Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
421 views

Multiple Linear Regression

Multiple linear regression is a statistical technique that uses several explanatory variables to predict the outcome of a response variable. It allows us to assess how well a set of predictor variables is able to predict a particular response variable. The multiple linear regression model finds the best fitting plane through the multidimensional space of the predictor variables to predict the response variable. Key outputs of multiple linear regression include goodness of fit measures like the multiple R and R-squared values, and statistical tests of the significance of each predictor variable coefficient.

Uploaded by

Marlene G Padigos
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
421 views

Multiple Linear Regression

Multiple linear regression is a statistical technique that uses several explanatory variables to predict the outcome of a response variable. It allows us to assess how well a set of predictor variables is able to predict a particular response variable. The multiple linear regression model finds the best fitting plane through the multidimensional space of the predictor variables to predict the response variable. Key outputs of multiple linear regression include goodness of fit measures like the multiple R and R-squared values, and statistical tests of the significance of each predictor variable coefficient.

Uploaded by

Marlene G Padigos
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 26

Multiple Linear

Regression

Multiple Regression Model


A regression model that contains more than one

regressor variable.

Multiple Linear Regression Model


A multiple regression model that is a linear

function of the unknown parameters b0, b1, b2,


and so on.
Yi 0 1 xi1 2 xi 2 p 1 xi , p 1 i
Examples:
log10 Yi 0 1 xi1 2 exp( xi 2 ) i

Nonlinear:

Yi 0 e 1 xi i

Intercept predicts
where the regression
plane crosses the Y
axis

Slope for variable X1


(1) predicts the
change in Y per unit
X1 holding X2 constant

The slope for variable


X2 (2) predicts the
change in Y per unit
X2 holding X1 constant
3

Estimates for the multiple slope coefficients


are derived by minimizing residuals 2 to derive this
multiple regression model:

The standard error of the regression is


based on the residuals2:

A multiple regression analysis involves


estimation, testing, and diagnostic procedures
designed to fit the multiple regression model to a
set of data. E ( y ) 0 1x1 2 x 2 k x k

The Method of LeastySquares


b0 b1x1 b2 x 2 bk x k
The prediction equation
is the line that minimizes SSE, the sum of
squares
y . of the deviations of the observed values
y from the predicted values

When you perform multiple regression analysis, use a step-bystep approach:


1. Obtain the fitted prediction model.
2. Use the analysis of variance F test and R 2 to determine
how
well the model fits the data.
3. Check the t tests for the partial regression coefficients to
see
which ones are contributing significant information in the
presence of the others.
4. If you choose to compare several different models, use
R 2(adj) to compare their effectiveness
5. Use-computer generated residual plots to check for
violation
of the regression assumptions.

First time to Use MLR


in Excel

Open MS Excel and


Click this icon
.
Click on the Excel
options.

Multiple Regression

Click Add- ins and


Select Analysis
ToolPak from the
Add-ins List.
Multiple Regression

Click on Excel Add-ins.


Then Click Go...

Multiple Regression

10

Check on
Analysis
ToolPak, Then
Click OK.

Multiple Regression

11

To check:
Go to Data Menu and Go
to Data analysis Tab.

Multiple Regression

12

EXAMPLE

The example on the next slide is about


the result on the quizzes and
summative test of 20 students in TLE
subjects.
The Hypothesis:
Is there any relationship between the
students quiz results to his summative
test result @ .05 level of significance.
14

Students
student1
student2
student3
student4
student5
student6
student7
student8
student9
student10
student11
student12
student13
student14
student15
student16
student17
student18
student19

Quiz 1

Quiz 2
73
93
89
96
73
53
69
47
87
79
69
70
93
79
70
93
78
81
88

Multiple Regression

Quiz 3
80
88
91
98
66
46
74
56
79
70
70
65
95
80
73
89
75
90
92

Summative
Test
75
152
93
185
90
180
100
196
70
142
55
101
77
149
60
115
90
175
88
164
73
141
74
141
91
184
73
152
78
148
96
192
68
147
93
183
86
177
15

Excel

Demo

Multiple Regression

17

Then, P-value (0.9309)


> .05 therefore Accept Ho.
Multiple Regression

18

Then, P-value (0.65706) > .05 therefore Accept Ho.


So, there is a significant relationship between the
Multiple Regression

19

Then, P-value (0.241742) > .05 therefore Accept


Multiple Regression

20

Excel Regression Analysis


Output Explained:
Multiple Regression

These are the Goodness of Fit measures. They tell you


how well the calculated linear equation fits your data.

1.

Multiple R.
This is thecorrelation coefficient. It tells you how strong
the linear relationship is. For example, a value of 1
means a perfect positive relationship and a value of zero
means no relationship at all. It is the square root ofr
squared

2.

R square.
This is r2, theCoefficient of Determination. It tells you
how many points fall on the regression line. for example,
80% means that 80% of the variation of y-values around
the mean are explained by the x-values. In other words,
80% of the values fit the model.

3.

Adjusted R square.
The adjusted R-squared adjust for the number of
terms in a model. Youll want to use this instead of
#2 if you have more than one x variable.

4. Standard Error of the regression:


An estimate of the standard deviation of the error .
This isnotthe same as thestandard errorin
descriptive statistics! The standard error of the
regression is the precision that the regression
coefficient is measured; if the coefficient is large
compared to the standard error, then the coefficient
is probably different from 0.
5. Observations.
Number of observations in the sample.

SS = Sum of Squares.
Regression MS = Regression

SS /
Regressiondegrees of freedom.
Residual MS = mean square error
(Residual SS / Residual degrees of
freedom).
F: Overall F test for the null
hypothesis.
Significance F: The associated P-Value.

Coefficient:
Gives you theleast squaresestimate.
Standard Error:
The least squares estimate of the standard
error.
T Statistic:
The T Statistic for thenull hypothesisvs.
thealternate hypothesis.
P Value:
Gives you the p-value for the hypothesis test.
Lower 95%:
The lower boundary for theconfidence interval.
Upper 95%:
The upper boundary for theconfidence interval.

Thank you

You might also like