Introductory Econometrics: A Modern Approach (7e)

Chapter 7
Multiple Regression Analysis with
Qualitative Information

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 1
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (1 of 24)

• Qualitative Information
• Examples: gender, race, industry, region, rating grade...
• A way to incorporate qualitative information is to use dummy variables.
• They may appear as the dependent or as independent variables.
• A single dummy independent variable

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 2
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (2 of 24)

• Graphical Illustration

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 3
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (3 of 24)

• Dummy variable trap

• When using dummy variables, one category always has to be omitted:

• Alternatively, one could omit the intercept

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 4
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (4 of 24)

• Estimated wage equation with intercept shift
WAGE1.dta

• Does that mean that women are discriminated against?

• Not necessarily. Being female may be correlated with other produc-tivity
characteristics that have not been controlled for.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 5
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (5 of 24)

• Comparing means of subpopulations described by dummies

• Discussion
• It can easily be tested whether the difference in means is significant.
• The wage difference between men and women is larger if no other things are
controlled for; i.e. part of the difference is due to differences in education,
experience, and tenure between men and women.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 6
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (6 of 24)

• Further example: Effects of training grants on hours of training

JTRAIN.dta

• This is an example of program evaluation

• Treatment group (= grant receivers) vs. control group (= no grant)
• Is the effect of treatment on the outcome of interest causal? Counterfactuals!

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 7
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (7 of 24)

• Using dummy explanatory variables in equations for log(y)

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 8
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (8 of 24)

• Using dummy variables for multiple categories WAGE1.dta
• 1) Define membership in each category by a dummy variable
• 2) Leave out one category (which becomes the base category)

i.married#i.female

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 9
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (9 of 24)

• Incorporating ordinal information using dummy variables
• Example: City credit ratings and municipal bond interest rates

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 10
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (10 of 24)

• Interactions involving dummy variables
• Allowing for different slopes

• Interesting hypothesis

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 11
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (11 of 24)

• Graphical illustration

Interacting both the intercept

and the slope with the female
dummy enables one to model
completely independent wage
equations for men and women.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 12
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (12 of 24)

• Estimated wage equation with interaction term

No evidence against hypothesis Does this mean that there is no significant evidence of lower pay for
that the return to education is women at the same levels of educ, exper, and tenure? No: this is only
the same for men and women. the effect for educ = 0. To answer the question one has to recenter the
interaction term, e.g. around educ = 12.5 (= average education).

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 13
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (13 of 24)

• Testing for differences in regression functions across groups
• Unrestricted model (contains full set of interactions)

• Restricted model (same regression for both groups)

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 14
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (14 of 24)

• Null hypothesis

GPA3.dta
• Estimation of the unrestricted model

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 15
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (15 of 24)

• Joint test with F-statistic

• Alternative way to compute F-statistic in the given case

• Run separate regressions for men and for women; the unrestricted SSR is given
by the sum of the SSR of these two regressions.
• Run regression for the restricted model and store SSR.
• If the test is computed in this way it is called the Chow-Test.
• Important: Test assumes a constant error variance across groups.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 16
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (16 of 24)

• A Binary dependent variable: the linear probability model
• Linear regression when the dependent variable is binary

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 17
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (17 of 24)

• Example: Labor force participation of married women MROZ.dta

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 18
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (18 of 24)

• Example: Female labor participation of married women (cont.)
Graph for nwifeinc=50, exper=5, age=30,
kindslt6=1, and kidsge6=0

The maximum level of education in the

sample is educ=17. For the given case,
this leads to a predicted probability to
be in the labor force of about 50%.

There is a negative predicted

probability, but no problem because no
woman in the sample has educ < 5.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 19
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (19 of 24)

• Disadvantages of the linear probability model
• Predicted probabilities may be larger than one or smaller than zero.
• Marginal probability effects sometimes logically impossible.
• The linear probability model is necessarily heteroskedastic.
• Thus, heteroskedasticity consistent standard errors need to be computed.

• Advantages of the linear probability model

• Easy estimation and interpretation
• Estimated effects and predictions are often reasonably good in practice.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 20
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (20 of 24)

• More on policy analysis and program evaluation
• Example: Effect of job training grants on worker productivity

• Treatment group: grant receivers, Control group: firms that received no grant

• Grants were given on a first-come, first-served basis. This is not the same as giving them out
randomly. It might be the case that firms with less productive workers saw an opportunity to
improve productivity and applied first.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 21
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (21 of 24)

• Addressing the problem of self-selection

• We include x1 through xj to account for the possibility that the

treatment (w) is not randomly assigned.
• For example, children eligible for a program like Head Start participate
based on parental decisions. We thus need to control for things like
family background and structure to get closer to random assignment
into the treatment (participates in Head Start) and control (does not
participate) groups.
© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 22
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (22 of 24)

• Addressing the problem of self-selection continued (cont.)
• Consider the simple regression:

• We need to make the strong assumption that w is independent of

[y(0),y(1)]. In other words, treatment is randomly assigned.
• A more convincing case is to include covariates x1 through xj

• Now we assume that w is independent of [y(0),y(1)] conditional upon

x1 through xj.
• This is known as regression adjustment and allows us to adjust for differences
across units in estimating the causal effect of the treatment.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 23
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (23 of 24)

• Relaxing the assumption of a constant treatment effect
• We can allow the treatment effect to vary across observations and instead
estimate the average treatment effect (ATE)

• The estimated coefficient on w will be the ATE.

• The regression that allows individual treatment effects to vary is
known as the unrestricted regression adjustment (URA).
• By contrast, a restricted regression adjustment (RRA) forces the
treatment effect to be identical across individuals.
© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 24
Introductory Econometrics: A Modern Approach (7e)

Multiple Regression Analysis with Qualitative Information (24 of 24)

• An alternative method for obtaining the URA ATE

• Now for every unit in the sample, predict yi(0) and yi(1) regardless
of whether the unit is in the control or treatment groups.
• Use these predicted values to compute the ATE as:

• Though this yields the same ATE as running the regression with
interaction terms, computing a standard error by hand can be tricky.

© 2020 Cengage. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a
password-protected website or school-approved learning management system for classroom use. 25