0% found this document useful (0 votes)
231 views

Lecture 5 - Functional Forms of Linear Regression Models - Lin-Log Model

The lin-log model relates a linear dependent variable to the log of an independent variable. It estimates the absolute change in the dependent variable for a percentage change in the independent variable. An example uses data on household expenditures to model the share of food spending (dependent variable) as a function of the log of total household expenditures (independent variable), supporting Engel's hypothesis that the food spending share decreases as total expenditures increase.

Uploaded by

anjali
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
0% found this document useful (0 votes)
231 views

Lecture 5 - Functional Forms of Linear Regression Models - Lin-Log Model

The lin-log model relates a linear dependent variable to the log of an independent variable. It estimates the absolute change in the dependent variable for a percentage change in the independent variable. An example uses data on household expenditures to model the share of food spending (dependent variable) as a function of the log of total household expenditures (independent variable), supporting Engel's hypothesis that the food spending share decreases as total expenditures increase.

Uploaded by

anjali
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/ 6

Functional Forms of Linear Regression

Models

1
1
Lin-Log Model
• In this model, the dependent variable is in linear form while the independent variable
 

is in log form.
• This model is used when we are interested in finding the absolute change in the
dependent variable for a percentage change in the independent variable.

The Lin-Log Regression Model is of the form:

In discrete terms, therefore

2
2
Now, if we want the relative change in X percentage terms, then we need to evaluate:
 

Hence, if we want to find out the absolute change in Y due to a percentage change in X,
then we need to divide the slope coefficient i.e. by 100.

• The Lin-Log Model has been used in Engel Expenditure Functions the share of
expenditure on food decreases as total expenditure increases. In this case, we want to
measure how much the expenditure on food changes in absolute terms, if total
expenditure increases by 1%.

3
3
Illustration of Lin-Log Model
 

• The dataset is from Econometrics by Example: Gujarati

• It contains data on food consumed at home (fdho) and total household expenditure
(expend), both in dollars, for 869 US households in 1995.

• The dependent variable is sfdho: share of food expenditure in total expenditure

• The independent variable is expend: total expenditure

• sfdho = f(expend)

• The functional form of the regression model is:

4
4
Illustration of Lin-Log Model

5
5
Interpretation

• All the estimated coefficients are individually highly statistically significant.

• The interpretation of the slope coefficient of about -0.08 is that if total expenditure
increases by 1%, on average, the share of expenditure on food and non-alcoholic
beverages goes down by about 0.0008 units, thus supporting the Engel’s hypothesis.

• Alternatively, the slope coefficient can be interpreted as: If total expenditure


increases by 100%, on average, the share of expenditure on food and nonalcoholic
beverages goes down by about 0.08 units.

6
6

You might also like