PSC 200: Applied Data Analysis
Fall 2008
Lecture: 10:00-10:50 Mon, Wed, Gavet 301
Labs: Thursdays 2:00 – 3:15 (Hylan 307) and Fridays 10:00-10:50 (Gavet 244)
Class website: http://mail.rochester.edu/~mksr/PSC200.htm
Prof. Mark Kayser
mark.kayser@rochester.edu
Harkness 320B
OH: Wednesdays
2:30-4:30
Adam Ramey (TA)
adam.ramey@rochester.edu
Harkness 334
OH: Tuesdays
1:45-2:45
Overview: This course offers an introduction to empirical research methods in political science. By the end of the semester, students should have a better acquaintance with the type of empirical work done by most political scientists (and other social scientist) and the ability to understand and critique it.
Readings are from the following books:
Required:
On library reserve for reference:
Grading: Grades will be based on three in-class exams, multiple data analysis exercises, several brief homework assignments, and a final data analysis/paper. Unless otherwise indicated, each assignment is due one week from the day it is assigned. Assignments must be turned in on paper (not emailed) and properly formatted. Grades will be weighted as follows: exams 15% each; data analyses and homework assignments 30% (collectively); final data analysis/paper 15%; participation in weekly labs 10%. The lowest grade on a homework or data analysis assignment will be dropped with no questions asked. Use this privilege wisely; it is intended for unforeseen circumstances, accidents, and illnesses. Late assignments are downgraded by one grade level for each day they are late, e.g. B+ to B and will not be accepted after seven days. Students are responsible for delivering their homework, in hardcopy, to the TA. Emailed attachments will not be accepted. Grade appeals should be submitted to the appropriate TA as a type-written memo specifying the question(s) in doubt and grounds for the appeal.
Make-up Exams: Students are expected to take all exams at the announced times. A single make-up exam will be scheduled for students with documented extenuating circumstances such as personal illness requiring medical attention. Athletes whose competition schedule prevents them from taking an exam should arrange for their coaches to administer the exam. Undocumented absences earn a zero.
Recitations: The teaching assistant will hold weekly recitations in computer labs to reinforce concepts from the class, assist with software questions, review homework, and provide general guidance. Attendance is mandatory.
Readings: The readings are shown below. Readings not from the class texts are available
on JSTOR (www.jstor.org) or via hyperlink
from the online version of this syllabus
(http://mail.rochester.edu/~mksr/PSC200.html).
They are provided as an example of how the methods you are learning are
used in actual research. Please be sure
to read them before class. The review
problems at the end of each chapter in Pollock are very helpful and may
occasionally be assigned as homework.
You may wish to do them regardless of whether they are assigned. The Agresti and Finlay book on reserve in the
library is a good supplementary resource.
Software: We use SPSS for the
most of our computer based analysis in this class. The menu-driven interface of this package
makes it appealing for students gaining their first introduction to data
analysis. If you have data analytic
ambitions that extend beyond this class, you will probably notice many of the
shortcomings of SPSS for intensive users.
In such a case, you might want to consider programs such as STATA (fast)
and R (flexible and free). Both your
professor and TA are happy to support you in your use of these other packages.
Academic Honesty: None of the assignments in this class are
collaborative. I encourage you to study
together and learn to use the software together. Assignments, however, are expected to
represent your individual effort. Copied
or plagiarized work will incur penalties consistent with the College’s policy
on academic honesty (http://www.rochester.edu/College/honesty/).
Syllabus: This syllabus may be altered during the semester to accommodate the learning pace of the class. It is the students’ responsibility to keep abreast of assignments and due dates by attending class monitoring the class website (http://mail.rochester.edu/~mksr/PSC200.html). I often post lecture notes online.
COURSE SCHEDULE:
Week 1. Introduction
Week 2. Concepts and Measurement
Readings:
Supplemental:
Homework 1 (assigned in
class)
Week 3-1. Descriptive Statistics
Readings:
Supplemental:
Week 3-2. Constructing Variables
Readings:
Supplemental:
1st Data Analysis. This
assignment will be described in detail in class.
Week 4-1. Forming Hypotheses
Readings:
Supplemental:
Week 4-2. Research Design: Experiments and Controlled
Comparisons
Readings:
Supplemental:
Homework 2 (assigned in class)
Week 5-1.
In-Class Review
Week 5-2.
Exam 1
Week 6-1. Assessing Hypotheses: Crosstabs & Means
Readings:
Supplemental:
Week 6-2. Controlling for a Third Variable
Readings:
Supplemental:
2nd Data Analysis assigned in class.
Week 7-1. z distributions, Confidence Intervals and
Inference
Readings:
Supplemental:
Week 7-2. t distributions and Inference with Sample
Proportions
Readings:
Supplemental:
Homework 2 assigned in class
Week 8-1. Review of Statistical Inference &
Probability Distributions
Week 8-2.
Tests of Significance
Readings:
Supplemental:
Week 9-1.
In-Class Review
Week 9-2.
Exam 2
10-1. Proportional Reduction of Error & Chi-sq
tests
Readings:
Supplemental:
Week 10-2. Correlation and Bivariate
Regression
Readings:
3rd Data Analysis:
assigned in class.
Week 11-1. Measures of Fit
Readings:
Supplemental:
Week 11-2. No
Class
Week 12-1:
Introduction to Multiple Regression
Readings:
Supplemental:
Final Data
Analysis: Multiple Regression. Assignment
will be handed out in class.
Week 12-2: OLS
Assumptions
Readings:
Week 13-1. Influential Observations
Readings:
Supplemental:
Week 13-2. Multicollinearity
Readings:
Week 14-1.
Model Specification
Week 14-2.
Non-linear Regression
Supplemental:
Week 15-1. In Class Review
Week 15-2. Exam 3
Final Data Analysis Due after Exam 3. Due date will be announced in class.
Does globalization
shrink or expand the welfare state? You
will evaluate the empirical support for both the efficiency (shrinking state)
and compensation (expanding state) hypotheses.