Scribd
Upload
34 views

Chapter - III - Multiple Linear Regression Model

The document discusses multiple linear regression models. It defines a stochastic multiple regression model with three variables: a dependent variable Y and two explanatory variables X2 and X3. It explains that the regression coefficients β2 and β3 are called partial regression coefficients, where β2 measures the change in Y from a one-unit change in X2 while holding X3 constant, and vice versa for β3. It also covers estimating regression coefficients using ordinary least squares, interpreting partial regression coefficients, and assessing the significance of regression models using analysis of variance.

Uploaded by

Anuska Jayswal
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
34 views

Chapter - III - Multiple Linear Regression Model

The document discusses multiple linear regression models. It defines a stochastic multiple regression model with three variables: a dependent variable Y and two explanatory variables X2 and X3. It explains that the regression coefficients β2 and β3 are called partial regression coefficients, where β2 measures the change in Y from a one-unit change in X2 while holding X3 constant, and vice versa for β3. It also covers estimating regression coefficients using ordinary least squares, interpreting partial regression coefficients, and assessing the significance of regression models using analysis of variance.

Uploaded by

Anuska Jayswal
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Chapter -3:Multiple Linear Regression Model

Course Instructor: Sabin Shrestha


Stochastic Specification ofPRF
❖ We may write the three-variable stochastic PRF as:
Yi = β1 + β2X2i + β3X3i + ui ……………………….(3.1)
where Y is the dependent variable,
X2 and X3 the explanatory variables (or regressors),
u the stochastic disturbance term, and
i the ith observation.
❖Given the assumptions of the classical regression model, it follows that,
on taking the conditional expectation of Y on both sides of (3.1), we
obtain
E(Yi|X2i,X3i) = β1+ β2X2i+ β3i X3i ……………………………(3.2)
❖In words, (3.2) gives the conditional mean or expected value of Y
conditional upon the given or fixed values of X and X
Assumption
Assumption
Estimation of Multiple Regression Coefficient

❖Estimated regression coefficient

❖Beta Coefficient can be estimated with OLS method.


❖Developing Normal Equation

❖Solving normal equation, we can find the value beta coefficient


The meaning of Partial Regression Coefficients

❖The regression coefficients β2 and β3 are known as partial regression


or partial slope coefficients.
❖The meaning of partial regression coefficient is as follows: β2
measures the change in the mean value of Y, E(Y), per unit change in
X2, holding the value of X3 constant.
❖Likewise, β3 measures the change in the mean value of Y per unit
change in X3, holding the value of X2 constant.
The meaning of Partial Regression Coefficients

❖The regression coefficients β2 and β3 are known as partial regression


or partial slope coefficients.
❖The meaning of partial regression coefficient is as follows: β2
measures the change in the mean value of Y, E(Y), per unit change in
X2, holding the value of X3 constant.
❖Likewise, β3 measures the change in the mean value of Y per unit
change in X3, holding the value of X2 constant.
Problem in Stata

❖Use table – 6.4


❖We consider the behavior of child mortality (CM) in relation to per
capita GNP (PGNP). PGNP is expected to have negative impact on
CM. similarly for female literacy as measured by the female literacy
rate (FLR) we expect that FLR too will have a negative impact on CM
as a priori.. Now when we introduce both the variables in our model,
and examine the influence of each the regressor.

❖ CM = Child mortality, the number of deaths of children under age 5 in a year per 1000 live
births
❖ FLFP = Female literacy rate, percent
❖ PGNP = per capita GNP
Problem in Stata – Interpretation, Hypothesis testing
❖ -0.0056 is the partial regression coefficient
of PGNP and tells us that with the influence
of FLR held constant, as PGNP increases,
say, by a rupee, on average, child mortality
goes down by 0.0056 units.
❖ To make it more economically interpretable,
if the per capita GNP goes up by one
thousand rupees, on average, the number of
deaths of children under age 5 goes down by
about 5.6 per thousand live births.

❖ The coefficient -2.2316 tells us that holding the influence of PGNP constant, on average, the number of deaths of
children under age 5 goes down by about 2.23 per thousand live births as the female literacy rate increases by
one percentage point

❖ Can you check which variable has more impact on CM?


Analysis of Variance (ANOVA)
❖ Study of the total sum of squares and its decomposition from regression
viewpoint is ANOVA
Degree of
Source of Variation Sum of Square (SS) Mean Sum of Square F
Freedom
Explained Sum of Square (ESS) Explained Mean Sum of Square
Due to Regression (ESS) k-1
2
=2 (MSE)=
Fcal =

Due to Residual (RSS) Residual Sum of Square (RSS) Residual Mean Sum of Square
n-k
=
2 2
(MSR) =

Total Sum of Square (TSS) 2


=2 n-1

❖F value is used to assess the significance of overall model.


❖If Fcal> Ftab then Ho is rejected.
R2 and the adjusted R2

Coefficient of multiple ❖Adjusted Coefficient of


determination (R2) : Determination (2):
❖ The percent of variation in the ▪ The percent of variation in the dependent
dependent variable explained by the variable explained by the set of independent
variables adjusted to number of parameters
set of independent variables, X1,
▪ With the inclusion of additional explanatory
X2, X3,…, Xn. variable, R2 will always increase but will
never decline

▪ Adjusted R2 accounts for this defect

You might also like