Scribd
Upload
472 views

Chapter 4-Functional Forms of Regression Model

1. The document discusses different functional forms of regression models including log-log, semilog (lin-log and log-lin), and reciprocal models. 2. The log-log model expresses the dependent and independent variables as natural logarithms and the slope coefficient directly measures elasticity. 3. The lin-log and log-lin semilog models have either the dependent or independent variable in logarithmic form. The log-lin model shows the percentage change in the dependent variable from a one-unit increase in the independent variable. 4. Reciprocal models take the reciprocal of one of the variables. They are useful when the dependent variable increases at a decreasing rate as the independent variable increases.

Uploaded by

Muliana Samsi
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
472 views

Chapter 4-Functional Forms of Regression Model

1. The document discusses different functional forms of regression models including log-log, semilog (lin-log and log-lin), and reciprocal models. 2. The log-log model expresses the dependent and independent variables as natural logarithms and the slope coefficient directly measures elasticity. 3. The lin-log and log-lin semilog models have either the dependent or independent variable in logarithmic form. The log-lin model shows the percentage change in the dependent variable from a one-unit increase in the independent variable. 4. Reciprocal models take the reciprocal of one of the variables. They are useful when the dependent variable increases at a decreasing rate as the independent variable increases.

Uploaded by

Muliana Samsi
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

CHAPTER 4

FUNCTIONAL FORMS OF
REGRESSION MODEL

PREPARED BY:
DR. SITI MULIANA SAMSI
Common Mathematical Functions Used n
Predictive Econometrics Models
Types of Mathematical Functions:

Linear y = a + bx
Logarithmic y = ln(x)
Polynomial (2nd order) y = ax2 + bx + c
Polynomial (3rd order) y = ax3 + bx2 + dx + e
Power y = axb
Exponential y = abx
(the base of natural logarithms, e = 2.71828…is often used for the constant b)
Functional forms of regression models
We will discuss the following regression models:
1. The log – log model
2. Semilog models: lin-log and log-lin models
3. Reciprocal models
The special features of each model , when they are appropriate, and how they are estimated
The LOG – LOG model
 Consider the following model:
 which may be expressed alternatively as

(4.1)
 where ln=natural log (i.e. Log to the base e, and where e = 2.718)

(4.2)
 To obtain model which is linear in the parameters, denote α = lnβ1

(4.3)
The LOG – LOG model
   Y represents the quantity of commodity demanded and X its unit price, measures the
If
price elasticity of demand, a parameter of considerable economic interest
The LOG – LOG model
   the assumptions of the classical linear regression model are fulfilled, the parameters of
If
(4.3) can be estimated by the OLS method by letting

 The OLS estimators and obtained will be best linear unbiased estimators of and
respectively.
 One attractive feature of the log-log model, which has made it popular in applied work, is
that the slope coefficient measures elasticity of Y with respect to X:

 shows the percentage change in Y for a given (small) percentage change in X.


The LOG – LOG model
LOG -LIN model
  Population Regression Function (PRF) in case of log-lin model:

 where β1, β2 - population regression coefficients, - residual term.


 For sample data:
 where - OLS estimates for unknown population parameters, - estimate for
residual term.
 Take log from both sides:

 β2 shows: if value of X increases by 1 unit, Y mean increases by β2 *100%


LOG -LIN model
 How to measure the Growth rate: application of The LOG-LIN model
Economists, businesspeople, and governments are often interested in finding out
the rate of growth of certain economic variables, such as population, GDP, money
supply, employment, productivity, and trade deficit.
 Let have values Y0;Y1; ...., Yt, where t - time Suppose that we want to estimate
compound (i.e., over time) rate of growth of Y
LOG -LIN model
LOG -LIN model
LOG -LIN model
LIN-LOG model
LIN-LOG model

 Regression
  slope coefficient is =10359
 Interpretation: Increase in M2 by 1 percent, on average, leads to increase in GDP by 103.57 million
of euro .
Reciprocal model
Reciprocal model
Reciprocal model
Choice of Functional Form
Choice of Functional Form
Summary
Comparing two R²

You might also like