TIME SERIES ANALYSIS (POLS 502)
Course Outline
Required Texts
Grade Requirements
Course Calendar
 
FALL 
 2003  
INSTRUCTOR  Ruhil OFFICE 1147 BSB
PHONE (312) 413-7274 OFFICE HOURS By Appointment or Luck
CLASS TIME Monday:  6:00-8:30 CLASS MEETS IN 4133 BSB

Course Overview
This is an advanced course in statistics for the social sciences, with particular emphasis on studying processes and events as they unfold over time. In particular, you will wrestle with the rudiments of 
1. Pure time-series analyses (Box-Jenkins/ARIMA modeling, distributed-lag models, Vector autoregression (VAR), and Cointegration);
2. Pooled cross-sectional time-series analysis;
3. Panel data analysis; and
4. Survival analysis (also known as duration, hazard, or event history models). 

Rapid theoretical advances in political science research, the accumulation of reliable temporal data, the abundance of user-friendly statistical packages (for e.g., RATS; STATA; SPSS; LIMDEP; and EVIEWS), and a yen to minimize slippage between theory building and theory testing are forcing political scientists to recognize the shortcomings of static models. However, those who recognize the limitations (and, more important, the misspecification) of static models are few and far in-between. Consequently, this course is your portal to the frontiers of empirical political science research. However, because frontiers are by definition challenging, generally inhospitable domains, be prepared to put in tremendous effort if you wish to master the material. 

If you have any conditions or challenges that may make it difficult for you to meet the requirements of this course or that may leadyou to require extra time on assignments, let me know so that we can make the necessary arrangements.

Texts and Other Requirements
  REQUIRED TEXTS
 
Carefully work through the assigned material before coming to class. You will have to go over the material after class as well to ensure full comprehension. Let me know if you get lost in the material. 

The following texts are mandatory purchases for this course. 
• Allison, Paul D. 1984. Event History Analysis: Regression for Longitudinal Event Data. Newbury Park, CA: Sage Publications.
• Box-Steffensmeier, Janet M., and Bradford Jones. 2000. Timing and Political Change: Event History Analysis in Political Science. Ann Arbor: University of Michigan Press. (Unpublished; see me)
• McCleary, Richard, and Richard A. Hay. 1980. Applied Time Series Analysis for the Social Sciences. Beverly Hills, CA: Sage Publications.
• Ostrom, Charles W. 1978. Time Series Analysis: Regression Techniques. Newbury Park, NJ: Sage Publications.

I will assign other readings that will be available to you either in an electronic or in a hardcopy format.  For e.g., a synopsis of Engle & Granger's work on Autoregressive Conditional Heteroscedasticity and Cointegration, respectively. 

You must hold an active on-campus or off-campus email account. I will broadcast answer keys, handouts, and other relevant data via email since it is the speediest mode of communication. In due course of time the website for the course will be up and running and I hope you will utilize this resource as well since I will rely on applets to complement standard instructional technology – i.e., the chalk-and-blackboard. The URL for the website, when up and running, will be
http://www.uic.edu/classes/pols/pols502/pols502.html 
  RECOMMENDED TEXTS
There are also a growing number of online statistics texts that explain the innards of statistics in an easy-to-understand manner, using everyday language and examples. A few of the better online statistics texts are linked below. You may be surprised at their usefulness. 
Internet Glossary of Statistical Terms
Statistics at Square One
Introductory Statistics: Concepts, Models, and Applications
The Data Analysis Briefbook
Statistics: The Study of Stability in Variation
Introduction to Probability
Virtual Laboratories in Probability and Statistics
HyperStat Online
The Statistics Homepage
The Statlets at Duke
  DATA SETS AND CODEBOOKS
From time to time I will provide you with data sets and codebooks. These data will be used either for in-class  exercises and/or homework assignments. When these data are made available you will be able to download them from the relevant area in the Course Calendar (see below)

Grade Requirements
   GRADE COMPOSITION 
The grades you earn in this course are a function of your ability to work hard and to persevere. Practice, practice, and practice; there is no other way known to mankind that bestows thorough understanding of the mechanics underlying the seemingly oblique formulae or, for that matter, how statistical theories shed light on the substantive phenomena of interest to us, researchers. Thus, if you are not prepared to sell your soul to the devil and work hard, drop this course.

 Your grade will be composed of: 
(a)   short focused assignments wherein you will most likely be given a dataset and instructed to apply particular analytic techniques. Carrying equal weight, the assignments will jointly constitute 50 percent of your course grade. 

(b) A theoretically-motivated research paper on a topic of your choosing. However, the paper must involve either pure time series data or some other longitudinal data, with the analytical technique employed guided by the fit of the technique to the theoretical model and data specificities. Presumably this paper will be either a chapter or more in your dissertation or a paper that you hope to present at a conference. The paper contributes 50 percent to your overall grade. 

Note: Late assignments are unacceptable, regardless of the reason behind the delay. If you know you will be unable to make a deadline, obtain my prior approval. 

Course Calendar
Since the emphasis in this course is on giving you a thorough understanding of the rudiments of time-serial anayses, we shall set our own pace. Hence in the calendar below I do not demarcate specific portions of time during which particular topics will be covered. 

Course Introduction

  1. Box, George E. P. 1976. "Science and Statistics." Journal of the American Statistical Association 71(356):791-99.
  2. Box, George E. P. 1979. "Some Problems of Statistics and Everyday Life." Journal of the American Statistical Association 74(365):1-4.
  3. Isaac, Larry W. and Larry J. Griffin. 1989. "Ahistoricism in Time-Series Analyses of Historical Process: Critique, Redirection, and Illustrations from U.S. Labor History." American Sociological Review 54(6):873-90.
  4. Chapter 3 in Gujarati's Basic Econometrics
Ordinary Least Squares, Time Series Data and the Problem of Autocorrelation
• Gujarati, Chapter 12: 400-35
• Gray, Virginia. 1976. "Models of Comparative State Politics: A Comparison of Cross-Sectional and Time Series Analyses." American Journal of Political Science XX(2):235-56.
• Tucker, Harvey J. 1982. "It's About Time: The Use of Time in Cross-Sectional State Policy Research." American Journal of Political Science 26:176-96.
Gujarati Table 12.4

Pooled Cross-Sectional Time-Series Analysis 
• Beck, Nathaniel and Jonathan N. Katz. 1995. "What To Do (and Not To Do) With Time-Series Cross-Section Data." American Political Science Review 89(3):634-47. 
• Berk, Richard A., Donnie M. Hoffman, Judith E. Maki, David Rauma, and Herbert Wong. 1979. "Estimation Procedures for Pooled Cross-Sectional and Time-Series data." Evaluation Quarterly 3(3):385-410.
• Sayrs, Lois W. 1989. Pooled Time Series Analysis. Newbury Park, CA: Sage Publications.
• Stimson, James A. 1985. "Regression in Space and Time: A Statistical Essay." American Journal of Political Science 29(4):914-47.
LSDV Data & Do Files
Assignment 2

Event Count Models
• Beck, E. M. and Stewart E. Tolnay. 1995. "Analyzing Historical Count Data: Poisson and Negative Binomial Regression Models." Historical Methods 28:125-31.
• King, Gary. 1989. "Event Count Models for International Relations: Generalizations and Applications." International Studies Quarterly 33:123-47.
• Michener, Ron and Carla Tighe. 1992. "A Poisson Regression Model of Highway Fatalities." American Economic Review 82(2):452-6.
• Zorn, Christopher J. W. 1998. "An Analytic and Empirical Examination of Zero-Inflated and Hurdle Poisson Specifications." Sociological Methods and Research 26(February):368-400.
• Ruhil, Anirudh V. S. and Paul Teske. 2003. 

Event History Analysis
• Allison, Paul D. 1984. Event History Analysis: Regression for Longitudinal Event Data. Newbury Park, CA: Sage Publications.
• Beck, Nathaniel, Jonathan N. Katz, and Richard Tucker. 1998. "Taking Time Seriously: Time-Series--Cross-Section Analysis with a Binary Dependent Variable." American Journal of Political Science 42(4):1260-88.
• Berry, Frances S. and William D. Berry. 1990. "State Lottery Adoptions as Policy Innovations: An Event History Analysis." American Political Science Review 84(2):395-415.
• Box-Steffensmeier, Janet M. and Bradford S. Jones. 1997. "Time is of Essence: Event History Models in Political Science." American Journal of Political Science 41(4):1414-61.
• Hannan, Michael T. and Glenn R. Carroll. 1981. "Dynamics of Formal Political Structure: An Event-History Analysis." American Sociological Review 46(February):19-35.
• Raffalovich, L. and David Knoke. 1983. "Quantitative Methods for the Analysis of Historical Change." Historical Methods 16:149-54.
• Ruhil, Anirudh V. S. 2003. 
• Teachman, Jay D. and Mark D. Hayward. 1993. "Interpreting Hazard Rate Models." Sociological Methods and Research 21:340-71.
EHA Notes
Example Data (1)
Conflict.dta

Box-Jenkins/ARIMA Models
• McCleary, Richard, and Richard A. Hay. 1980. Applied Time Series Analysis for the Social Sciences. Beverly Hills, CA: Sage Publications.
• Mishler, William and Reginald S. Sheehan. 1993. "The Supreme Court as a Countermajoritarian Institution? The Impact of Public Opinion on Supreme Court Decisions." American Political Science Review 87(1):87-101.
• Morgan, David R. and John P. Pelissero. 1980. "Urban Policy: Does Political Structure Matter?" American Political Science Review 74(4):999-1006.
• Ruhil, Anirudh V. S. 2003. " " Urban Affairs Review 
• Norpoth, Helmut and Thomas Yantek. 1983. "Macroeconomic Conditions and Fluctuations of Presidential Popularity: The Question of Lagged Effects." American Journal of Political Science 27(4):785-807.
• Segal, Jeffrey and Helmut Norpoth. 1994. "Popular Influence on Supreme Court Decisions." American Political Science Review 88:711-24.
• Meffert, Michael F., Helmut Norpoth, and Anirudh V. S. Ruhil.  
Time-Series Example Data (1)
Box-Jenkins Data

Vector Autoregression, and Granger Causality
• To be announced

Cointegration, and Structural Breaks
• To be announced