Scribd
Upload
372 views

Lecture 6 - Functional Forms of Linear Regression Models - Reciprocal Model

The document discusses three cases of reciprocal linear regression models: 1) Slopes are negative as the independent variable increases and the dependent variable approaches an asymptotic limit. 2) Slopes are positive as the independent variable increases and the dependent variable approaches an asymptotic limit. 3) Slopes are positive, the dependent variable approaches an asymptotic limit, and there is a threshold value below which the dependent variable is zero. The document provides examples of applications for each case and illustrates a reciprocal model that fits wage and unemployment rate data better than a linear model.

Uploaded by

anjali
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
372 views

Lecture 6 - Functional Forms of Linear Regression Models - Reciprocal Model

The document discusses three cases of reciprocal linear regression models: 1) Slopes are negative as the independent variable increases and the dependent variable approaches an asymptotic limit. 2) Slopes are positive as the independent variable increases and the dependent variable approaches an asymptotic limit. 3) Slopes are positive, the dependent variable approaches an asymptotic limit, and there is a threshold value below which the dependent variable is zero. The document provides examples of applications for each case and illustrates a reciprocal model that fits wage and unemployment rate data better than a linear model.

Uploaded by

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

Functional Forms of Linear Regression

Models

1
1
Reciprocal Model
• Models of the following type are known as Reciprocal Models:
 

• The model is non-linear in X because it enters the model inversely or reciprocally.


But it is a linear regression model because the parameters are linear

• The key feature of this model is that as X increases indefinitely, the term approaches
zero and Y approaches the limiting or asymptotic value of . Therefore, reciprocal
models have built into them an asymptote or limit value that the dependent variable
will take when the value of the X variable increases indefinitely.

• The slope of the PRL is

2
2
Likely Shapes of Reciprocal Model
 

Case I: and

• As
• Slope is negative

Application:
If we let Y stand for the average fixed cost (AFC) of production, that is, the total fixed
cost divided by the output, and X for the output, then as economic theory shows, AFC
declines continuously as the output increases (because the fixed cost is spread over a
larger number of units) and eventually becomes asymptotic at level .

3
3
Case II: and
 

• As
• Slope is positive
• If Y = 0,
Application:
• An important application of Case II is the Engel expenditure curve which relates a
consumer’s expenditure on a commodity to his or her total expenditure or income.
• If Y denotes expenditure on a commodity and X the total income, then certain commodities
have these features:
(1) There is some critical or threshold level of income below which the commodity is not
purchased (e.g., an automobile). In the figure, this threshold level of income is at the level .
(2) There is a satiety level of consumption beyond which the consumer will not go no matter
how high the income (even millionaires do not generally own more than two or three cars at a
time). This level is nothing but the asymptote shown in the figure.
For such commodities, the reciprocal model of is the most appropriate.
4
4
 

Case III: and

• As which is negative
• Slope is positive
• If Y = 0,

Application:
• An important application of Case III is the Phillips Curve which shows an inverse
relationship between change in inflation (proxied by change in money wages) and the
unemployment rate.
• is the natural rate of unemployment.
• indicates the asymptotic floor for wage change

5
5
Illustration
• Dataset on percent change in the index of hourly earnings (Y) and the civilian
unemployment rate (X) for the United States for the years 1958 to 1969.

6
6
Illustration
• The Regression Equation is given by:

7
7
If we had fitted a Linear Model

8
8
Linear Model
• The Regression Equation in case of the linear model is given by:

9
9
Comparison of the two models

• In the linear model, the slope coefficient is negative, for the higher the
unemployment rate is, the lower the rate of growth of earnings will be, ceteris
paribus.

• In the reciprocal model, however, the slope coefficient is positive, which should be
the case because the X variable enters inversely (two negatives make one positive).
In other words, a positive slope in the reciprocal model is analogous to the negative
slope in the linear model.

10
10
Comparison of the two models
 

• The linear model suggests that as the unemployment rate increases by 1 percentage
point, on the average, the percentage point change in the earnings is a constant
amount of -0.79 no matter at what X we measure it.

• On the other hand, in the reciprocal model the percentage point rate of change in the
earnings is not constant, but rather depends on at what level of X (i.e., the
unemployment rate) the change is measured.

• Since the dependent variable in the two models is the same, we can compare the two
values. The for the reciprocal model is higher than that for the linear model,
suggesting that the former model fits the data better than the latter model.

11
11

You might also like