Techniques for Data Analysis

The course aims to provide students with the fundamental conceptual tools needed to understand, interpret, and critically evaluate quantitative data and information in social, economic, and organizational contexts. The course is based on the idea that data do not speak for themselves: their meaning depends on how they were produced and measured, whom or what they represent, how they are analysed, and the context in which the results are interpreted.
Particular attention will be devoted to developing the ability to ask the appropriate questions when faced with data, graphs, and quantitative claims. The main tools of descriptive statistics, the analysis of relationships between variables, and statistical inference will be introduced, with emphasis on their meaning, interpretation, strengths, and limitations rather than on the manual execution of calculations. Students will also be introduced, in a guided way, to free code-free tools such as jamovi for carrying out simple analyses of real-world data without requiring programming skills, as well as to the critical use of GenAI to support data analysis and interpretation. For example, rather than learning how to mechanically calculate a statistical measure, students will be expected to understand why two organizations with similar average salaries may have very different salary distributions, or why an observed relationship between remote working and employee satisfaction does not necessarily imply a causal effect.
The course therefore aims to develop critical quantitative literacy that will be useful for subsequent studies, professional activities and, more generally, for the informed interpretation of the quantitative information that characterizes contemporary social and public life, including when data, analyses, or interpretations are produced using software or GenAI systems.

By the end of the course, students should be able to correctly read and interpret data, tables, graphs, and simple results from statistical analyses; select and interpret the main descriptive measures according to the problem under consideration; understand the meaning of relationships between variables; and distinguish association from causation.
Students should also understand the logic of sampling and statistical inference, interpreting in substantive terms concepts such as estimates, margins of error, confidence intervals, hypothesis testing, and statistical significance, and distinguishing statistical significance from the substantive relevance of a result.
Students should be able to recognize some of the main problems that may compromise the quality of data and conclusions - for example, non-representative samples, inappropriate comparisons, misleading uses of percentages and graphs, confounding, or unjustified causal interpretations - and to discuss plausible alternative interpretations.
Through concrete cases, real-world data, and individual and group activities, the course will also develop students' ability to critically evaluate quantitative evidence and clearly communicate its results, limitations, and degree of uncertainty. By the end of the course, students should also be able, at an introductory and guided level, to use free code-free tools such as jamovi to explore and analyse simple real-world datasets, correctly interpret the resulting outputs, and critically assess analyses and interpretations generated using software or GenAI tools, without delegating methodological judgement to such tools.