This workshop will introduce participants to the basics of assembling longitudinal cross-sample and within-sample panel datasets as well as how to conduct trend analyses using STATA. It is designed for social scientists who wish to conduct longitudinal data analyses either as a core component of their projects or as a complementary component to their ongoing research. The session will explore the key differences between types of longitudinal data and the key theoretical concepts that are core to conducting analyses of these types of data, including fixed and random effects, time variables, and the utility of multilevel modelling in trend analyses.

The session will cover the most important considerations involved in creating a cross-time single sample panel as well as explore the core practical skills required to merge, clean, and assemble repeated cross-sample data. During this workshop, participants will generate a new dataset, drawing on existing sources. They will also be introduced to the basics of running trend analyses on these data.

All exercises and sample analyses will be done using STATA, providing participants with important introductory skills and the sample coding that they will need to start applying these techniques in their own projects.

Outline

• Introducing Longitudinal Data

  • Panel vs. cross-sectional data

  • Benefits and drawbacks of each data type

  • Important considerations when assembling longitudinal datasets

    • Drawing on existing sources of data

    • Creating custom datasets

    • Combining multiple data sources

• Practical Exercise: Creating a workable dataset:

  • Locating and accessing cross-sectional and panel data – some sample sources

  • Assembling a dataset using STATA

  • Merging multiple datasets

  • Handling missing data

• Conducting Trend Analyses

  • Theoretical considerations

    • Fixed and random effects models

    • Multilevel data considerations

    • Assumptions and Limitations

• Practical Exercise: Conducting a trend analysis

  • Setting up the analysis

  • Running the analysis

  • Interpreting the results

Audience & Prerequisites

This workshop is designed as an accessible introduction; however, some preliminary knowledge of quantitative research methods is recommended.

Note: Practical examples employed in this workshop will be drawn from publicly available data from the World Bank, World Values Surveys, and Our World in Data. Please make sure to have a web-enable computer so that you can download sample datasets and other materials. All participants are also asked to arrive with STATA already installed on their devices. A trial license link will be shared in advance of the session for those who do not have an active STATA license.

Suggested Readings & Resources

Baum, C.F. 2015. “Stata: The language of choice for time-series analysis?” The Stata Journal. 5(1): 46-63. https://journals.sagepub.com/doi/pdf/10.1177/1536867X0500500110

Cameron, A. C., & Trivedi, P. K. 2010. “Microeconometrics Using STATA”. Stata Press. https://www.stata.com/bookstore/microeconometrics-stata/

Wooldridge, J. M. (2010). Econometric Analysis of Cross Section and Panel Data. MIT Press. https://ipcig.org/evaluation/apoio/Wooldridge%20-%20Cross-section%20and%20Panel%20Data.pdf

Data Sources:

• World Values Surveys: https://www.worldvaluessurvey.org/WVSDocumentationWVL.jsp

• World Bank: https://data.worldbank.org/

• Our World in Data: https://ourworldindata.org/