Scribd
Upload
136 views

Econometrics - Classical Regression Assumptions

1) The document discusses the assumptions of the classical linear regression model, including that the relationship between the dependent and independent variables is linear, the error terms have a mean of zero and are independent and normally distributed. 2) It introduces the Gauss-Markov theorem, which states that under the assumptions, the least squares estimator is the best linear unbiased estimator (BLUE). 3) The key assumptions required for the Gauss-Markov theorem are that the regression is linear in parameters, there is random sampling, the error terms have zero conditional mean, and the errors have equal variance given any value of the independent variable (homoscedasticity).

Uploaded by

Abigail V
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
136 views

Econometrics - Classical Regression Assumptions

1) The document discusses the assumptions of the classical linear regression model, including that the relationship between the dependent and independent variables is linear, the error terms have a mean of zero and are independent and normally distributed. 2) It introduces the Gauss-Markov theorem, which states that under the assumptions, the least squares estimator is the best linear unbiased estimator (BLUE). 3) The key assumptions required for the Gauss-Markov theorem are that the regression is linear in parameters, there is random sampling, the error terms have zero conditional mean, and the errors have equal variance given any value of the independent variable (homoscedasticity).

Uploaded by

Abigail V
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

Econometrics

Assumptions of the classical regression model/Guass Markov


A regression analysis as performed on the number of employees (X) and profits per employee
(Y) for 16 publishing firms. A portion of the computer generated output is provided below.

Predictor Coef. SE Coef. t ratio p-value


Constant 17.954 4.457 4.03 0.001
Employees -0.2715 0.1726 -1.57 0.138

S = 10.6112 R-Sq = 15% R-Sq(adj) = 9%

a) Identify the least squares estimates of the slopes and intercept coefficients. (2 marks)
b) Test the hypothesis 𝐻0 : 𝛽1 = 0 with 𝛼 = 0.1. Does there appear to be a relationship
between profits per employee and number of employees? Explain. (5 marks)
c) Interpret 𝑟 2 . (3 marks)
d) Is this fitted regression function likely to be a good tool for forecasting profits per
employee for a given number of publishing firm employees? Explain your answer.
(5 marks)

2
Assumptions of the Regression Model
•  
1. The relationship between and is linear
2. The error term has a mean of zero for a given value of
3. The error terms are independent (No autocorrelation)
4. For an given the distribution of is normal
5. The spread of for each is constant. That is the standard
deviation for each error term is equal (homoscedasticity)

3
4
Homoscedastic

5
Heteroscedastic

6
•6.  No Multicollinearity – The x variables are not related to each
other.
Motor accidents = (number of cars) + (number of residents)
7. Exogeneity – All the explanatory variables are unrelated with
the error terms.
Cov (x,u) = 0 (X is exogenous)
Cov (x,u) ≠ 0 (X is endogenous)

7
•  
X1 Y

u1

8
Main Assumptions of the Error Terms
•1.   The error terms are random variables with a mean of 0 i.e.
2. The variances of the error terms are equal i.e.
(Homoscedasticity)
3. The error terms are not correlated i.e.
4. The error terms are normally distributed

9
Desirable properties of an Estimator
1. Unbiased
2. Efficient
3. Consistent

10
Guass Markov Theorem
This theorem states that given the classical assumptions the least
square estimator is BLUE. It requires that the first six of the
seven assumptions be met.
BLUE – Best linear unbiased estimator.

11
The Gauss-Markov Theorem
•The
  theorem shows that the least squares estimators have the
smallest variance of any other linear estimators. If represents
any linear estimator of and represents the OLS estimator of , it
can be shown that,

12
Assumptions of the GM theorem
•1.   Linear in parameters -
2. Random sampling
3. Zero conditional mean - The error u has an expected value of
zero given any value of the explanatory variable. In other words
E(u/x) = 0
4. The error u has the same variance given any value of the
explanatory variable. In other words Var (u/x) =

13
No perfect collinearity

14

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