Scribd
Upload
41 views34 pages

BMA3102 Topic One

The document outlines a course on Business Statistics, covering topics such as correlation and regression analyses, sampling, normal distribution, and hypothesis testing. It details methods for analyzing correlation, including scatter diagrams and various coefficients, as well as regression analysis techniques. Additionally, it provides examples and calculations for applying these statistical methods in business contexts.

Uploaded by

eliebuhendwam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
41 views34 pages

BMA3102 Topic One

The document outlines a course on Business Statistics, covering topics such as correlation and regression analyses, sampling, normal distribution, and hypothesis testing. It details methods for analyzing correlation, including scatter diagrams and various coefficients, as well as regression analysis techniques. Additionally, it provides examples and calculations for applying these statistical methods in business contexts.

Uploaded by

eliebuhendwam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 34

BMA3102: BUSINESS STATISTICS

II

Gabriel Kamau
078928605
gabkkamau@gmail.com
Brief Outline

•Correlation and Regression Analyses


•Sampling
•Normal Distribution
•Introduction to Hypothesis Testing
•Parametric Tests
•Non-Parametric Tests
TOPIC ONE: CORRELATION &
REGRESSION ANALYSES
1.1 Introduction
• Correlation refers to the degree to which two or more variables
are related.
• Correlation analysis is a technique used to establish whether two
or more variables are related or not.
• Methods of studying correlation
i) Scatter diagram
ii) Karl Pearson’s coefficient of correlation
iii) Spearman’s Rank coefficient of correlation
iv) Method of least square
1.2 Scatter diagram
• Is a graphical method of checking whether two variables are
related or not.
• It can be used to study different types of correlation:
i) Perfect correlation: Where all the points in a graph lie on the
best line of fit i.e. all the changes in dependent variable can be
explained by the changes in the independent variable. There
are two types of perfect correlation:
a) Perfect Positive: as the independent variable increases, the
dependent variable also increases
b) Perfect negative: as the independent variable increases, the
dependent decreases.
Perfect positive

18

16

14

12

10

0
0 2 4 6 8 10 12 14
Perfect negative

70

60

50

40

30

20

10

0
0 2 4 6 8 10 12 14
Cont...

ii) Part correlation: In this case not all points are on the
best line of fit i.e. not all changes in the dependent can
be explained by changes in the independent. There are
four types:
a) Strong positive correlation
b) Strong negative correlation
c) Weak positive correlation
d) Weak negative correlation
Strong positive correlation

25

20

15

10

0
0 2 4 6 8 10 12 14
Strong negative correlation

30

25

20

15

10

0
0 2 4 6 8 10 12 14
Weak positive correlation

35

30

25

20

15

10

0
0 2 4 6 8 10 12
Weak negative correlation

90

80

70

60

50

40

30

20

10

0
0 5 10 15 20 25 30
iii) No Correlation: in this case the variables do not
show any trend of relationship
Eg1. The following data relates to the cost of advertising
(000Rwf) and sales (0000rwf) for XYZ ltd.

Mont Jan Feb Mar April May June July Aug


h
Adver 100 80 80 70 120 160 160 200
tising
Sales 60 80 100 60 100 120 80 160

• Draw a scatter diagram to check for linear relationship.


Comment on the correlation.
• H/W Use Karl Pearson and comment.
1.3 Karl Pearson’s coefficient of
correlation
•Also known as product moment coefficient of
correlation.
•Is symbolized by r and lies between -1 and +1
.

𝑛Σ𝑥𝑦 − Σ𝑥Σ𝑦
𝑟=
𝑛Σ𝑥 2 − Σ𝑥 2 ∗ 𝑛Σ𝑦 2 − Σ 2
Eg2. Calculate the product moment coefficient for the
following. Comment on your answer.

X 1 5 6 7 9 10 12 14 16

Y 10 10 8 9 7 10 6 4 2
Using scientific calculator
• Step one: CLEAR THE MEMORY
Shift Mode 3(all) =
• Step two: ENTER DATA
Mode 3(reg) 1(lin)
Then enter data x and its y
X1 , y1 M+
X2 , y2 M+
• Step three :Obtaining results
Finding summations: shift 1
Eg Σxy: shift 1 scroll until u see Σxy 3 =
Finding r: shift 2 scroll until u see r 3 =
1.4 Spearman Rank coefficient of
correlation
•Also known as rank coefficient of correlation.
•It is symbolized by R and also lies between -1 and +1.

6 d 2
•R= 1-
n  n 2  1

d= difference between ranks


Rank coefficient of correlation is applicable when the data is
ordered i.e positions are assigned.
Eg3. Eight contestants were ranked by two judges as
shown below.
Contesta A B C D E F G H
nt
Judege1 1 5 7 2 8 3 4 6

Judge2 1 3 5 6 8 2 7 4

Required: Calculate rank coefficient of correlation


•Note if data is not ranked, use Karl Pearson’s
coefficient of correlation. But if you have to use
Spearman’s coefficient, you have to first rank the data.
•There are two techniques for data ranking:
a. From highest to the lowest
b. From lowest to highest
Eg4. Eight contestants were given the following marks
(out of 50) by two judges as shown below. Calculate
rank coefficient of correlation
Contesta A B C D E F G H
nt
Judege1 48 35 20 47 38 30 31 42

Judge2 29 37 20 40 36 35 25 45
•Note: if there is a tied rank, the formula is adjusted to
take care of the tied ranks.
3
2 Σ 𝑡 −𝑡
6Σ𝑑 +
𝑅 =1− 12
𝑛 𝑛2 − 1

• Where t= no. of tied ranks


Eg5.Eight contestants were given the following marks
(out of 50) by two judges as shown below. Calculate
rank coefficient of correlation

Contesta A B C D E F G H
nt
Judege1 48 35 20 47 38 30 35 42

Judge2 29 37 20 40 36 35 25 45
1.5 Method of Least Square

•Also known as Regression Analysis.


•This refers to the analysis of the changes which occur
in the dependent variable as a result of changes
occurring on the independent variable.
•Knowledge of regression is particularly very useful in
business statistics where it is necessary to consider the
corresponding changes on dependant variables
whenever independent variables change
Classifications of Regression Analysis

•Broadly classified in:


i. Simple or Multiple Regression analysis
 Simple Regression Analysis: it involves only one
independent variable
 Multiple Regression Analysis : it involves more than
one independent variables.
ii) Linear or non Linear Regression Analysis
 Linear Regression Analysis: The parameters form a
straight line in a graph
 Non linear Regression Analysis: The parameters do
not form a straight line but a curve in a graph.
Formulating the regression equation
•The regression equation of Y on X takes the general
form:

•Where y-hat= is the estimated value of the dependent


variable
•a = is the y-intercept
•b= is the gradient or coefficient of regression
•x= is the independent variable.
•The main objective is to find a and b.
i. By use of normal equations
ii. By use of direct method
iii. By use of scientific calculator
i) Using normal equations

Σy = an + bΣx
Σxy = aΣx + bΣx2

where a= y-intercept

b=gradient(coefficient of regression)
y= dependent variable
x= independent variable
Eg6. Determine the regression equation of
Y on X. Find y hat when x=4

X 1 3 5 6 7 9 10 10

Y 2 6 8 10 6 10 8 12
ii) Using direct method

a=Σy- bΣx
n
b=n Σxy - ΣxΣy
nΣx2-(Σx)2
iii) Using calculator
• Step one: CLEAR THE MEMORY
Shift Mode 3(all) =
• Step two: ENTER DATA
Mode 3(reg) 1(lin)
Then enter data x and its y
X1 , y1 M+
X2 , y2 M+
• Step three :Obtaining results
Finding A: shift 2 scroll until you see A 1 =
Finding B: shift 2 scroll until you see B 2 = Finding r: shift 2 scroll
until you see r 3 =
•Finding y hat: x shift 2 scroll until you see y hat 2 =
Coefficient of determination (r2)

•This refers to the ratio of the explained variation


to the total variation and is used to measure the
strength of the linear relationship.
•It shows how much of the changes of the
dependent variable are due to the changes of the
independent variable.
•It is usually expressed as a percentage.
• Coefficient of det= Explained variation
Total variation

• Or find Karl Pearson coefficient of correlation (spearman’s


coefficient of correlation) and then square it.
• Eg if r=-0.789
• R2= 0.622 i.e. 62.2% of the changes in the dependent
is due to the changes in the independent
Eg7. The following data was taken from the books of XYZ Ltd and relates
to the cost of production (0000rwf) and number of units produced.
Month Jan Feb March April May June July Aug Sept

Produc 20 26 26 18 40 44 42 38 36
tion
cost

No. of 10 20 26 20 38 35 36 26 20
units

i. Draw a scatter diagram to check for linear relationship.


ii. Find Karl Pearson’s coefficient and determine the strength of the
relationship.
iii. Formulate the regression equation of Y(no . Of units) on x.
iv. Comment using the coefficient of determination

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy