98804 - Analysis of Public Opinion Laboratory (LM)

Learning outcomes

The laboratory introduces to the method of empirical research in the field of public opinion analysis, basic statistical techniques, and the use of survey data for the analysis of opinions on issues of public interest, political attitudes, and voting behavior. At the end of the laboratory, the student knows: - how to design and conduct opinion surveys; - how the results of such surveys can be interpreted through statistical analysis to study the factors underlying political orientations and voting choices.

Course contents

The laboratory teaches how to read, analyse, visualise and communicate data on citizens’ opinions and attitudes. No prior statistical knowledge is assumed: all techniques are introduced starting from basic concepts and applied directly to the data during the practical sessions.

The working path progressively covers: types of variables and the data matrix; frequency distributions, measures of central tendency and dispersion; cross-tabulations and comparisons between groups; the construction and reading of charts; correlation and the construction of indexes from batteries of questions; and an introduction to regression models (linear and logistic) as tools for assessing the relative weight of multiple factors. The depth at which the more advanced techniques are covered is calibrated to the background and interests of the participants.

The practical sessions use national and comparative survey data (including the European Social Survey, the World Values Survey, the Eurobarometer and ITANES) as well as published opinion polls, with reference to the topics covered in the Public Opinion Analysis course: the cleavages and divisive issues salient today (state intervention vs free market, globalism vs nationalism, climate change, immigration, civil rights) and the factors that influence opinions and voting choices. The working tools are the spreadsheet (Microsoft Excel) and the statistical software Stata, freely available to Unibo students; both are introduced step by step.

The final assignment can be oriented, at each participant’s choice, in two directions: a short piece of academic-style analysis (testing a hypothesis on survey data, with tables and commentary); or a journalistic, data-journalism-style product, i.e. a short note accompanied by charts readable by a non-specialist audience, built on original elaborations of the data. The two options require the same basic technical skills and are assessed according to the same criteria.

Readings/Bibliography

The laboratory is based on the lecturer’s classes and on the practical sessions. No textbook is required: the working materials (datasets, step-by-step software guides, commented examples) are made available on Virtuale during the course. Targeted reading suggestions will also be provided, depending on each participant’s background and interests (academic analysis or data communication).

Teaching methods

The laboratory consists of fifteen working sessions with compulsory attendance (absence from no more than three sessions is allowed). The first sessions recap the essential concepts of research methodology and descriptive statistics, without assuming prior knowledge. Most sessions consist of guided computer-based exercises, in which participants apply the techniques presented to datasets provided by the lecturer. In the final sessions, participants take turns presenting and discussing their own analyses. All classes are held in person. Each participant must have, including during classes, a personal computer connected to the internet with an up-to-date version of Stata installed (instructions on how to install it will be given in class). To support individual study and practice, video recordings of some classes will be made available.

Assessment methods

Assessment does not result in a mark but in a pass/fail judgement (idoneità).

In order to obtain a pass, each participant must: (a) take an active part in the practical sessions, within the attendance limits indicated above; (b) produce and present in class their own analysis, based on original elaborations of the data from one of the surveys provided by the lecturer, either as a short piece of academic-style analysis or as a journalistic-style product with charts; the presentation is followed by a short discussion with the lecturer and the class.

The pass is awarded on the basis of three criteria: technical correctness of the elaborations; ability to interpret the results appropriately, recognising the limits of the data; clarity of the presentation and ability to answer questions about one’s own analysis. Those who do not obtain a pass may present a revised version of their work in a subsequent exam session.

Students with SLD or temporary or permanent disabilities: it is recommended that they contact in good time the relevant University office (https://site.unibo.it/studenti-con-disabilita-e-dsa/en); the office will propose to the students concerned any appropriate adjustments, which must in any case be submitted, 15 days in advance, to the approval of the lecturer, who will assess their appropriateness also in relation to the learning objectives of the course.

AI may be used to support individual work, for example to clarify concepts, interpret error messages or suggest command syntax. However, the analyses presented must be carried out and understood first-hand: the in-class discussion verifies the participant’s command of the procedure followed, and any use of AI must be declared in the presentation.

Teaching tools

Classroom with projector; participants’ personal computers; software: Microsoft Excel and Stata (free licence for Unibo students); datasets and working materials shared on Virtuale; video recordings of some classes.

Office hours

See the website of Salvatore Vassallo