Have a question?
Message sent Close

Introduction To Econometrics (ECON 139) Answers

Instructor
Sandra Watson
0
0 reviews
  • Description
  • Full Document
Blur-Preview

Duke University

Introduction to Econometrics (ECON 139)

Book solution “Introduction to Econometrics”, James H. Stock; Mark W. Watson – Answers to concept questions

Chapter 1
1.1 The experiment that you design should have one or more treatment groups and a control
group; for example, one treatment could be studying for four hours, and the control
would be not studying (no treatment). Students would be randomly assigned to the
treatment and control groups, and the causal effect of hours of study on midterm
performance would be estimated by comparing the average midterm grades for each of
the treatment groups to that of the control group. The largest impediment is to ensure
that the students in the different treatment groups spend the correct number of hours
studying. How can you make sure that the students in the control group do not study at
all, since that might jeopardize their grade? How can you make sure that all students in
the treatment group actually study for four hours?
1.2 This experiment needs the same ingredients as the experiment in the previous question:
treatment and control groups, random assignment, and a procedure for analyzing the
resulting experimental data. Here there are two treatment levels: not wearing a seatbelt
(the control group) and wearing a seatbelt (the treated group). These treatments should
be applied over a specified period of time, such as the next year. The effect of seat belt
use on traffic fatalities could be estimated as the difference between fatality rates in the
control and treatment group. One impediment to this study is ensuring that participants
follow the treatment (do or do not wear a seat belt). More importantly, this study raises
serious ethical concerns because it instructs participants to engage in known unsafe
behavior (not wearing a seatbelt).
1.3
a. You will need to specify the treatment(s) and randomization method, as in Questions
1.1 and 1.2.
b. One such cross-sectional data set would consist of a number of different firms with
the observations collected at the same point in time. For example, the data set might
contain data on training levels and average labor productivity for 100 different firms
Stock/Watson – Introduction to Econometrics – 3rd Updated Edition – Review the Concepts
during 2010. Chapter 4 introduces linear regression as a way to estimate causal
effects using cross-sectional data.
c. The time series data would consist of observations for a single firm collected at
different points in time. For example, the data set might contain data on training
levels and average labor productivity for the firm for each year between 1960 and
2010. Chapter 15 discusses how linear regression can be used to estimate causal
effects using time series data.
d. Panel data would consist of observations from different firms, each observed at
different points in time. For example, the data might consist of training levels and
average labor productivity for 100 different firms, with data on each firm in 1990,
2000, and 2010. Chapter 10 discusses how linear regression can be used to estimate
causal effects using panel data.

PREVIEW

 

Introduction To Econometrics (ECON 139) Answers

NOTE: Please check the details before purchasing the document.

error: