Document 13234917

advertisement
 Quantitative Methods in International Relations
SIS 806
Fall 2014
Class Meetings: F 11:45a – 2:25p (SIS 348)
Instructor: Austin Hart
Email: ahart@american.edu
Office: SIS 345
Office Hours: Th 3:00p – 6:00p (drop-in), and by appointment
Overview and Objectives
“Large-N” analysis – assessing relationships among variables over numerous observations – is
now a staple of international relations research. Engaging in and contributing to the field now
requires the ability to interpret the results of statistical analyses and to understand both their
implications and limitations. This course will train students to be critical consumers of empirical
research and capable producers of statistical analysis. By the end of the semester, you will be
able to recognize common sources of bias in empirical studies, and suggest appropriate remedies.
You will also learn to use statistical techniques to answer research questions on your own.
Students will learn (i) how to summarize and evaluate empirical relationships, (ii) how to make
appropriate statistical inference, and (iii) how to present statistical findings to a general audience.
Required Texts
There are two textbooks for this course. The first is The Fundamentals of Political Science
Research, 2nd Edition (Cambridge University Press) by Kellstedt and Whitten. The second is
Naked Statistics: Stripping the Dread from the Data (WW Norton) by Charles Wheelan. I will
post the supplemental readings on Blackboard. Complete the readings before class, and bring the
readings with you each week.
Background Knowledge
This course provides a rigorous introduction to statistical methods. In order to succeed, you need
a working knowledge of basic mathematics and statistical computing. Many of you will have
what you need after the “Math Boot Camp.” If you are unable to attend the boot camp, please let
me know so that I can direct you to a great set of resources. This is NOT a math class. It’s a stats
class. But math happens. Be ready for it when it does.
Assignments and Grading
Your grade will be determined by your performance on weekly problem sets (50%), a final exam
(25%), and an original research project (25%). Note that all written work must be formatted
professionally. Type everything out. Use plain language, and write in complete sentences. I will
distribute a Style Guide with templates for tables, charts, etc.
Statistical Computing
This course will use the statistical software package Stata. There are three ways to access Stata:
• Free: Connect via the Virtual Computing Lab (www.american.edu/vcl). Download the
VCL Client and access Stata from your personal computer, on or off campus, at any time.
Follow the installation instructions carefully.
• Recommended: Purchase a personal copy of Stata/IC. The 6-month license for students
costs $69. A perpetual license costs $189.
• Free: Use the campus computer labs. Stata is available on the U: drive on all university
computers.
Becoming proficient with Stata is an important and challenging part of this course. When you
have questions about Stata:
• Review sample exercises from class and the Stata guides on Blackboard
• Consult your classmates
• Search online
• Consult the UCLA IDRE website: http://www.ats.ucla.edu/stat/stata/
• Speak with me.
I will post datasets and code files on Blackboard. Be sure to save these files in a directory to
which you have access—on your own computer or on your university drive—so you do not lose
saved work after each session.
Academic Integrity
I have zero tolerance for scholastic dishonesty and will enforce American University policies on
academic integrity strictly. By registering for this course, you have acknowledged your
awareness of the Academic Integrity Code (http://www.american.edu/academics/integrity/), and
you are obliged to become familiar with your rights and responsibilities as defined by the Code.
Emergency Preparedness
In the event of a declared emergency, American University will implement a plan for meeting
the needs of all members of the university community. Should the university be required to
close for a period of time, we, as faculty and staff, are committed to ensuring that all aspects of
our educational programs will be delivered to our students. These may include altering and
extending the duration of the traditional term schedule to complete essential instruction in the
traditional format and/or use of distance instructional methods. Specific strategies will vary from
class to class, depending on the format of the course and the timing of the emergency. Faculty
will communicate class-specific information to students via AU e-mail and Blackboard, while
students must inform their faculty immediately of any absence due to illness. Students are
responsible for checking their AU e-mail regularly and keeping themselves informed of
emergencies. If such an event occurs, students should refer to the AU Web site (www. prepared.
american.edu) and the AU information line at (202) 885-1100 for general university-wide
information, as well as contact their faculty and/or respective dean’s office for course and
school/ college-specific information.
Course Schedule
I. The Empirical Approach to Understanding and Explanation
Week 1 (September 4): Logic of scientific inference
• Kellstedt & Whitten, Ch. 1.
• King, Keohane, & Verba (1994) Designing Social Inquiry, Ch. 1.
• Wheelan, Intro & Ch. 1.
• Brady et al. (2001) “Law and Data: The Butterfly Ballot Episode”
• Rule (1994) “Women’s Underrepresentation and Electoral Systems”
Week 2 (September 11): Causality; Operationalization
• Holland (1986) “Statistics and Causal Inference”
• Kellstedt & Whitten, Ch. 3 and 5.1-5.8
• Murnane & Willett (2011) Methods Matter, Ch. 3.
• Wheelan, Ch. 7
• Sambanis (2004) “What is Civil War?” 814-858. (READ QUICKLY)
II. Research Design
Week 3 (September 18): Randomized trials
• Kellstedt & Whitten, Ch. 4
• Angrist & Pischke (2014) Mastering ‘Metrics, Ch. 1
• Fisher (1935) The Design of Experiments, Ch. 1-12
• Campbell & Stanley (1963) Experimental and Quasi-Experimental Designs for Research, p. 1-34
• Milgram (1965) “Some Conditions of Obedience and Disobedience to Authority”
• Bhavnani (2009) “Do Electoral Quotas Work after They Are Withdrawn? Evidence from a
Natural Experiment in India”
Week 4 (September 25): Quasi-experimental & observational designs
• Rule (1994) “Women’s Underrepresentation and Electoral Systems”
• Campbell & Stanley, p. 34-43, 47-50
• Angrist & Pischke, Ch. 2
• Wheelan, Ch. 11, 13
• Campbell & Ross (1968) “The Connecticut Crackdown on Speeding”
• Maluccio & Flores (2004) “Impact Evaluation of a Conditional Cash Transfer Program”
Week 5 (October 2): Panel data and causality
• Green et al. (2001) “Dirty Pool”
• Ross (2008) “Oil, Islam, and Women”
• Lenz (2012) Follow the Leader? How Voters Respond to Politicians’ Policies and Performance,
Ch. 1-2
• Hart (2013) “Can Candidates Activate or Deactivate the Economic Vote? Evidence from Two
Mexican Elections.”
Week 6 (October 16): Design workshop day
III. Statistical Inference
Week 7 (October 23): Probability theory; Inference
• Kellstedt & Whitten, Ch. 6
• Wheelan, Ch. 5-6
Week 8 (October 30): Inference; Hypothesis testing
• Wheelan, Ch. 8-10
IV. Evaluating Empirical Relationships
Week 9 (November 6): Bivariate hypothesis tests, part 1
• Kellstedt & Whitten, Ch. 7
Week 10 (November 13): Bivariate hypothesis tests, part 2
• Kellstedt & Whitten, Ch. 8
• Wheelan, Ch. 11
Week 11 (November 20): Multivariate hypothesis tests
• Kellstedt & Whitten, Ch. 9-10
• Wheelan, Ch. 12
• Angrist & Pischke, Ch. 2
• Mutz (2010) “The Dog that Didn’t Bark: The Role of Canines in the 2008 Campaign”
Week 12 (November 24): Research workshop
Week 13 (December 4): Final Exam
DECEMBER 11: Final paper due by 5:00p EST
Download