Methodologies for the Social Sciences II: Quantitative

Periodo di svolgimento
Ore del corso
20
Ore dei docenti responsabili
20
Ore di didattica integrativa
0
‌‌

Modalità esame

Prova scritta

Prerequisiti

Compulsory for the 1st year students of the PhD Programme in "Political Science and Sociology"

Compulsory for the 1st year students of the PhD Programme in "Transnational Governance"

Optional for the 5th year students of the MA Programme in "Political and Social Sciences"

Programma

The course consists in an introduction to quantitative data analysis for social and political science research, with a particular focus on linear regression. The course will start from the basics of quantitative analysis: types of variables, data sets, simple descriptive statistics. It will then cover all the main aspects of regression analysis: its assumptions, the estimation technique, its application to concrete research problems, the presentation of results. The course will conclude by giving an overview of other types of regressions that participants might need to use in their future research (such as regression models for categorical variables). At the end of this course, participants will be able to select the appropriate method for their research question, carry out basic quantitative analysis (including descriptive tables and graphs) as well as linear regressions, and they will be able to meaningfully interpret the results of these methods. The course combines the theoretical study of basic statistical analysis with practical exercise with the statistical programme STATA.

Session 1 – Introduction to Quantitative Methods (Tue, January 11, 14-17)

Variables and types of variables. Examining and reading data sets. Descriptive statistics. Cross

tabulations. Basic graphs.

 

Required readings: Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test

Ideas, San Francisco: Jossey-Bass. Chapters 1 to 3.

Additional reading: Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test

Ideas, San Francisco: Jossey-Bass. Chapter 4.

Acock, A. C. (2018). A Gentle Introduction to STATA. College Station, Texas: Stata Press. Chapters 4-5.

 

Session 2 – Bivariate regression: Fitting a straight line (Wed, January 12, 10-13)

 

Fitting a straight line. Bivariate regression. Estimation and interpretation of coefficientsand

significance tests. Measuring the goodness of fit of a linear regression.

 

Required readings: Lewis-Beck, C. and Lewis Beck, M. (2016) Applied Regression: An Introduction.

Thousand Oaks, California: SAGE. Chapters 1-2.

Additional reading: Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test

Ideas, San Francisco: Jossey-Bass. Chapter 5.

 

Session 3 – Multivariate regression: an introduction (Fri, January 21, 14-17)

 

Interpreting and assessing the goodness of fit of multivariate regression. Checking the assumptions of

linear regressions: omitted variables, functional forms, outliers, normality of residuals.

 

Required readings: Lewis-Beck, C. and Lewis Beck, M. (2016) Applied Regression: An Introduction.

Thousand Oaks, California: SAGE. Chapters 2-3.

 

Additional readings: Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test Ideas, San Francisco: Jossey-Bass. Chapters 6-7.

G. King and M. E. Roberts (2015) ‘How Robust Standard Errors Expose Methodological Problems They Do Not Fix, and What to Do About It’, Political Analysis, 23(2), 159–179.

 

Session 4 – Multivariate regression: interpretation and presentation (Fri, January 28, 14-17)

 

Checking the assumptions of linear regressions: heteroskedasticity and multicollinearity. How to

present regression results: calculating and plotting explanatory variables’ effects.

 

Required readings: Lewis-Beck, C. and Lewis Beck, M. (2016) Applied Regression: An Introduction. Thousand Oaks, California: SAGE. Chapters 3-4.

Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test Ideas, San Francisco: Jossey-Bass. Chapter 10.

 

Additional readings: G. King, M. Tomz and J. Wittenberg (2000) ‘Making the Most of Statistical Analyses: Improving Interpretation and Presentation’, American Journal of Political Science, 44(2), 347–361.

T. Brambor, W.R. Clark, and M. Golder, (2005) ‘Understanding Interaction Models: Improving Empirical Analyses’, Political Analysis, 14(1): 63–82.

 

Session 5 – Extensions of the linear regression model (I) (Mon, February 14, 14-17)

 

Introduction to discrete choice models: the logit model.

 

Required readings: Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test

Ideas, San Francisco: Jossey-Bass. Chapters 13-14.

 

Additional reading: Long J. S. and Freese J. (2014) Regression Models for Categorical Dependent Variables using Stata, Third Edition. Stata Press. Chapters 5-6.

 

Session 6 – Extensions of the linear regression model (II) (Tue, February 15, 10-13)

 

Multinomial logit and ordered logit. Introduction to models for count data.

 

Required readings: Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test

Ideas, San Francisco: Jossey-Bass. Chapters 13-14.

 

Additional reading: Long J. S. and Freese J. (2014) Regression Models for Categorical Dependent Variables using Stata, Third Edition. Stata Press. Chapters 7-8-9.

 

Session 7 – Final thoughts and future directions: research design and interpretation (Tue, February 22, 15-17)

 

Reflect on your own research project, your data and what research design is the most appropriate.

 

Required readings: Treiman, D. J. (2008) Quantitative Data Analysis: Doing Social Research to Test

Ideas, San Francisco: Jossey-Bass. Chapters 16.

Obiettivi formativi

By the end of this module, students will be able to:

- understand the key issues in quantitative analysis and the underlying logic of regression techniques;

- meaningfully interpret the results of regression models;

- use the statistical software STATA for descriptive and inferential analysis

- apply the techniques and methods explored in the module to their own PhD project (if relevant)

Riferimenti bibliografici