STATISTICAL MODELLING - 2018/9

Module code: SOCM018

Module Overview

We live in a world where large quantities of data are regularly collected about people, institutions, and social structures. This module will demonstrate how quantitative analysis techniques can be used to leverage this data and answer complex questions about the social world. Questions like ‘why some people are more at risk of crime than others?’, ‘what explains differences in life expectancy between countries?’, and ‘do gender inequalities persist in the workplace’. 

Throughout the module, the emphasis is on the underlying principles and uses of statistical models and not on the mathematical and statistical theory. It therefore gives students a solid empirical grounding to be able to critically evaluate the findings from a wide range of quantitative social science research. In the accompanying workshops students will get hands on experience of estimating a number of different statistical models in R, engaging with important issues including how to select an appropriate model, assessing the adequacy of a fitted model (in comparison to alternative models) and the statistical and substantive interpretation of the results.

Module provider

Sociology

Module Leader

BRUNTON-SMITH IR Prof (Sociology)

Number of Credits: 15

ECTS Credits: 7.5

Framework: FHEQ Level 7

JACs code: G340

Module cap (Maximum number of students): N/A

Module Availability

Semester 2

Prerequisites / Co-requisites

Students must have completed SOCM010 (Social data analytics), or be able to demonstrate that they have received an equivalent level of quantitative methods training

Module content

This module elaborates on quantitative approaches to social science, combining this with practical model building experience and critique using R. Indicative content includes:


Designing and building statistical models to answer social science questions
The general linear model 
Operationalising concepts and selecting variables
Interpreting results and finding the narrative


Hands on practical workshops will provide students with experience of:


Linear regression
Logistic regression
Multinomial regression
Poisson regression
Interaction effects and nonlinear relationships
Model fit and diagnostics
Missing data adjustments


 

Assessment pattern

Assessment type Unit of assessment Weighting
Coursework Two part statistical modelling exercise (4,000 words) 100

Alternative Assessment

Assessment Strategy

The assessment strategy is designed to provide students with the opportunity to demonstrate:

A detailed understanding of how to use statistical models to answer questions about the social world. Using real data, students will fit a number different models (linear, logistic, multinomial), requiring them to make appropriate modelling decisions based on particular data constraints, and assess the robustness of models. They will also demonstrate their ability to interpret the results of these models, and discuss their implications.

Thus, the summative assessment for this module consists of:

A two part analytic report (4,000 words) where students will conduct statistical analysis and write up their results. 

Formative assessment and feedback 

Students will be able to complete workshop exercises during days 1-3 of the short-course, giving them the chance to discuss the answers with each other and the lecturer. Day 4 of the course is devoted to independent study, where students will be able to make initial progress on their assignment. All students will be invited back to the classroom on day 5 where there will be additional opportunities to receive formative feedback from the lecturer and other students.

Module aims

  • • Provide a clear description, definition of, and discussion of the assumptions regarding statistical models
  • • Enable students to critically evaluate the full range of quantitative research conducted in the social sciences
  • • Introduce the General Linear Model and provide hands on experience with statistical models for dealing with a range of different response types - linear, logistic, multinomial and poisson models
  • • Discuss implications for modelling more complex data, notably from longitudinal studies
  • • Outline approaches for dealing with missing data

Learning outcomes

Attributes Developed
001 Have a critical awareness of the rationale and terminology of statistical modelling C
002 Be able to engage with existing quantitative research, highlighting its key strengths and weaknesses KC
003 Have a comprehensive understanding of the logic of model development and testing KC
004 Be able to develop multiple regression, logistic regression, multinomial logistic and poisson regression models and critically evaluate the results PT
005 Be able to clearly tabulate and present the results of regression outputs PT

Attributes Developed

C - Cognitive/analytical

K - Subject knowledge

T - Transferable skills

P - Professional/Practical skills

Overall student workload

Workshop Hours: 10

Independent Study Hours: 130

Lecture Hours: 10

Methods of Teaching / Learning

The learning and teaching strategy is designed to: 

Provide students with a working knowledge of statistical modelling techniques to deal with a range of different data scenarios. Alongside theoretical knowledge, workshops will give students practical experience of different techniques, and how they should be applied. Students will also learn how to critically assess the fit of their models, and how they might improve their models. 

The learning and teaching methods include:


Lectures
Practical workshops in R
Group discussion and feedback


This module is taught intensively during one-week. Days 1-3 will consist of a combination of lectures and hands on practical sessions with the statistics package R (www.r-project.org). Day 4 is devoted to independent study, allowing students to undertake preparatory work on their assignment. Finally, on day 5 students will get the opportunity to receive formative feedback on their initial assignment plans and peer feedback during group discussion. Students will then complete their practical assignment

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

Reading list for STATISTICAL MODELLING :

Programmes this module appears in

Programme Semester Classification Qualifying conditions
Social Research Methods MSc 2 Optional A weighted aggregate mark of 50% is required to pass the module

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2018/9 academic year.