Scribd
Upload
207 views

Objectives: - by The End of This Lecture Students Will

The document discusses simple linear regression models, describing the population regression function (PRF) and sample regression function (SRF) that is estimated using ordinary least squares (OLS) to minimize the sum of squared residuals and obtain coefficient estimates. OLS solves the first order conditions simultaneously to calculate the slope and intercept coefficients, and an example application to housing price data is presented.

Uploaded by

Syaharani
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
207 views

Objectives: - by The End of This Lecture Students Will

The document discusses simple linear regression models, describing the population regression function (PRF) and sample regression function (SRF) that is estimated using ordinary least squares (OLS) to minimize the sum of squared residuals and obtain coefficient estimates. OLS solves the first order conditions simultaneously to calculate the slope and intercept coefficients, and an example application to housing price data is presented.

Uploaded by

Syaharani
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 14

Lecture 2

Objectives
• By the end of this lecture students will:
– understand the simple linear regression model
– understand the logic behind the method of ordinary
least squares (OLS) estimation
• CLRM topic is a review of the material covered in
316-206 Quantitative Methods 2
• References:
– Gujarati., chapter 2
• also pp 100-105
The Model
– True Model (Population Regression Function)
Yi    X i  ui
– Yi is the ith observation of the dependent variable
– Xi is the ith observation of the independent or
explanatory variable
– ui is the ith observation of the error or disturbance term
  and  are unknown parameters (coefficients)
– i = 1,..., n observations
The Model
• Estimated model (Sample Regression
Function)
Yi  ˆ  ˆX i  uˆi
• where
–
ˆ and ˆ are the estimators of the coefficients
(parameters)
– are the i estimated residuals
ûi
• Objective: estimate the PRF on basis of SRF
The Model
• In terms of the SRF the observed Yi can be
written as
Yi  Yˆi  uˆi
• in terms of the PRF Yi can be written as
Yi  E (Yi | X i )  ui
• Given the SRF is an approximation to the PRF
can we make this approximation as close as
possible?
Y
SRF : Yˆi  ˆ  ˆX i
Yi
Yi
ui ûi PRF : E (Y | X i )    X i
Yˆi
Yˆi
E(Y|Xi) E(Y|Xi)

X
Xi
Ordinary Least Squares (OLS)
• OLS obtains the estimators ̂ and ˆ
minimising the sum of squared residuals
(RSS) with respect to  and  :
N N
RSS   ui   (Yi    X i )
ˆ 2
ˆ ˆ 2

i 1 i 1
• Partially differentiate RSS w.r.t. the
coefficients
Ordinary Least Squares (OLS)
• The first order conditions are:

RSS N
• (1)  2 (Yi  ˆ  ˆX i )  0
ˆ i 1

RSS N
• (2)  2 (Yi  ˆ  ˆX i )( X i )  0
ˆ i 1
Ordinary Least Squares (OLS)
• Solving (1) and (2) simultaneously gives
N

(X i  X )(Yi  Y )
̂  i 1
N

 i
( X
i 1
 X ) 2

• and ˆ  Y  ˆX
• where Y and X are the sample means
Ordinary Least Squares (OLS)
• Example: Melbourne house prices
• Y price of house in A$’000
• X distance of house from GPO in
kilometres
• A=area of house in square metres
• Interpret the results
The EVIEWS regression results are:
=============================================================
LS // Dependent Variable is Y
Date: 02/06/98 Time: 13:45
Sample: 1 27
Included observations: 27
=============================================================
Variable Coefficient Std. Error t-Statistic Prob.
=============================================================
C 272.8357 15.96022 17.09473 0.0000
X -5.303697 1.138680 -4.657759 0.0001
=============================================================
R-squared 0.464608 Mean dependent var 213.1593
Adjusted R-squared 0.443192 S.D. dependent var 66.27232
S.E. of regression 49.45213 Akaike info criterion 7.873197
Sum squared resid 61137.82 Schwarz criterion 7.969185
Log likelihood -142.5995 F-statistic 21.69471
Durbin-Watson stat 0.863751 Prob(F-statistic) 0.000090
=============================================================
H O U S IN G P R IC E S ($ 0 0 0 )
500

400

300

200

100
0 10 20 30 40

DISTANCE FROM GPO


Ordinary Least Squares (OLS)
• What type of data is this?
• Calculate the missing values of Y-hat and
u-hat in the table
Yˆ  ˆ  ˆX
i i

Yˆi  272.8357  5.303697 X i


Yˆi  272.8357  5.303697(1.4)
Yˆ  265.4105
i
Ordinary Least Squares (OLS)
Yi  Yˆi  uˆi
uˆ  Y  Yˆ
i i i

uˆi  210.2  265.4


uˆi  55.2
Y2  300.4; Yˆ2  260.6; uˆ2  39.8
Y  340.6; Yˆ  260.6; uˆ  80.0
3 3 3
• CHECK THE ANSWERS YOURSELVES!
Summary and conclusions
• PRF vs SRF
• OLS methodology
• Next lecture
– Gujarati p65 – 76 (Classical Assumptions)
– Gujarati p107 – 112 (Normality Assumption)

You might also like