INTRODUCTION
Regression analysis is a statistical technique used to determine the relationship
between a dependent variable and one or more independent variables. It is often
used to predict or estimate the value of the dependent variable based on the
values of the independent variables.
The process involves fitting a regression model to the data, which involves
calculating the coefficients that best fit the data. These coefficients represent
the strength and direction of the relationship between the independent and
dependent variables.
 Simple Linear Regression: This method involves fitting a linear
equation to a set of data points. It is used when there is a single
independent variable and one dependent variable.
There are two types of regression analysis.
 Multiple Linear Regression: In this method, a linear equation is
fitted to a set of data points with multiple independent
variables and one dependent variable.
OVER RUN
1 2
2 5
3 8
4 12
5 14
6 18
7
8
9
X Y
Y
48
44
40
36
32
28
24
20
16
12
8
4
0 1 2 3 4 5 6 7 8 9 10 X
INTERCEPT
OVER RUNS
1 2
2 5
3 8
4 12
5 14
6 18
7
8
9
X Y
40
36
32
28
24
20
16
12
8
4
0 1 2 3 4 5 6 7 8 9
RUNS
OVE
R
OVER
X
o Independent variable/Explanatory Variable.
o Used to predict the variable of interest.
o Dependent variable/Explained Variable.
o It is predicted by using explanatory
variable.
RUN Y
Simple Linear
Regression
Regression equation of Y on X:
 “a” is Y-intercept” & a constant
 “b” is the “slope” of regression line & a constant.
 “b” represents change in Y variable for a unit change in X
variable.
For determination of “a” & “b” simultaneously
Y = a +
bx
𝜮𝒚 = 𝑵𝒂 + 𝒃𝜮𝑿
𝜮𝒙𝒚 = 𝒂𝜮𝒙 + 𝒃𝜮𝑿𝟐
Regression equation of X on Y: X = a + by
𝜮𝐱 = 𝑵𝒂 + 𝒃𝜮𝒀
𝜮𝒙𝒚 = 𝒂𝜮𝐘 + 𝒃𝜮𝒀𝟐
X = a + by
OVER RUN
1 2
2 5
3 8
4 12
5 14
6 18
Regression equation of Y on X:
Y = a +
bx
𝜮𝒚 = 𝑵𝒂 + 𝒃𝜮𝑿….1
𝜮𝒙𝒚 = 𝒂𝜮𝒙 + 𝒃𝜮𝑿𝟐….2
X Y XY 𝑿𝟐 𝒀𝟐
1 2 2 1 4
2 5 10 4 25
3 8 24 9 64
4 12 48 16 144
5 14 70 25 196
6 18 108 36 324
21 59 262 91 757
(59 = 6a + b x 21)......1
(262 = a x 21 + b x 91).....2
(59 = 6a + b x 21)......1 x 7
(262 = a x 21 + b x 91).....2 x 2
413 = 42a + 147b)......3
- 524 = 42a + 182b).....4
-111 = -35b
b =
−𝟏𝟏𝟏
−𝟑𝟓
b = 3.17
59 = 6a + 3.17 x 21
Value of a =
6a = 59 - 66.57 6a = -7.57 a =
−𝟕.𝟓𝟕
𝟔
a = -1.26
X Y
Regression equation of Y
on X:
Y = a +
bx
X = 12
Y =
..?
Y = -1.26 + 3.17 x 12 Y = -1.26 + 38.04
Y = 36.78
Regression equation of X on Y: X = a + by
𝜮𝐱 = 𝑵𝒂 + 𝒃𝜮𝒀
𝜮𝒙𝒚 = 𝒂𝜮𝐘 + 𝒃𝜮𝒀𝟐
(21 = 6 x a + b x 59)......1
(262 = a x 59 + b x 757).....2
(21 = 6 x a + b x 59)......1 x 59
(262 = a x 59 + b x 757).....2 x 6
1239 = 354a + 3481b
-1572 = 354a + 4542b
-333 = -1061b
b =
𝟑𝟑𝟑
𝟏𝟎𝟔𝟏
b = 0.314
Value of a =
21 = 6 x a + 0.314 x 59 6a = 21- 18.526 6a = 2.474 a =
𝟐.𝟒𝟕𝟒
𝟔
a = 0.412
Regression equation of X
on Y:
X = …?
Y = 27
X = 0.412 + 0.314 x 27 X = 0.412 + 8.478
Y = 8.89/
approx. 9
over
X = a + by
Regression | Linear | Regression Analysis | Complete Explanation | Regression |

Regression | Linear | Regression Analysis | Complete Explanation | Regression |

  • 2.
    INTRODUCTION Regression analysis isa statistical technique used to determine the relationship between a dependent variable and one or more independent variables. It is often used to predict or estimate the value of the dependent variable based on the values of the independent variables. The process involves fitting a regression model to the data, which involves calculating the coefficients that best fit the data. These coefficients represent the strength and direction of the relationship between the independent and dependent variables.
  • 3.
     Simple LinearRegression: This method involves fitting a linear equation to a set of data points. It is used when there is a single independent variable and one dependent variable. There are two types of regression analysis.  Multiple Linear Regression: In this method, a linear equation is fitted to a set of data points with multiple independent variables and one dependent variable.
  • 4.
    OVER RUN 1 2 25 3 8 4 12 5 14 6 18 7 8 9 X Y Y 48 44 40 36 32 28 24 20 16 12 8 4 0 1 2 3 4 5 6 7 8 9 10 X INTERCEPT
  • 5.
    OVER RUNS 1 2 25 3 8 4 12 5 14 6 18 7 8 9 X Y 40 36 32 28 24 20 16 12 8 4 0 1 2 3 4 5 6 7 8 9 RUNS OVE R OVER X o Independent variable/Explanatory Variable. o Used to predict the variable of interest. o Dependent variable/Explained Variable. o It is predicted by using explanatory variable. RUN Y Simple Linear Regression
  • 6.
    Regression equation ofY on X:  “a” is Y-intercept” & a constant  “b” is the “slope” of regression line & a constant.  “b” represents change in Y variable for a unit change in X variable. For determination of “a” & “b” simultaneously Y = a + bx 𝜮𝒚 = 𝑵𝒂 + 𝒃𝜮𝑿 𝜮𝒙𝒚 = 𝒂𝜮𝒙 + 𝒃𝜮𝑿𝟐 Regression equation of X on Y: X = a + by 𝜮𝐱 = 𝑵𝒂 + 𝒃𝜮𝒀 𝜮𝒙𝒚 = 𝒂𝜮𝐘 + 𝒃𝜮𝒀𝟐 X = a + by
  • 7.
    OVER RUN 1 2 25 3 8 4 12 5 14 6 18 Regression equation of Y on X: Y = a + bx 𝜮𝒚 = 𝑵𝒂 + 𝒃𝜮𝑿….1 𝜮𝒙𝒚 = 𝒂𝜮𝒙 + 𝒃𝜮𝑿𝟐….2 X Y XY 𝑿𝟐 𝒀𝟐 1 2 2 1 4 2 5 10 4 25 3 8 24 9 64 4 12 48 16 144 5 14 70 25 196 6 18 108 36 324 21 59 262 91 757 (59 = 6a + b x 21)......1 (262 = a x 21 + b x 91).....2 (59 = 6a + b x 21)......1 x 7 (262 = a x 21 + b x 91).....2 x 2 413 = 42a + 147b)......3 - 524 = 42a + 182b).....4 -111 = -35b b = −𝟏𝟏𝟏 −𝟑𝟓 b = 3.17 59 = 6a + 3.17 x 21 Value of a = 6a = 59 - 66.57 6a = -7.57 a = −𝟕.𝟓𝟕 𝟔 a = -1.26 X Y
  • 8.
    Regression equation ofY on X: Y = a + bx X = 12 Y = ..? Y = -1.26 + 3.17 x 12 Y = -1.26 + 38.04 Y = 36.78
  • 9.
    Regression equation ofX on Y: X = a + by 𝜮𝐱 = 𝑵𝒂 + 𝒃𝜮𝒀 𝜮𝒙𝒚 = 𝒂𝜮𝐘 + 𝒃𝜮𝒀𝟐 (21 = 6 x a + b x 59)......1 (262 = a x 59 + b x 757).....2 (21 = 6 x a + b x 59)......1 x 59 (262 = a x 59 + b x 757).....2 x 6 1239 = 354a + 3481b -1572 = 354a + 4542b -333 = -1061b b = 𝟑𝟑𝟑 𝟏𝟎𝟔𝟏 b = 0.314 Value of a = 21 = 6 x a + 0.314 x 59 6a = 21- 18.526 6a = 2.474 a = 𝟐.𝟒𝟕𝟒 𝟔 a = 0.412
  • 10.
    Regression equation ofX on Y: X = …? Y = 27 X = 0.412 + 0.314 x 27 X = 0.412 + 8.478 Y = 8.89/ approx. 9 over X = a + by