Scribd
Upload
2 views

Regression and correlation

The document presents an overview of regression analysis and correlation, detailing their definitions, types, and applications. It explains the relationship between dependent and independent variables, and introduces various regression types including linear, non-linear, and logistic regression. Additionally, it covers correlation, its measurement through the correlation coefficient, and methods such as scatter diagrams and Karl Pearson's coefficient.

Uploaded by

Maha Khan
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views

Regression and correlation

The document presents an overview of regression analysis and correlation, detailing their definitions, types, and applications. It explains the relationship between dependent and independent variables, and introduces various regression types including linear, non-linear, and logistic regression. Additionally, it covers correlation, its measurement through the correlation coefficient, and methods such as scatter diagrams and Karl Pearson's coefficient.

Uploaded by

Maha Khan
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

Regression

Analysis and
Correlation
• Presented by:
IQRA KHALID (SP24-R06-013)
NOOR BEGUM (SP24-R06-030)

• Presented To:
Dr. Zia Ul Haq Khan
Content

Regression
1 Analysis 2 Correlation

3 Types 4 Types

Importance Methods of
5 6 Measurement

www.presentati ongo.com
Regression Analysis

• It is statistical method used to find the relationship


between one dependent variable and one/many
Independent variables of interest.
• It is tool to identify that which variable have grater
impact over dependent variable, which variable can
be ignored and how these varibles interect with each
other.
Variables:
Y
DEPENDENT VARIABLES:

Dependent (scores)
• When we are trying to predict or explain(Y).
INDEPENDENT VARIABLES:
That are used to predict or explain the change in
dependent variables.
Examples: Independent (hours) X
 Predicting exam scores based on study hours.
 Predicting salary based on year of experience .
Example( regression analysis)
Types of regression analysis:

1. Linear regression:
it is an statistical method which describe the relationship between two variables ( one dependent
one independent variable). The primary object of linear regression is to predict dependent
variables on the bases of independent variables.
Formula: Y=a+bX
Y=dependent varible
X=independent variable
a=intercept
b=slope
Non-linear regression:

It is statistical technique that fits data to non linear model.This means that the
relationship between data and model is curve rather than a straight line.
Formula: y=f(x , β) +ε
y=dependent variable
x=independent variable
f(x , β) is a non linear function that depent on x and parameter β.
ε is the error term.
Logistic regression:

Logestic regression is statistical technique used to model the probability of a


binary outcome based on one or predictor varibles.Unlike linear regression
which predict continuous outcomes,logestic regression predict the likehood
of an event occurring ( such as yes/no,true/false,success/failure).
The formula for logistic regression is
Applications of regression analysis:
Continue…..
Correlation

• The mutual relation between two


variables or series
• Correlation analysis deals with
association , connection between two
or more variables .
E CORRELATION
LATION
relation means two variables TYPES OF CORRELATION
same direction
two variables
ased
on the other increased too
rsa.
ecreased and if
B • Positive Correlation
• Negative Correlation
eased , other decreased and • No correlation
other increased
C A
Correlation Coefficient
• Correlation is measured through the
“Correlation Coefficient”
• It summarizes in one figure the direction and
degree of correlation.
• It is denoted by “r”
• Its values range from -1 to +1
+1 Perfect positive correlation
-1 Perfect negative correlation
0 No correlation
Measurement of “r”
Methods of measuring correlation

Karl Pearson's
Scatter Diagram coefficient of
correlation
Scatter Diagram

• The scatter diagram is a simple and


diagrammatic representation of variables
• Easy way to study the correlation
between variables without calculating
any numerical value
Disadvantage
• Applicable only to two variables
Karl Pearson's coefficient of correlation

• The formula is as under :


X Y
1 3
2 4
3 5
X Y XY X2 Y2
1 3 3 1 9
2 4 8 4 16
3 5 15 9 25
ΣX= 6 ΣY=12 ΣXY=26 ΣX2 =14 ΣY2 =50

3(26) – (6)(12)

{3(14)-(6)2 } {3(50)-(12)2
78-72
(42-36) (150-144)

= 6
(6) (6)

=+1

You might also like