GV903-7-FY-CO:
Advanced Research Methods

The details
2020/21
Government
Colchester Campus
Full Year
Postgraduate: Level 7
Current
Thursday 08 October 2020
Friday 02 July 2021
30
10 June 2020

 

Requisites for this module
(none)
(none)
(none)
GV900

 

GV906, GV916

Key module for

MA L25212 Conflict Resolution,
MA L252EB Conflict Resolution,
MA L252EK Conflict Resolution,
MSC L25212 Conflict Resolution,
MSC L252EB Conflict Resolution,
MSC L252EK Conflict Resolution,
MA L24012 Global and Comparative Politics,
MA L240EB Global and Comparative Politics,
MA L240EK Global and Comparative Politics,
MSC L24012 Global and Comparative Politics,
MSC L240EB Global and Comparative Politics,
MSC L240EK Global and Comparative Politics,
MA L25012 International Relations,
MA L250EB International Relations,
MA L250EK International Relations,
MRESL25024 International Relations,
MSC L25012 International Relations,
MSC L250EB International Relations,
MSC L250EK International Relations,
MA L20612 Political Economy,
MA L206EB Political Economy,
MA L206EK Political Economy,
MRESL20624 Political Economy,
MSC L20612 Political Economy,
MSC L206EB Political Economy,
MSC L206EK Political Economy,
MA L20012 Political Science,
MA L200EB Political Science,
MSC L20012 Political Science,
MSC L200EB Political Science,
MA L20712 Public Opinion and Political Behaviour,
MA L207EB Public Opinion and Political Behaviour,
MA L207EK Public Opinion and Political Behaviour,
MSC L20712 Public Opinion and Political Behaviour,
MSC L207EB Public Opinion and Political Behaviour,
MSC L207EK Public Opinion and Political Behaviour,
MRESL20024 Political Science,
MA L24512 United States Politics,
MSC L16512 Quantitative International Development,
MSC F7D412 Environmental Futures with Climate Change,
MPHDL20148 Government,
PHD L20148 Government,
MPOLL268 International Relations,
MPOLL269 International Relations (Including Placement Year),
MPOLL370 International Relations (Including Year Abroad),
MPOLL234 Politics and International Relations,
MPOLL235 Politics and International Relations (Including Placement Year),
MPOLL236 Politics and International Relations (Including Year Abroad)

Module description

This module presents quantitative methods essential to test hypotheses.

The first part of the course focuses on hypothesis testing, hypothesis testing using least squares, and some classic violations of the Gauss-Markov conditions. We will cover cross-sectional and longitudinal models for continuous dependent variables. This first part will also cover the basics of programming, data management, and data visualisation in the statistical computing environment R as well as the preparation of documents with statistical contents using LaTeX and knitr, but the main focus of the module is on statistical theory.

The second part of the module focuses on more advanced models ubiquitous in political science based on maximum likelihood estimation and other estimation techniques, starting with the generalised linear model and its various outcome distributions (models for binary, ordered, categorical, count, and event history data) and ending with advanced topics like inferential network analysis and topics in causal inference. This second part will again focus mainly on statistical theory but also cover many political science applications and their implementation using R.

The models and methods are approached substantively, mathematically, and computationally. Throughout the module, students will also familiarise themselves with the interpretation and presentation of empirical evidence in political science.

The module will be particularly useful for students who aim to pursue careers in academia or in research-intensive environments, for example think tanks, research-related government posts, data science, or survey analytics.

Module aims

The module will enable students to...
• understand and apply the logic of hypothesis testing in a variety of political science contexts.
• understand and interpret statistical analyses in published political science research.
• master the mathematics behind ordinary least squares, maximum likelihood estimation, generalised linear models, and related regression models and estimation techniques.
• translate theories into empirical models.
• conduct their own basic and advanced regression analyses using empirical datasets, both manually and with software, commensurate with analyses published in leading political science journals.
• assess the goodness of fit of empirical models.
• understand which statistical model to employ in a given situation and to what extent the assumptions of each candidate model are met.
• effectively present quantitative results using R, LaTeX, and knitr.


Module learning outcomes

After completing this module, students will...
• formulate theories in ways that are amenable to multivariate hypothesis testing and be able to choose an appropriate statistical model commensurate with their theory.
• understand, and be able to improve upon, statistical analyses and their interpretations in leading political science journals.
• have practical experience with conducting high-quality quantitative political science research as well as with the implementation of basic and advanced regression models, both using ready-made functions/packages in R and manually/from scratch.
• master the mathematics and statistical theory underlying hypothesis testing, ordinary least squares, maximum likelihood estimation, generalised linear models, time series analysis, panel and multilevel models, event-history analysis, and similar techniques.
• know how to handle complex data structures and implement appropriate models, including temporal, spatial, and hierarchical dependence.
• understand the assumptions underlying a variety of statistical models and be able to diagnose violations of these assumptions.
• be able to present statistical results effectively.

Module information

This module will be delivered with (i) a weekly pre-recorded lecture and (ii) a weekly seminar. The pre-recorded lecture will consist of one or more items of prepared content that students can access electronically and must study before the seminar. The seminar will be simultaneously held face-to-face and online and will consist of one 50-minute session per week in which exercises and students' questions will be discussed. Students are expected to carefully read the literature on the reading list before consuming the pre-recorded lecture contents. Practical exercises – mostly software-based – will be provided on a weekly basis to prepare for the four assignments. Students are expected to complete these exercises before the weekly seminar, where the solutions will be discussed. A module forum will be available on Moodle; all students are expected to participate in the discussions on the forum by asking and answering questions.


Week Autumn Term
Week 2 Introduction to Advanced Research Methods
Week 3 Fundamentals of Mathematics and Probability;
Random Variables, Distributions, and Expectations
Week 4 Fundamentals of Mathematical Statistics and Matrix Algebra
Week 5 The Linear Regression Model – Estimation and Inference
Week 6 The Linear Regression Model – Model Specification, Interpretation, and Large-Sample Properties
Week 7 Heteroskedasticity and its Solutions; Measurement Issues
Week 8 Time Series Analysis
Week 9 Panel Data
Week 10 Instrumental Variables and Systems of EquationsWeek 11 Maximum Likelihood Estimation
Week Spring Term
Week 16 Binary Dependent Variables
Week 17 The Generalized Linear Model;
Bootstrapping and Permutations
Week 18 Ordinal Dependent Variables
Week 19 Nominal Dependent Variables
Week 20 Limited Dependent Variables
Week 21 Counts and Proportions
Week 22 Duration Models
Week 23 Network Models
Week 24 Causal Inference and Matching
Week 25 Missing Data; Spatial Models



Learning and teaching methods

This module will be delivered with (i) a weekly pre-recorded lecture and (ii) a weekly seminar. The pre-recorded lecture will consist of one or more items of prepared content that students can access electronically and must study before the seminar. The seminar will be simultaneously held face-to-face and online and will consist of one 50-minute session per week in which exercises and students' questions will be discussed. Students are expected to carefully read the literature on the reading list before consuming the pre-recorded lecture contents. Practical exercises – mostly software-based – will be provided on a weekly basis to prepare for the four assignments. Students are expected to complete these exercises before the weekly seminar, where the solutions will be discussed. A module forum will be available on Moodle; all students are expected to participate in the discussions on the forum by asking and answering questions.

Bibliography*

  • Beck, Nathaniel. (2008) 'Time-Series Cross-Sectional Methods', in The Oxford handbook of political methodology, Oxford: Oxford University Press. vol. Oxford handbooks of political science
  • Long, J. Scott. (c1997) Regression models for categorical and limited dependent variables, Thousand Oaks: Sage. vol. 7
  • Wooldridge, Jeffrey M. (©2020) Introductory econometrics: a modern approach, Boston, MA: Cengage.
  • Ward, Michael D.; Ahlquist, John S. (2018) Maximum Likelihood for Social Science, Cambridge: Cambridge University Press.
  • King, Gary. (1989) Unifying political methodology: the likelihood theory of statistical inference, Cambridge: Cambridge University Press.
  • Bueno de Mesquita, Bruce. (c2014) Principles of international politics, Los Angeles: Sage/CQ Press.
  • Wackerly, Dennis D.; Mendenhall, William; Scheaffer, Richard L. (2008) Mathematical statistics with applications, Belmont, CA: Thomson Brooks/Cole.
  • Myung, In Jae. (2003-2) 'Tutorial on maximum likelihood estimation', in Journal of Mathematical Psychology. vol. 47 (1) , pp.90-100
  • Miguel, Edward; Satyanath, Shanker; Sergenti, Ernest. (2004-08) 'Economic Shocks and Civil Conflict: An Instrumental Variables Approach', in Journal of Political Economy. vol. 112 (4) , pp.725-753
  • Alvarez, R. Michael; Nagler, Jonathan. (1998-01) 'When Politics and Models Collide: Estimating Models of Multiparty Elections', in American Journal of Political Science. vol. 42 (1) , pp.55-
  • Box-Steffensmeier, Janet M.; Jones, Bradford S. (1997-10) 'Time is of the Essence: Event History Models in Political Science', in American Journal of Political Science. vol. 41 (4) , pp.1414-
  • Box-Steffensmeier, Janet M.; Zorn, Christopher J. W. (2001-10) 'Duration Models and Proportional Hazards in Political Science', in American Journal of Political Science. vol. 45 (4) , pp.972-
  • Reuveny, Rafael; Li, Quan. (2003-09) 'The Joint Democracy-Dyadic Conflict Nexus: A Simultaneous Equations Model', in International Studies Quarterly. vol. 47 (3) , pp.325-346
  • Leifeld, Philip; Cranmer, Skyler J.; Desmarais, Bruce A. (2018) 'Temporal Exponential Random Graph Models with btergm: Estimation and Bootstrap Confidence Intervals', in Journal of Statistical Software. vol. 83 (6)
  • Jones, Bradford S.; Branton, Regina P. (2005-12) 'Beyond Logit and Probit: Cox Duration Models of Single, Repeating, and Competing Events for State Policy Adoption', in State Politics & Policy Quarterly. vol. 5 (4) , pp.420-443
  • Cranmer, Skyler J.; Leifeld, Philip; McClurg, Scott D.; Rolfe, Meredith. (2017-01) 'Navigating the Range of Statistical Tools for Inferential Network Analysis', in American Journal of Political Science. vol. 61 (1) , pp.237-251
  • Sigelman, Lee; Zeng, Langche. (2000) 'Analyzing Censored and Sample-Selected Data with Tobit and Heckit Models', in Political Analysis. vol. 8 (2) , pp.167-182
  • Ho, Daniel E.; Imai, Kosuke; King, Gary; Stuart, Elizabeth A. (2007) 'Matching as Nonparametric Preprocessing for Reducing Model Dependence in Parametric Causal Inference', in Political Analysis. vol. 15 (3) , pp.199-236
  • Cottrell, Allin. (1995) A Short Introduction to LaTeX.
  • Greene, William H. (©2018, 2012, 2008) Econometric analysis, New York, NY: Pearson.
  • Best, Henning; Wolf, Christof. (c2015) The SAGE handbook of regression analysis and causal inference, London: SAGE.
  • Torfs, Paul; Brauer, Claudia. (2014) A (Very) Short Introduction to R.
  • Kam, Cindy D.; Palmer, Carl L. (2008-07) 'Reconsidering the Effects of Education on Political Participation', in The Journal of Politics. vol. 70 (3) , pp.612-631
  • King, Gary; Tomz, Michael; Wittenberg, Jason. (1973-) 'Making the Most of Statistical Analyses: Improving Interpretation and Presentation', in American journal of political science, Hoboken, NJ [etc.]: Wiley-Blackwell Pub. on behalf of the Midwest Political Science Association [etc.]. vol. 44 (2) , pp.341-355
  • King, Gary. (©1998) Unifying political methodology: the likelihood theory of statistical inference, Ann Arbor: University of Michigan Press.
  • Paolino, Philip. (2001) 'Maximum Likelihood Estimation of Models with Beta-Distributed Dependent Variables', in Political Analysis. vol. 9 (4) , pp.325-346
  • Brambor, Thomas; Roberts Clark, William; Golder, Matt. (no date) 'Understanding Interaction Models: Improving Empirical Analyses', in Political Analysis, Political Analysis. vol. 14 (1) , pp.63-82

The above list is indicative of the essential reading for the course. The library makes provision for all reading list items, with digital provision where possible, and these resources are shared between students. Further reading can be obtained from this module's reading list.

Assessment items, weightings and deadlines

Coursework / exam Description Deadline Weighting
Coursework   Assignment 1     25% 
Coursework   Assignment 2     25% 
Coursework   Assignment 3     25% 
Coursework   Assignment 4     25% 

Overall assessment

Coursework Exam
100% 0%

Reassessment

Coursework Exam
100% 0%
Module supervisor and teaching staff
Prof Philip Leifeld, email: philip.leifeld@essex.ac.uk.
Professor Philip Leifeld
Module Supervisor Professor Philip Leifeld philip.leifeld@essex.ac.uk Module Administrator, Jamie Seakens (govpgquery@essex.ac.uk)

 

Availability
No
No
Yes

External examiner

Dr Nicholas Walter Vivyan
University of Durham
Senior Lecturer
Resources
Available via Moodle
Of 80 hours, 40 (50%) hours available to students:
40 hours not recorded due to service coverage or fault;
0 hours not recorded due to opt-out by lecturer(s).

 

Further information
Government

* Please note: due to differing publication schedules, items marked with an asterisk (*) base their information upon the previous academic year.

Disclaimer: The University makes every effort to ensure that this information on its Module Directory is accurate and up-to-date. Exceptionally it can be necessary to make changes, for example to programmes, modules, facilities or fees. Examples of such reasons might include a change of law or regulatory requirements, industrial action, lack of demand, departure of key personnel, change in government policy, or withdrawal/reduction of funding. Changes to modules may for example consist of variations to the content and method of delivery or assessment of modules and other services, to discontinue modules and other services and to merge or combine modules. The University will endeavour to keep such changes to a minimum, and will also keep students informed appropriately by updating our programme specifications and module directory.

The full Procedures, Rules and Regulations of the University governing how it operates are set out in the Charter, Statutes and Ordinances and in the University Regulations, Policy and Procedures.