Cambridge Research Methods (CaRM) course timetable

Have you received or collected your data (or anticipate doing so!), but are not sure what to do next? This course is designed to equip you with the skills you need to efficiently clean, reformat, and prepare your datasets using Stata. Ideal for social science researchers and analysts who want to use quantitative data for their dissertation or other research project and want to prepare their data efficiently and follow best practices.

Over four interactive sessions, you will master essential techniques for handling missing data, merging and appending datasets, batch processing, and recoding variables. Each session combines concise, focused lectures with practical, hands-on exercises using either your own data or datasets provided by the instructor.

Oral history research methods are employed by numerous disciplines, including history, sociology, human geography, and communication. Oral history involves conducting historical research through interviews, where an interviewer speaks with a narrator who has first-hand experience of significant historical events. The oral history method is a data collection technique that can also be used to enrich the mainstream historical record.

Session 1: Oral history: Principles and methods

Session 2: Making oral history: Practical workshop

As a science researcher, you will need to deal with quite heterogeneous and dirty data. The data may have been collected through different approaches: observation, surveys, interviews, experiments, published printed or online sources, etc. Moreover, the data may have been encoded by different software and persons, and comes to you in different formats (e.g., txt, csv, xlsx, json, etc). Therefore, the data typically needs to be preprocessed before you can make sense of it through statistics and graphical representations. For example, you may need to re-encode the information in a way that is more meaningful to your analysis goals. Also, you may need to re-arrange the data and clean it, removing duplicates and incomplete information. Finally, you may need to apply all these transformations to other similarly structured data, over and over again. Doing this “by hand” is an arduous, time-consuming and error-prone task; so, automatizing these routines is the smart way to go!

In this course, I will teach you how to read, transform and prepare different kinds of data using Python and its popular libraries NumPy and Pandas. We are going to solve several problems (“Missions”) together, of increasing levels of difficulty. Each Mission will introduce you to new data structures (e.g., dictionaries, series, dataframes), methods and attributes, extending your previous knowledge. The content of the course is designed to be to-the-point and focused on practicality. By the end of the course, you should be able to program preprocessing routines that you can apply to your own data. Moreover, you will have an advanced data-handling blueprint to which you can easily add new information and skills over time.

Social Network Analysis (SNA) is “a distinct research perspective in the behavioural and social sciences” because it elevates relationships as the primary unit of analysis when attempting to understand and explain social phenomena (Wasserman and Faust, 1994, p. 4). This methods module will introduce you to network research tools used to explore the social constructs that surround all of us, continuously facilitating and frustrating our individual ambitions. Each of our three sessions will focus on a primary component of modern SNA: relational data collection, network visualisation, and descriptive network statistics and modelling. We will use real relational datasets from historical network studies. Participants will also be encouraged to develop their own relational data and complete a basic descriptive analysis and network visualisation of their data. This module will make use of web-based tools and open-source options in the R environment. However, no previous training in SNA methods or R will be assumed by the instructor.

Researchers often feel overwhelmed by large amounts of qualitative data, wondering how to organize and analyse it, and use it effectively as primary research evidence. This module introduces principles and methods of sense-making, helping researchers identify and understand the patterns, themes, and meanings embedded in their data.

The module consists of a comprehensive lecture and two hands-on workshops. Session 1 introduces the basic principles and methods, focusing on the progression from data to sense-making, how to relate data to existing literature, and how to construct a well-supported argument based on the empirical evidence. The two workshops are designed for students to experience and practice coding (manually or using software) and to develop their own arguments. In Session 2, students can apply sense-making techniques to their own data and practice interpreting data to draw meaningful insights manually. Session 3 focuses on data analysis using Atlas.ti software, which allows students to practise coding, categorising, and conceptualising their own empirical data or open-sourced datasets.

Sessions:

Session 1: Lecture: Analysing and interpreting qualitative data

Session 2: Practical workshop: Making sense of data

Session 3: Practical workshop: Software coding demonstration

This course introduces students to discourse analysis with a particular focus on the (re)construction of discourse and meaning in textual data. It takes students through the different stages of conducting a discourse analysis in four practical-oriented sessions. The overall course focus is guided by a Foucauldian and Critical Discourse Analysis approach, conceptualising discourses as not only representing but actively producing the social world and examining its entanglement with power.

The first session gives an overview of theoretical underpinnings, exploring the epistemological positions that inform different strands of discourse analysis. In the second session, we delve into the practical application of discourse analysis of textual data. Topics covered include, among others, what research questions and aims are suitable for discourse analysis as well as data sampling. In the third session, we discuss how to analyse textual data based on discourse analysis using the computer-assisted qualitative data analysis software Atlas.ti. The fourth session will take a workshop format in which students apply the gained knowledge by developing their own research design based on discourse analysis.

The module introduces causal inference methods that are commonly used in quantitative research, in particularly social policy evaluations. It covers the contexts and principles as well as applications of several specific methods - instrumental variable approach, regression discontinuity design, and difference-in-differences analysis. Key aspects of the module include investigations of the theoretical basis, statistical process, and illustrative examples drawn from research papers published on leading academic journals. The module incorporates both formal lecturing and lab practice to facilitate understanding and applications of the specific methods covered. The module is suitable for those who are interested in quantitative research and analysis of causality across a range of topics in social sciences.

'A hammer is to carpentry what research methods are to social and political scientists’​ (Hewitt, 2001, p. 371)​. ‘It is the main device by which we perform our work’ and fulfil our duties to critically engage theory and practice, as well as generate knowledge ​(Johan Adriaensen, 2015, p. 1)​.

This training course explores the intricate world of elite/expert interviews within social science research. It provides participants with a comprehensive understanding of the method's rationale, ethical considerations, practical preparations, and execution strategies. Throughout the course, participants will explore various sampling techniques, ethical dilemmas, access negotiation tactics, and the crucial role of reflexivity in this research approach.

The data we obtain from survey and experimental platforms (for behavioural science) can be very messy and not ready for analysis. For social science researchers, survey data are the most common type of data to deal with. But typically the data are not obtained in a format that permits statistical analyses without first conducting considerable time re-formatting, re-arranging, manipulating columns and rows, de-bugging, re-coding, and linking datasets. In this module students will be introduced to common techniques and tools for preparing and cleaning data ready for analysis to proceed. The module consists of four lab exercises where students make use of real life, large-scale, datasets to obtain practical experience of generating codes and debugging.

Building upon the univariate techniques introduced in the Foundations in Applied Statistics (FiAS) module, these sessions aim to provide students with a thorough understanding of statistical methods designed to test associations between two variables (bivariate statistics). Students will learn about the assumptions underlying each test, and will receive practical instruction on how to generate and interpret bivariate results using Stata. It introduces students to four of the most commonly used statistical tests in the social sciences: correlation, chi-square tests, t-tests, and analysis of variance (ANOVA).

The module is divided between pre-recorded mini-lectures, in which you’ll learn the relevant theory, and in-person, hands-on practical sessions, in which you will learn how to apply these techniques to analyse real data using the statistical package, Stata.

You will learn the following techniques:

• Cross-tabulations
• Scatterplots
• Covariance and correlation
• Nonparametric methods
• Two-sample t-tests
• ANOVA

As well as viewing the pre-recorded mini lectures via Moodle and attending the live lab sessions, students are expected to do a few hours of independent study each week.

Building upon the univariate techniques introduced in the Foundations in Applied Statistics (FiAS) module, these sessions aim to provide students with a thorough understanding of statistical methods designed to test associations between two variables (bivariate statistics). Students will learn about the assumptions underlying each test, and will receive practical instruction on how to generate and interpret bivariate results using R. It introduces students to four of the most commonly used statistical tests in the social sciences: correlation, chi-square tests, t-tests, and analysis of variance (ANOVA).

The module is divided between pre-recorded mini-lectures, in which you’ll learn the relevant theory, and in-person, hands-on practical sessions, in which you will learn how to apply these techniques to analyse real data using the statistical package, R.

You will learn the following techniques:

• Cross-tabulations
• Scatterplots
• Covariance and correlation
• Nonparametric methods
• Two-sample t-tests
• ANOVA

As well as viewing the pre-recorded mini lectures via Moodle and attending the live lab sessions, students are expected to do a few hours of independent study each week.

Open Source Investigation for Academics is methodology course run by Cambridge’s Digital Verification Corps, in partnership with Cambridge’s Centre of Governance and Human Rights, Cambridge Research Methods and Cambridge Digital Humanities, as well as with the Citizen Evidence Lab at Amnesty International.

Please note that places on this module are limited, so please only make a booking if you are able to attend all of the sessions.