration

Restaurant () Student Population Quarterly Sales


(1000s) ($1000s)
1 2 58
2 6 105
3 8 88
4 8 118
5 12 117
6 16 137
7 20 157
8 20 169
9 22 149
10 26 202

05/05/2024 By: Nejat A. - Lecturer of Management Dep 194


artment (HU)
Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 195


artment (HU)
…Solution

Restaur
Population Sales
ant ()
1 2 58 116 4
2 6 105 630 36
3 8 88 704 64
4 8 118 944 64
5 12 117 1404 144
6 16 137 2192 256
7 20 157 3140 400
8 20 169 3380 400
9 22 149 3278 484
10 26 202 5252 676
Total 140 1300 21040 2528
05/05/2024 By: Nejat A. - Lecturer of Management Dep 196
artment (HU)
…Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 197


artment (HU)
…Solution

05/05/2024 By: Nejat A. - Lecturer of Management Dep 198


artment (HU)
Linear Correlation

 Measures the relative strength of the linear relationship


between two variables.
 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.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 199


artment (HU)
…Linear Correlation

r = -1 r = - 0.6 r=0
Y Y Y

X . X X
r = +1 r = + 0.3 r=0
Y
Y Y

X X X
05/05/2024 By: Nejat A. - Lecturer of Management Dep 200
artment (HU)
…Linear Correlation

Linear relationships Curvilinear relationships

Y Y

X X

Y Y

X X
05/05/2024 By: Nejat A. - Lecturer of Management Dep 201
artment (HU)
…Linear Correlation

Strong relationships Weak relationships

Y Y

X X

Y Y

X X
05/05/2024 By: Nejat A. - Lecturer of Management Dep 202
artment (HU)
…Linear Correlation

No relationship

X
05/05/2024 By: Nejat A. - Lecturer of Management Dep 203
artment (HU)
Correlation Coefficient

05/05/2024 By: Nejat A. - Lecturer of Management Dep 204


artment (HU)
Illustration

 Consider 11 families randomly selected from the population


of families with one brother and one sister, both full grown.
Let denote the height (in inches) of the brother in the
family. Let denote the height (in inches) of the sister in the
family.

05/05/2024 By: Nejat A. - Lecturer of Management Dep 205


artment (HU)
…Illustration

No.
1 71 69
2 68 64
3 66 65
4 67 63
5 70 65
6 71 62
7 70 65
8 73 64
9 72 66
10 65 59
11 66 62

05/05/2024 By: Nejat A. - Lecturer of Management Dep 206


artment (HU)
Solution
No. () ()

1 71 69
2 68 64
3 66 65
4 67 63
𝒙=
∑ 𝒙 𝒊 𝟕𝟓𝟗
= =𝟔𝟗
5 70 65
𝒏𝒙 𝟏𝟏
6 71 62
7 70 65
8 73 64
9 72 66
10 65 59
11 66 62
Total 759 704
05/05/2024 By: Nejat A. - Lecturer of Management Dep
artment (HU)
207
…Solution
No. () ()

1 71 69 2
2 68 64 -1
3 66 65 -3
4 67 63 -2
𝒙=
∑ 𝒙 𝒊 𝟕𝟓𝟗
= =𝟔𝟗
5 70 65 1
𝒏𝒙 𝟏𝟏
6 71 62 2
7 70 65 1
8 73 64 4
9 72 66 3
10 65 59 -4
11 66 62 -3
Total 759 704
05/05/2024 0 By: Nejat A. - Lecturer of Management Dep
artment (HU)
208
…Solution
No. () ()

1 71 69 2 5
2 68 64 -1 0
3 66 65 -3 1
4 67 63 -2 -1
𝒚=
∑ 𝒚 𝒊 𝟕𝟎𝟒
= =𝟔𝟒
5 70 65 1 1
𝒏𝒚 𝟏𝟏
6 71 62 2 -2
7 70 65 1 1
8 73 64 4 0
9 72 66 3 2
10 65 59 -4 -5
11 66 62 -3 -2
Total 759 704
05/05/2024 0 0
By: Nejat A. - Lecturer of Management Dep
artment (HU)
209
…Solution
No. () ()

1 71 69 2 5 10 4 25
2 68 64 -1 0 0 1 0
3 66 65 -3 1 -3 9 1
4 67 63 -2 -1 2 4 1
5 70 65 1 1 1 1 1
6 71 62 2 -2 -4 4 4
7 70 65 1 1 1 1 1
8 73 64 4 0 0 16 0
9 72 66 3 2 6 9 4
10 65 59 -4 -5 20 16 25
11 66 62 -3 -2 6 9 4
Total 759 704
05/05/2024 0 0 39
By: Nejat A. - Lecturer of Management Dep
artment (HU)
74 66 210
…Solution
No. () ()

1 71 69 2 5 10 4 25
2 68 64 -1 0 0 1 0
3 66 65 -3 1 -3 9 1
4 67 63 -2 -1 2 4 1
5 70 65 1 1 1 1 1
6 71 62 2 -2 -4 4 4
7 70 65 1 1 1 1 1
8 73 64 4 0 0 16 0
9 72 66 3 2 6 9 4
10 65 59 -4 -5 20 16 25
11 66 62 -3 -2 6 9 4
Total 759 704
05/05/2024 0 0 39
By: Nejat A. - Lecturer of Management Dep
artment (HU)
74 66 211
…Solution
No. () ()

1 71 69 2 5 10 4 25
2 68 64 -1 0 0 1 0
3 66 65 -3 1 -3 9 1
4 67 63 -2 -1 2 4 1
5 70 65 1 1 1 1 1
6 71 62 2 -2 -4 4 4
7 70 65 1 1 1 1 1
8 73 64 4 0 0 16 0
9 72 66 3 2 6 9 4
10 65 59 -4 -5 20 16 25
11 66 62 -3 -2 6 9 4
Total 759 704
05/05/2024 0 0 39
By: Nejat A. - Lecturer of Management Dep
artment (HU)
74 66 212
…Solution
No. () ()

1 71 69 2 5 10 4 25
2 68 64 -1 0 0 1 0
3 66 65 -3 1 -3 9 1
4 67 63 -2 -1 2 4 1
5 70 65 1 1 1 1 1
6 71 62 2 -2 -4 4 4
7 70 65 1 1 1 1 1
8 73 64 4 0 0 16 0
9 72 66 3 2 6 9 4
10 65 59 -4 -5 20 16 25
11 66 62 -3 -2 6 9 4
Total 759 704
05/05/2024 0 0 39
By: Nejat A. - Lecturer of Management Dep
artment (HU)
74 66 213
…Solution
No. () ()

1 71 69 2 5 10 4 25
2 68 64 -1 0 0 1 0
3 66 65 -3 1 -3 9 1
4 67 63 -2 -1 2 4 1
5 70 65 1 1 1 1 1
6 71 62 2 -2 -4 4 4
7 70 65 1 1 1 1 1
8 73 64 4 0 0 16 0
9 72 66 3 2 6 9 4
10 65 59 -4 -5 20 16 25
11 66 62 -3 -2 6 9 4
Total 759 704
05/05/2024 0 0 39
By: Nejat A. - Lecturer of Management Dep
artment (HU)
74 66 214
…Solution
No. () ()

1 71 69 2 5 10 4 25
2 
68 Conclusion:
64 -1 Since
0 the0 value of1 0
3 66
(correlation
65 -3
coefficient)
1 -3
is 0.558
9 1
(positive) we can conclude that there
4 67 63 -2 -1 2 4 1
is positive relation between the
5 70 65 1 1 1 1 1
height of brothers and the height of
6 71 62 2
sisters. -2 -4 4 4
7 70 65 1 1 1 1 1
8 73 64 4 0 0 16 0
9 72 66 3 2 6 9 4
10 65 59 -4 -5 20 16 25
11 66 62 -3 -2 6 9 4
Total 759 704
05/05/2024 0 0 39
By: Nejat A. - Lecturer of Management Dep
artment (HU)
74 66 215
Rank Correlation

𝟔∑ 𝒅
𝟐
𝒓 𝒔 =𝟏 −
𝒏 ( 𝒏 −𝟏 ) 𝟐

05/05/2024 By: Nejat A. - Lecturer of Management Dep 216


artment (HU)
Illustration

 The following data shows the annual income per head of


population, (in US $) and the infant mortality, (per thousand
live births) for a sample of 11 countries:

05/05/2024 By: Nejat A. - Lecturer of Management Dep 217


artment (HU)
…Illustration

Country
 The following data shows the annual income per head of
A 130 150
population, (in US $) and the infant mortality, (per thousand
B 5950 43
live births) for
C a sample of 11560countries: 121
D 2010 53
E 1870 41
F 170 169
G 390 143
H 580 59
I 820 75
J 6620 20
K 3800 39

05/05/2024 By: Nejat A. - Lecturer of Management Dep 218


artment (HU)
Solution

𝟔∑ 𝒅
𝟐
𝒓 𝒔 =𝟏 −
𝒏 ( 𝒏 −𝟏 ) 𝟐

05/05/2024 By: Nejat A. - Lecturer of Management Dep 219


artment (HU)
…Solution
Country Ranak Ranak
A 130 150 1 10 -9 81
B 5950 43 10 4 6 36
C 560 121 4 8 -4 16
D 2010 53 8 5 3 9
E 1870 41 7 3 4 16
F 170 169 2 11 -9 81
G 390 143 3 9 -6 36
H 580 59 5 6 -1 1
I 820 75 6 7 -1 1
J 6620 20 11 1 10 100
K 3800 39 9 2 7 49
Total 416
05/05/2024 By: Nejat A. - Lecturer of Management Dep 220
artment (HU)
…Solution
Country Ranak Ranak
A 130 150 1 10 -9 81
B 5950 43 10 4 6 36
C 560 121 4 8 -4 16
D 2010 53 8 5 3 9
E 1870 41 7 3 4 16
F 170 169 2 11 -9 81
G 390 143 3 9 -6 36
H 580 59 5 6 -1 1
I 820 75 6 7 -1 1
J 6620 20 11 1 10 100
K 3800 39 9 2 7 49
Total 416
05/05/2024 By: Nejat A. - Lecturer of Management Dep 221
artment (HU)
…Solution
Country Ranak Ranak
A 130 150 1 10 -9 81
B 5950 43 10 4 6 36
C 560 121 Since4the value
Conclusion: 8 of (rank
-4 16

D 2010 53 coefficient)
correlation 8 5
is -0.936 3 9
E 1870 41we can
(negative) 7 conclude3 that 4are 16
F negatively
170 169related.
2 11 -9 81
G 390 143 3 9 -6 36
H 580 59 5 6 -1 1
I 820 75 6 7 -1 1
J 6620 20 11 1 10 100
K 3800 39 9 2 7 49
Total 416
05/05/2024 By: Nejat A. - Lecturer of Management Dep 222
artment (HU)
End of Chapter Six

You might also like