Unit information: Advanced Quantitative Methods for Social and Policy Research in 2019/20

Unit name	Advanced Quantitative Methods for Social and Policy Research
Unit code	POLIM0021
Credit points	20
Level of study	M/7
Teaching block(s)	Teaching Block 1 (weeks 1 - 12)
Unit director	Dr. Mircea Popa
Open unit status	Not open
Pre-requisites	EITHER: POLI20001, SOCI20069 and one of POLI30011, SOCI30065, SPOL30031 or SPOL30032 OR: GEOG30021 OR: registration on the MRes Advanced Quantitative Methods programme
Co-requisites	None
School/department	School of Sociology, Politics and International Studies
Faculty	Faculty of Social Sciences and Law

Description including Unit Aims

The purpose of this unit is to introduce students to some of the higher-level quantitative methods, concepts and thinking that can be found in contemporary quantitative social science, with application to social and policy research, drawing upon the lecturers' own experiences of using the methods in their own research. Such topics may include discrete dependent variables, logistic regression, nonparametric estimation, postestimation, multilevel modelling, time-series, social network analysis, data reduction and reliability. The course also includes discussion of data collection, survey design and sampling, that will help students when thinking about their extended research projects.

The unit aims:

• To expose students to some of the more advanced quantitative methods now found in the social sciences, going beyond traditional statistical inference and building upon regression
• To give students experience of applying those methods through 'hands-on' learning
• To encourage students to consider issues of research design and establishing robust answers to questions of association and causation
• To help the students learn from real research being undertaken by members of the University of Bristol
• To prepare the students for their extended research project using quantitative methods

Intended Learning Outcomes

At the end of this unit a successful student will:

-Be able to employ advanced statistical methods such as maximum likelihood estimation, time series estimation, and social network analysis to analyse social science data. -Be able to use statistical software such as R and Stata to implement the methods taught in the unit. -Be able to address data challenges such as missing data, data reduction and reliability, and sampling concerns. -Be able to engage with current applied research using the methods taught in the unit.

Teaching Information

Combination of lectures and computer-based seminars.

Assessment Information

Portfolio of applied data analysis (100%), assesses all learning outcomes. Students will have a choice among several data analysis methods to use in the assignment, reflecting the methods taught in the unit. Assignment length: 3500-4000 words. Students will receive written comments on their work from the markers.

Reading and References

Guided reading will be given in class. Such reading may include:

Ulrich Kohler, Kristian Bernt Karlson, and Anders Holm, 'Comparing coefficients of nested nonlinear probability models', The Stata Journal, 11/3 (2011), pp. 420-438.