An Introduction to Survey Research

Course information

The course provides an overview of survey sampling and design, survey statistics, ethics for survey research, and survey data processing, management, and analysis. Topics include sampling decisions, questionnaire design, survey-based experiments, and parametric and non-parametric statistical tests.

Prerequisite Knowledge

Elementary knowledge of non-parametric and parametric statistics and an understanding of data cleaning and processing. No background in survey design is assumed.

Intended Learning Outcomes

By the end of this course learners will be able to:

  • Understand key issues involved in the design of high quality surveys;
  • Appreciate connections between survey length, question wording, and the quality of data generated;
  • Recognise the processes behind simple and complex sampling and the controversies surrounding low response rates and potential moves away from random probability sampling;
  • Have the capability to draft ethical consent forms, identify situations when different forms of ethical consent are necessary, and realise where participant anonymity may be compromised;
  • Execute and interpret non-parametric statistical techniques commonly applied to survey data;
  • Develop and interpret multivariate models with dichotomous, binary, ordinal and, nominal dependent variables;
  • Identify problems associated with missing data and fixes to missing data problems;
  • Understand the design and analysis of survey experiments embedded onto surveys;
  • Have a basic understanding of latent variable models and the measurement of subjective concepts (e.g. political trust) common in the social sciences and of interest to government agencies.

Syllabus

Week 1

  • Theory and Question Driven Survey Design
  • The Total Survey Error Approach
  • Survey Flow

Week 2

  • Survey Length and Format
  • Designing Meaningful Questions
  • Data Capture and Generation

Week 3

  • Measuring Attitudes
  • Question Ordering Effects
  • Open Ended Questions

Week 4

  • Drawing Samples: Simple, Complex, and Probabilistic/Non-Probabilistic
  • Issues of Survey non-Response and Incentivisation
  • Survey Interview Modes (Face-to-Face vs. Internet)

Week 5

  • Gaining Ethical Approval to Survey the Public
  • Guidance in Developing Respondent Information Sheets
  • Data Anonymisation

Mid-term week break

Week 6

  • Survey Data Cleaning
  • Interpreting Cross-Tabulations
  • Basic Non-Parametric Statistics Relevant to Survey Data Analysis

Week 7

  • Logic of Discrete Choice Modelling
  • Logit, Probit, Ordinal Probit/Logit and Multivariate Logit Models
  • Moderation and Mediation

Week 8

  • Missing Data, Middle Categories, and Don't Knows
  • Assumptions Behind Types of Missing Data
  • Typical Fixes to Missing Data

Week 9

  • Designing Survey Experiments
  • Analysing Survey Based Experiments
  • Complex Experiments

Week 10

  • Data Reduction via Principal Components Modelling
  • Introduction to Exploratory and Confirmatory Factor Analysis
  • Structural Equation Modelling for Panel Data

Online Learning

  • Release of recorded video and short formative assessments provided to students
  • Bookable one-to-one sessions with tutors
  • Collective Class Meetings at the conclusion of parts 1 and 2
  • Dedicated online space with message boards, essential readings, and links to relevant examples
  • Podcasts with guest experts in survey data analysis

Textbooks

Weisberg, H., 2005. The total survey error approach. Chicago: University of Chicago Press. (E-Book for Reference—available in Glasgow's library)

Clarke, H.D., Kornberg, A. and Scotto, T.J., 2010. Accentuating the Negative?. Methodology.

Assessment (for credit only)

One piece of written work constituting justification for a short survey of the student's choice and a completed draft of the survey and three short problem sets quizzes.

Software

To take our courses please use an up-to-date version of a standard browser (such as Google Chrome, Firefox, Safari, Internet Explorer or Microsoft Edge) and a PDF reader (such as Acrobat Reader). Learning material will be distributed through Moodle. We encourage all learners to install R and RStudio and we provide detailed installation instructions, but learners can also use free cloud-based services (RStudio Cloud). Learners need to install Zoom for participating in video conferencing sessions. We recommend the use of a head set for video conferencing sessions.