Flores

Alejandro Quiroz Flores is Senior Lecturer (Associate Professor) at the Department of Government, University of Essex. He obtained his PhD in Politics at New York University. He specializes in Methodology and Political Economy. His work has appeared at Political Science Research and Methods, the British Journal of Political Science, and International Studies Quarterly, among others. He is the author of Ministerial Survival During Political and Cabinet Change: Foreign Affairs, Diplomacy and War, by Routledge (2016).

Course Content
This course will cover the statistical concepts and techniques that are used to model time. These models are also known as survival or event history models, and we use them to analyze the duration of time until some event happens—the termination of civil wars, the completion of a medical treatment, or the loss of political office, among other events.

The course will be divided into three main sections:
1. Continuous Time Duration Models: We will examine parametric duration models (exponential, Weibull, log-logistic, generalized gamma, etc.) and semi-parametric duration models (Cox model). In addition to seeing how these models are estimated and interpreted, we will also look at various residual-based diagnostic tests.

2. Discrete Time Duration Models: We will look at the connection between discrete time duration models and binary time-series-cross-section models. We will examine various ways to deal with time dependence, ongoing events, multiple events, and time varying covariates. Finally, we will take a look at Markov transition models.

3. More Advanced Duration Models: We will examine models dealing with competing risks, split populations, heterogeneity, frailty, and repeated events, as well as dyadic event history models for emulation and machine learning applications to survival analysis.

Course Objectives
The central objective of this course is to learn how to identify, and correctly apply, the statistical techniques appropriate to answering questions relating to time and duration. Students will be able to identify and classify data problems in survival analysis, define the appropriate survival function, distribution function, hazard function, relative hazard, and cumulative hazard, as well as summarize and interpret analyses of survival data using various estimators. By the end of the course, students should be quite adept at programming Stata to estimate and interpret a wide variety of different duration models.

Course Prerequisites
Students should already have some experience with the theory behind Maximum Likelihood Estimation. Some knowledge of basic calculus (differentiation and integration), exponents and logarithms, and Stata code will be helpful.

Background Reading
King, Gary, James Alt, Michael Laver & Nancy Burns. 1990. “A Unified Model of Cabinet Dissolution in Parliamentary Democracies.” American Journal of Political Science 34: 847-871.
Diermeier, Daniel and Randy T. Stevenson. 1999. “Cabinet Survival and Competing Risks.” American Journal of Political Science 43: 1051-1098.
Box-Steffensmeier, Janet M. & Christopher J. W. Zorn. 2001. “Duration Models and Proportional Hazards in Political Science.” American Journal of Political Science 45: 972-988.

Required Readings
Box-Steffensmeier, Janet & Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press.

Day 1: Introduction and preliminaries. Survival models and the analysis of time. Key probability concepts. Quantities of interest. Univariate and bivariate analyses.

Exercise:
• Identifying duration data in Stata.
• Univariate and bivariate analyses.

Reading:
• Box-Steffensmeier, Janet M. & Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. Ch. 1.
• Nagler, Jonathan. 1995. “Coding Style and Good Computing Practices.” The Political Methodologist 6.
• King, Gary, Michael Tomz & Jason Wittenberg. 2000. “Making the Most of Statistical Analyses: Improving Interpretation and Presentation.” American Journal of Political Science 44: 341-355.

Day 2: Continuous time duration models. Parametric models: exponential, Weibull, log-logistic, generalized gamma, etc. Estimation and interpretation.

Exercise:
• Correctly setting survival time in Stata.
• Estimation and interpretation of parametric duration models.
• Model selection.

Reading:
• Box-Steffensmeier, Janet M. & Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. Ch. 2-3.
• King, Gary, James Alt, Michael Laver & Nancy Burns. 1990. “A Unified Model of Cabinet Dissolution in Parliamentary Democracies.” American Journal of Political Science 34: 847-871.

Day 3: Continuous time duration models. Kaplan-Meier estimates. The Cox semi-parametric model. Proportionality. Dealing with tied data. Obtaining baseline hazard and survivor functions.

Exercise:
• Producing Kaplan-Meier estimates.
• Estimation and interpretation of the Cox model.
• Quantities of interest and marginal effects.

Reading:
• Box-Steffensmeier, Janet M. & Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. Ch. 4.

Day 4: Continuous time duration models. Typical problems in estimation. Diagnostic tests and solutions.

Exercise:
• Diagnostic tests and solutions.

Reading:
• Box-Steffensmeier, Janet M. & Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. Ch. 8.
• Keele, Luke. 2010. “Proportionally Difficult: Testing for Nonproportional Hazards in Cox Models.” Political Analysis 18 (2): 189-205.
• Licht, Amanda. 2011. “Change Comes with Time: Substantive Interpretation of Nonproportional Hazards in Event History Analysis.” Political Analysis 19 (2): 227-243.
• Park, Sunhee, and David J. Hendry. 2015. “Reassessing Schoenfeld Residual Tests of Proportional Hazards in Political Science Event History Analyses.” American Journal of Political Science 59 (4): 1072-1087.

Day 5: Discrete time duration models. The structure of survival data. The modeling of duration dependence in discrete models.

Exercise:
• Working with discrete survival data.
• Estimation and interpretation.

Reading:
• Box-Steffensmeier, Janet M. and Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. Ch. 5, 7.
• Beck, Nathaniel, Jonathan N. Katz, and Richard Tucker. 1998. “Taking Time Seriously: Time-Series Cross-Section with a Binary Dependent Variable.” American Journal of Political Science 42: 1260-1288.
• Box-Steffensmeier, Janet M. 1996. “A Dynamic Analysis of the Role of War Chests in Campaign Strategy.” American Journal of Political Science 40: 352-371.
• Oneal, John and Bruce Russett. 1999. “Assessing the Liberal Peace with Alternative Specifications: Trade Still Reduces Conflict.” Journal of Peace Research 36: 423-442.

Day 6: Discrete time duration models. Time-varying covariates. Complex spells of time. Markov transition models.

Exercise:
• Types of spells of time.
• Estimation and interpretation of Markov transition models.

Reading:
• Przeworski, Adam, Michael E. Alvarez, José Antonio Cheibub and Fernando Limongi. 2000. Democracy and Development: Political Institutions and Well-Being in the World, 1950-1990. New York: Cambridge University Press. Ch. 2.

Day 7: Competing risks models. Continuous time models and multinomial logit models.

Exercise:
• Estimation and interpretation.

Reading:
• Box-Steffensmeier, Janet M. and Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. pp. 166-182.
• Diermeier, Daniel and Randy T. Stevenson. 1999. “Cabinet Survival and Competing Risks.” American Journal of Political Science 43: 1051-1098.
• Gordon, Sandford. 2002. “Stochastic Dependence in Competing Risks.” American Journal of Political Science, 46: 200-217

Day 8: Unobserved heterogeneity and frailty models. Multiple failures and repeated events models.

Exercise:
• Estimation and interpretation.

Reading:
• Box-Steffensmeier, Janet M. and Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. Ch. 9-10 (155-166).
• Box-Steffensmeier, Janet M. and Christopher J. W. Zorn. 2002. “Duration Models for Repeated Events.” Journal of Politics 64: 1069-1094.
• Box-Steffensmeier, Janet M. and Suzanna De Boef. 2007. “Event Dependence and Heterogeneity in Duration Models: The Conditional Frailty Model.” Political Analysis.

Day 9: Advances in Survival Analysis: Dyadic Event History Models, Applied Machine Learning, and Bivariate Survival Models.

Exercise:
• Working with dyadic survival data.
• Estimation and interpretation of bivariate survival models.
• Working with Random Survival Forests

Reading:
• Boehmke Frederick J. 2009. “Policy Emulation or Policy Convergence? Potential Ambiguities in the Dyadic Event History Approach to State Policy Emulation.” Journal of Politics 71(3): 1125–1140.
• Strobl, Carolin, James Malley, and Gerhard Tutz. 2009. An Introduction to Recursive Partitioning: Rationale, Application, and Characteristics of Classification and Regression Trees, Bagging, and Random Forests. Psychological Methods 14 (4): 323-348.
• Ishwaran, Hemant, Udaya B. Kogalur, Eugene H. Blackstone, and Michael S. Lauer. 2008. Random Survival Forests. Annals of Applied Statistics 2(3): 841–860.
• Quiroz Flores, Alejandro. 2016. Ministerial Survival During Political and Cabinet Change: Foreign Affairs, Diplomacy and War. London: Routledge. Ch. 7.

Day 10: Review.

Reading:
• Box-Steffensmeier, Janet M. & Bradford S. Jones. 2004. Event History Modeling: A Guide for Social Scientists. New York: Cambridge University Press. Ch. 11.