Dummy Variables: Nominal Scale

Dummy Variables
Four types of variables that one generally encounters in

empirical analysis:
These are: ratio scale, interval scale, ordinal scale, and
nominal scale.
The types of variables that we have encountered in the
preceding chapters were essentially ratio scale. But this
should not give the impression that regression models can deal
only with ratio scale variables. Regression models can also
handle other types of variables mentioned previously.
In this lecture, we consider models that may involve not only
ratio scale variables but also nominal scale variables. Such
variables are also known as indicator variables, categorical
variables, qualitative variables, or dummy variables.
THE NATURE OF DUMMY VARIABLES
In regression analysis the dependent variable, or regressand, is frequently
influenced not only by ratio scale variables (e.g., income, output, prices,
costs, height, temperature) but also by variables that are essentially
qualitative, or nominal scale, in nature, such as sex, race, color, religion,
nationality, geographical region, political upheavals, and party affiliation.
For example, holding all other factors constant, female workers are found to
earn less than their male counterparts or nonwhite workers are found to earn
less than whites. One way we could “quantify” such attributes is by
constructing artificial variables that take on values of 1 or 0, 1 indicating the
presence (or possession) of that attribute and 0 indicating the absence of
that attribute.
Variables that assume such 0 and 1 values are called dummy variables.
Example:
Suppose we want to find out if the average annual salary (AAS) of public school
teachers differs among the three geographical regions of the country.
Geographical regions are (1) Northeast and North Central, (2) South, (3) West.
If you take the simple arithmetic average of the average salaries of the teachers in
the three regions, you will find that these averages for the three regions are as
follows: $24,424.14 (Northeast and North Central), $22,894 (South), and
$26,158.62 (West). These numbers look different, but are they statistically
different from one another? There are various statistical techniques to compare
two or more mean values, which generally go by the name of analysis of
variance. But the same objective can be accomplished within the framework of
regression analysis.
To see this, consider the following model:
where Yi = (average) salary of public school teacher in state i

D2i = 1 if the state is in the Northeast or North Central
= 0 otherwise (i.e., in other regions of the country)
D3i = 1 if the state is in the South
= 0 otherwise (i.e., in other regions of the country)
Mean salary of public school teachers in the Northeast and North Central:
Mean salary of public school teachers in the South:
Mean salary of public school teachers in the West:
The “slope” coefficients β2 and β3 tell by how much the mean salaries of
teachers in the Northeast and North Central and in the South differ from the mean
salary of teachers in the West. But how do we know if these differences are
statistically significant?
Overall conclusion is that statistically the mean salaries of public
school teachers in the West and the Northeast and North Central are
about the same but the mean salary of teachers in the South is
statistically significantly lower by about $3265.
A caution is in order in interpreting these differences. The dummy

variables will simply point out the differences, if they exist, but they do
not suggest the reasons for the differences.
From the preceding discussion, it is clear that all one has to do is see if
the coefficients attached to the various dummy variables are
individually statistically significant. This example also shows how easy
it is to incorporate qualitative, or dummy regressors in the regression
models.
Caution in the Use of Dummy Variables
1. If a qualitative variable has m categories, introduce only (m − 1) dummy
variables. If you do not follow this rule, you will fall into what is called the
dummy variable trap.
2. The category for which no dummy variable is assigned is known as the
base, benchmark, control, comparison, reference, or omitted category.
And all comparisons are made in relation to the benchmark category.
3. The intercept value (β1) represents the mean value of the benchmark
category.
4. The coefficients attached to the dummy variables are known as the
differential intercept coefficients because they tell by how much the
value of the intercept that receives the value of 1 differs from the intercept
coefficient of the benchmark category.
5. If a qualitative variable has more than one category, as in our illustrative
example, the choice of the benchmark category is strictly up to the
researcher.
6. There is a way to circumvent this trap by introducing as many dummy
variables as the number of categories of that variable, provided we do not
introduce the intercept in such a model. Thus, if we drop the intercept term
and consider the following model,
β1 = mean salary of teachers in the West

β2 = mean salary of teachers in the Northeast and North Central.
β3 = mean salary of teachers in the South.
In other words, with the intercept suppressed, and allowing a dummy
variable for each category, we obtain directly the mean values of the
various categories.
Which is a better method of introducing a dummy variable: (1) introduce
a dummy for each category and omit the intercept term or (2) include
the intercept term and introduce only (m − 1) dummies, where m is the
number of categories of the dummy variable? As Kennedy notes:
‘Most researchers find the equation with an intercept more convenient

because it allows them to address more easily the questions in which they
usually have the most interest, namely, whether or not the categorization
makes a difference, and if so, by how much. If the categorization does
make a difference, by how much is measured directly by the dummy
variable coefficient estimates.’
ANOVA MODELS WITH TWO QUALITATIVE VARIABLES
EXAMPLE:
Hourly Wages in relation to Marital status and region of residence.

From a sample of 528 persons in May 1985, the following regression results
were obtained:
ˆYi = 8.8148 + 1.0997D2i − 1.6729D3i
se = (0.4015) (0.4642) (0.4854)
t = (21.9528) (2.3688) (−3.4462) (9.3.1)
(0.0000)* (0.0182)* (0.0006)*
R2 = 0.0322
where Y = hourly wage ($)
D2 = married status, 1 = married, 0 = otherwise
D3 = region of residence; 1 = South, 0 = otherwise
In this example we have two qualitative regressors, each with two categories.
Hence we have assigned a single dummy variable for each category.
Which is the benchmark category here?
unmarried persons who do not live in the South are the omitted category.
Therefore, all comparisons are made in relation to this group. The mean
hourly wage in this benchmark is about $8.81. Compared with this, the
average hourly wage of those who are married is higher by about $1.10, for
an actual average wage of $9.91 ( = 8.81 + 1.10). By contrast, for those
who live in the South, the average hourly wage is lower by about $1.67, for
an actual average hourly wage of $7.14.
The point to note about this example is this:
Once you go beyond one qualitative variable, you have to pay close
attention to the category that is treated as the base category, since all
comparisons are made in relation to that category. This is especially
important when you have several qualitative regressors, each with several
categories.
REGRESSION WITH A MIXTURE OF QUANTITATIVE AND
QUALITATIVE REGRESSORS: THE ANCOVA MODELS
In most economic research a regression model contains some explanatory

variables that are quantitative and some that are qualitative. Regression
models containing an admixture of quantitative and qualitative variables are
called analysis of covariance (ANCOVA) models.
ANCOVA models are an extension of the ANOVA models in that they

provide a method of statistically controlling the effects of quantitative
regressors, called covariates or control variables, in a model that includes
both quantitative and qualitative, or dummy, regressors.
let us reconsider earlier example maintaining that the average salary of
public school teachers may not be different in the three regions if we take
into account any variables that cannot be standardized across the regions.
Consider, for example, the variable expenditure on public schools by local
authorities, as public education is primarily a local and state question. To see
if this is the case, we develop the following model:
Teacher’s salary in relation to region and spending on public school per pupil
The results of the model (9.4.1) are as follows:
Y^i = 13,269.11 − 1673.514D2i − 1144.157D3i + 3.2889Xi
se = (1395.056) (801.1703) (861.1182) (0.3176)
t = (9.5115)* (−2.0889)* (−1.3286)** (10.3539)*
R2 = 0.7266
INTERACTION EFFECTS USING DUMMY VARIABLES
Consider the following model:
where Y = hourly wage in dollars

X = education (years of schooling)
D2 = 1 if female, 0 otherwise
D3 = 1 if nonwhite, 0 otherwise
This model implicitly assumes that the differential effect of the gender
dummy D2 is constant across the two categories of race and the differential
effect of the race dummy D3 is also constant across the two sexes. That is
to say, if the mean salary is higher for males than for females, this is so
whether they are nonwhite or not. Likewise, if, say, nonwhite have lower
mean wages, this is so whether they are females or males.
But in many applications such an assumption may be untenable. A female
nonwhite may earn lower wages than a male nonwhite. In other words,
there may be interaction between the two qualitative variables D2 and D3.
Therefore their effect on mean Y may not be simply Additive but multiplicative
as well, as in the following model.
which is the mean hourly wage function for female nonwhite workers.
Observe that
α2 = differential effect of being a female
α3 = differential effect of being a nonwhite
α4 = differential effect of being a female nonwhite
which shows that the mean hourly wages of female nonwhite is different
(by α4) from the mean hourly wages of females or nonwhite Hispanics. If,
for instance, all the three differential dummy coefficients are negative, this
would imply that female nonwhite workers earn much lower mean hourly
wages than female or nonwhite workers as compared with the base
category, which in the present example is male white.
EXAMPLE 9.5
AVERAGE HOURLY EARNINGS IN RELATION TO EDUCATION,
GENDER, AND RACE
Let us first present the regression results based on model without interaction
term. we obtained the following results:
Yi = −0.2610 − 2.3606D2i − 1.7327D3i + 0.8028Xi
t = (−0.2357)** (−5.4873)* (−2.1803)* (9.9094)*
R2 = 0.2032 n = 528
The results show, ceteris paribus, the average hourly earnings of females are
lower by about $2.36, and the average hourly earnings of nonwhite workers are
also lower by about $1.73.
We now consider the results of model which includes the interaction dummy.
Yi =−0.26100 −2.3606D2i −1.7327D3i +2.1289D2iD3i +0.8028Xi
t = (−0.2357)** (−5.4873)* (−2.1803)* (1.7420)** (9.9095)**
R2 = 0.2032 n = 528
Holding the level of education constant, if you add the three dummy coefficients
you will obtain: −1.964 (=−2.3605 − 1.7327 + 2.1289), which means that mean
hourly wages of nonwhite female workers is lower by about $1.96, which is
between the value of −2.3605 (gender difference alone) and −1.7327 (race
difference alone).
THE USE OF DUMMY VARIABLES IN SEASONAL ANALYSIS
The process of removing the seasonal component from a time series is

known as deseasonalization or seasonal adjustment, and the time series
thus obtained is called the deseasonalized, or seasonally adjusted, time
series. Important economic time series, such as the unemployment rate,
the consumer price index (CPI), the producer’s price index (PPI), and the
index of industrial production, are usually published in seasonally
adjusted form.
Consider the model:
where Yt = sales (in thousands) and the D’s are the dummies, taking a value
of 1 in the relevant quarter and 0 otherwise.
How do we obtain the deseasonalized time series of sales? This can be
done easily. You estimate the values of Y from model for each observation
and subtract them from the actual values of Y, that is, you obtain (Yt − ˆYt )
which are simply the residuals from the regression.
What do these residuals represent? They represent the remaining
components of the sales time series, namely, the trend, cycle, and random
components.

Dummy Variables: Nominal Scale

Uploaded by

Copyright:

Available Formats

Dummy Variables: Nominal Scale

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Dummy Variables: Nominal Scale

Uploaded by

Copyright:

Available Formats

Dummy Variables

Four types of variables that one generally encounters in

where Yi = (average) salary of public school teacher in state i

Mean salary of public school teachers in the South:

Mean salary of public school teachers in the West:

A caution is in order in interpreting these differences. The dummy

β1 = mean salary of teachers in the West

‘Most researchers find the equation with an intercept more convenient

Hourly Wages in relation to Marital status and region of residence.

The point to note about this example is this:

In most economic research a regression model contains some explanatory

ANCOVA models are an extension of the ANOVA models in that they

Consider the following model:

where Y = hourly wage in dollars

The process of removing the seasonal component from a time series is

You might also like