Panel Data Analysis (Intensive)

Prerequisites

This module provides an applied introduction to panel data analysis (PDA). Panel data are gathered by taking repeated observations from a series of research units (eg. individuals, firms) as they move through time. This course focuses primarily on panel data with a large number of research units tracked for a relatively small number of time points.

The module begins by introducing key concepts, benefits and pitfalls of PDA. Students are then taught how to manipulate and describe panel data in Stata. The latter part of the module introduces random and fixed effects panel models for continuous and dichotomous outcomes. The course is taught through a mixture of lectures and practical sessions designed to give students hands-on experience of working with real-world data from the British Household Panel Survey.

This module is designed for MPhil and PhD students as part of the Social Science Research Methods Centre (SSRMC) training programme - a shared platform for providing research students with a broad range of quantitative and qualitative research methods skills that are relevant across the social sciences.

• Students should be comfortable with multiple regression. Familiarity with Stata is very helpful but not absolutely essential. Notes and Stata code will be provided.
• To use the Titan Teaching Room computers you must bring your password for the Desktop Services system. Please note, your password for the Desktop Services system is distinct from your Raven/department/email password. If you are uncertain about this you are advised to go to the University Computing Service Helpdesk before the first day of class or find out more on the UCS Newcomers page.
• You must have access to the associated Moodle course page (http://www.ssrmc.group.cam.ac.uk/ssrmc-modules/before-first-session)

Number of sessions: 2

• Introduction to PDA: Concepts and uses
• Manipulating and describing panel data
• An overview of random effects, fixed effects and ‘hybrid’ panel models
• Panel models for dichotomous outcomes

1. To introduce key concepts in longitudinal research. 2. To explain how to manipulate and analyse panel data in Stata. 3. To provide an overview of important panel regression modelling techniques.

Presentations, demonstrations and practicals

Stata on MCS

• Allison, P. (2009) Fixed Effects Regression Models. London: SAGE (especially chapters 1-3).
• Longhi, S. and Nandi, A. (2015) A Practical Guide to Using Panel Data. London: SAGE (a fantastic resource covering both theoretical and practical aspects of PDA).
• Taris, T. (2000) A Primer in Longitudinal Data Analysis. London: SAGE (provides a useful overview of key concepts covered in the course).

• Bell, A. and Jones, K. (2015) Explaining Fixed Effects: Random Effects Modelling of Time Series, Cross-Sectional and Panel Data. Political Science Research and Methods 3 (1), pp. 133-153 http://dx.doi.org/10.1017/psrm.2014.7 (an accessible evaluation of different modelling approaches).
• Cameron, C. and Trivedi, P. (2010) Microeconometrics Using Stata (Revised Edition). College Station, TX: Stata Press (especially chapters 8 and 18).

A short project based task applying techniques taught in the lectures and practicals.

All students are expected to give feedback for each module they take...

At the end of each module, students will be sent a link to a very short evaluation form. They will also be able to find this link on the Moodle page for their course. The survey takes a few minutes to fill in, and can even be done on a mobile phone. Students that do not respond to the survey the first time, will receive regular automated reminders until the survey is completed.

Students will not be given certification or proof of attendance for any module for which they have not provided feedback.

• To gain maximum benefits from the course it is important that students do not see this course in isolation from the other MPhil courses or research training they are taking.
• Responsibility lies with each student to consider the potential for their own research using methods common in fields of the social sciences that may seem remote. Ideally this task will be facilitated by integration of the SSRMC with discipline-specific courses in their departments and through reading and discussion.

8 hours - A morning lecture and an afternoon lab session
This is an intensive, one-day module

Once a year