ID:
509981
Durata (ore):
36
CFU:
6
SSD:
Psicologia generale
Anno:
2026
Dati Generali
Periodo di attivitÃ
Secondo Semestre (15/02/2027 - 04/06/2027)
Syllabus
Obiettivi Formativi
The course provides a gentle but rigorous introduction to applied data analysis in psychology and the human sciences. Starting from basic intuitions about samples and populations, it covers the reasoning behind traditional statistical tests (such as t-tests and ANOVAs) and gradually builds up to more advanced approaches (such as regression and mixed-effects models). The course is hands-on: alongside the theory of each analysis, students learn when to apply it and how to run it in R, a free and widely used statistical software. The aim is to provide theoretical and applied skills useful for any career path involving data analysis, particularly in experimental and clinical psychology.
Expected learning outcomes. At the end of the course, students will be able to:
Knowledge and understanding
- understand the logic of statistical inference (sampling, probability distributions, central limit theorem, standard error);
- know the main approaches to hypothesis testing (Fisher; Neyman-Pearson) and the meaning of p-values, confidence intervals and effect sizes;
- know the assumptions and appropriate use of t-tests, ANOVAs (independent, repeated measures, factorial), correlation, linear and logistic regression and mixed-effects models;
- understand the main pitfalls of null-hypothesis significance testing (low power, p-hacking, replication issues) and their ethical implications for research.
Applying knowledge and understanding
- choose and justify an appropriate analysis for a given research question and design;
- import, manipulate and visualise data in R, and run, check and report the analyses covered in the course;
- adapt existing R code to new datasets and research questions.
Making judgements
- critically evaluate analytical choices, check whether assumptions are met, and interpret results in light of the research question, including their limitations.
Communication skills
- report and interpret statistical results clearly, as in a scientific paper, with appropriate graphs and captions.
Learning skills
- independently use documentation and online resources to learn new analyses and R functions.
Expected learning outcomes. At the end of the course, students will be able to:
Knowledge and understanding
- understand the logic of statistical inference (sampling, probability distributions, central limit theorem, standard error);
- know the main approaches to hypothesis testing (Fisher; Neyman-Pearson) and the meaning of p-values, confidence intervals and effect sizes;
- know the assumptions and appropriate use of t-tests, ANOVAs (independent, repeated measures, factorial), correlation, linear and logistic regression and mixed-effects models;
- understand the main pitfalls of null-hypothesis significance testing (low power, p-hacking, replication issues) and their ethical implications for research.
Applying knowledge and understanding
- choose and justify an appropriate analysis for a given research question and design;
- import, manipulate and visualise data in R, and run, check and report the analyses covered in the course;
- adapt existing R code to new datasets and research questions.
Making judgements
- critically evaluate analytical choices, check whether assumptions are met, and interpret results in light of the research question, including their limitations.
Communication skills
- report and interpret statistical results clearly, as in a scientific paper, with appropriate graphs and captions.
Learning skills
- independently use documentation and online resources to learn new analyses and R functions.
Prerequisiti
There are no formal prerequisites. Some familiarity with the basics of descriptive statistics (e.g., mean, standard deviation, frequency distributions) and of research design is helpful but not required: the course starts from basic intuitions and builds up gradually.
No previous programming experience is required.
As the course is taught entirely in English, students should be able to follow lectures, read scientific materials and write reports in English (approximately B2 level).
No previous programming experience is required.
As the course is taught entirely in English, students should be able to follow lectures, read scientific materials and write reports in English (approximately B2 level).
Metodi didattici
The course is taught in person, entirely in English, over 12 lectures.
Workload. In line with the University's rules, each CFU (25 hours) includes 5 hours of lecture-based teaching (DE, didattica erogativa), 1 hour of interactive teaching (DI, didattica interattiva) and 19 hours of individual study. For this 6-CFU course (150 hours) this amounts to:
- 30 hours of DE;
- 6 hours of DI;
- 114 hours of individual study (indicative: learning pace and style vary from student to student).
Each lecture combines two components:
- Lecture component (DE): the lecturer introduces the reasoning and computations behind widely used data analysis approaches in psychological and experimental science, with slides and worked examples.
- Practical component (DI): students implement each method in R on real or simulated data, individually and in small groups. After initial guidance from the lecturer, the focus is on developing students' ability to adapt heavily commented code to new data and questions.
Consistency with learning objectives. Lectures and individual study support the understanding of statistical reasoning; hands-on practice in R develops the ability to apply it, to make and justify analytical choices, and to report results.
Students should bring a laptop to class and install R and RStudio beforehand (https://posit.co/download/rstudio-desktop/). Because the course emphasises practical work, attendance is strongly recommended, although not compulsory. The lecturer is available for office hours by appointment.
Workload. In line with the University's rules, each CFU (25 hours) includes 5 hours of lecture-based teaching (DE, didattica erogativa), 1 hour of interactive teaching (DI, didattica interattiva) and 19 hours of individual study. For this 6-CFU course (150 hours) this amounts to:
- 30 hours of DE;
- 6 hours of DI;
- 114 hours of individual study (indicative: learning pace and style vary from student to student).
Each lecture combines two components:
- Lecture component (DE): the lecturer introduces the reasoning and computations behind widely used data analysis approaches in psychological and experimental science, with slides and worked examples.
- Practical component (DI): students implement each method in R on real or simulated data, individually and in small groups. After initial guidance from the lecturer, the focus is on developing students' ability to adapt heavily commented code to new data and questions.
Consistency with learning objectives. Lectures and individual study support the understanding of statistical reasoning; hands-on practice in R develops the ability to apply it, to make and justify analytical choices, and to report results.
Students should bring a laptop to class and install R and RStudio beforehand (https://posit.co/download/rstudio-desktop/). Because the course emphasises practical work, attendance is strongly recommended, although not compulsory. The lecturer is available for office hours by appointment.
Verifica Apprendimento
Assessment consists of a practical written exam, taken in person on a computer, identical for attending and non-attending students. It assesses the ability to apply the course content to a realistic research problem.
Format. Students receive a research scenario (background, hypotheses) and a dataset, which change from one exam session to the next. Within 2 hours and 30 minutes, they write a report of about 2 A4 pages (docx or pdf) answering a set of guided questions: they must choose and justify a data analysis approach, run it (preferably in R), and report and interpret the results as in a scientific paper. The report is sent to the lecturer by email before leaving the classroom. All materials and software are allowed (notes, slides, course code, books, online resources), except AI tools.
Scoring (30 points in total):
- design, descriptive statistics, null and alternative hypotheses: 4 points;
- data visualisation (choice and justification of the graph, caption): 4 points;
- choice and justification of the statistical test: 5 points;
- assumptions (identification and checking): 5 points;
- running the test, reporting and interpreting results (including p-values and effect sizes): 7 points;
- follow-up tests, effect sizes and confidence intervals: 5 points.
An optional bonus question (e.g., an exploratory analysis) is worth up to 3 additional points. It can compensate for points lost in the other questions.
Assessment criteria: appropriateness and justification of analytical choices; correctness of the analyses; quality and clarity of graphs and captions; accuracy of the interpretation in light of the research question; clarity of scientific reporting.
Final mark. The mark, out of 30, is the sum of the points obtained. The exam is passed with a score of 18/30 or higher. A total score of 31 or higher (including the bonus question) corresponds to 30 cum laude.
Results are communicated through the University portal.
Format. Students receive a research scenario (background, hypotheses) and a dataset, which change from one exam session to the next. Within 2 hours and 30 minutes, they write a report of about 2 A4 pages (docx or pdf) answering a set of guided questions: they must choose and justify a data analysis approach, run it (preferably in R), and report and interpret the results as in a scientific paper. The report is sent to the lecturer by email before leaving the classroom. All materials and software are allowed (notes, slides, course code, books, online resources), except AI tools.
Scoring (30 points in total):
- design, descriptive statistics, null and alternative hypotheses: 4 points;
- data visualisation (choice and justification of the graph, caption): 4 points;
- choice and justification of the statistical test: 5 points;
- assumptions (identification and checking): 5 points;
- running the test, reporting and interpreting results (including p-values and effect sizes): 7 points;
- follow-up tests, effect sizes and confidence intervals: 5 points.
An optional bonus question (e.g., an exploratory analysis) is worth up to 3 additional points. It can compensate for points lost in the other questions.
Assessment criteria: appropriateness and justification of analytical choices; correctness of the analyses; quality and clarity of graphs and captions; accuracy of the interpretation in light of the research question; clarity of scientific reporting.
Final mark. The mark, out of 30, is the sum of the points obtained. The exam is passed with a score of 18/30 or higher. A total score of 31 or higher (including the bonus question) corresponds to 30 cum laude.
Results are communicated through the University portal.
Testi
The bibliography is the same for attending and non-attending students.
Mandatory materials (available on Google Drive: http://bit.ly/3E6sH8u):
- slides and notes;
- R code used in class (heavily commented).
Optional materials:
- Field, A., Miles, J., & Field, Z. Discovering Statistics Using R. 1st ed., 2012. London: SAGE Publications;
- references provided in the slides;
- open-source online resources, e.g., the University of Edinburgh's statistics in R materials (https://uoepsy.github.io/) and the books available at https://bookdown.org/.
Mandatory materials (available on Google Drive: http://bit.ly/3E6sH8u):
- slides and notes;
- R code used in class (heavily commented).
Optional materials:
- Field, A., Miles, J., & Field, Z. Discovering Statistics Using R. 1st ed., 2012. London: SAGE Publications;
- references provided in the slides;
- open-source online resources, e.g., the University of Edinburgh's statistics in R materials (https://uoepsy.github.io/) and the books available at https://bookdown.org/.
Contenuti
The course consists of 12 lectures, each combining a theoretical and a practical (R) component. Topics:
1. Statistics and the inferential mind: samples and populations; probability distributions; the normal distribution, the central limit theorem and the standard error.
2. Introduction to R: basic operations and functions; simulating populations and the central limit theorem.
3. Fisher's approach to inferential tests: null-hypothesis significance testing, the z-test and p-values.
4. Neyman-Pearson's approach: confidence intervals and effect sizes (e.g., Cohen's d); covariance and Pearson's correlation; one-sample, independent-samples (Welch) and paired t-tests and their assumptions.
5. Omnibus tests: partitioning variance; independent and repeated-measures ANOVA and their assumptions.
6. Post-hoc tests: multiple comparisons and alpha inflation (Bonferroni, Holm, Benjamini-Hochberg); confidence intervals and effect sizes in ANOVA (e.g., eta squared).
7. Factorial ANOVA: main effects and interactions.
8. Regression analysis: continuous predictors, prediction, visualisation and multiple regression.
9. Everything is regression: t-tests and ANOVAs as special cases of regression (dummy coding, mixed predictor types).
10. Logistic regression and mixed-effects models: binary outcomes; the generalised linear model framework; fixed and random effects.
11. Pitfalls of null-hypothesis significance testing (replication, power, p-hacking) and recap.
Throughout the course, particular attention is given to data manipulation, data visualisation with high-quality graphs, and the interpretation and reporting of results.
1. Statistics and the inferential mind: samples and populations; probability distributions; the normal distribution, the central limit theorem and the standard error.
2. Introduction to R: basic operations and functions; simulating populations and the central limit theorem.
3. Fisher's approach to inferential tests: null-hypothesis significance testing, the z-test and p-values.
4. Neyman-Pearson's approach: confidence intervals and effect sizes (e.g., Cohen's d); covariance and Pearson's correlation; one-sample, independent-samples (Welch) and paired t-tests and their assumptions.
5. Omnibus tests: partitioning variance; independent and repeated-measures ANOVA and their assumptions.
6. Post-hoc tests: multiple comparisons and alpha inflation (Bonferroni, Holm, Benjamini-Hochberg); confidence intervals and effect sizes in ANOVA (e.g., eta squared).
7. Factorial ANOVA: main effects and interactions.
8. Regression analysis: continuous predictors, prediction, visualisation and multiple regression.
9. Everything is regression: t-tests and ANOVAs as special cases of regression (dummy coding, mixed predictor types).
10. Logistic regression and mixed-effects models: binary outcomes; the generalised linear model framework; fixed and random effects.
11. Pitfalls of null-hypothesis significance testing (replication, power, p-hacking) and recap.
Throughout the course, particular attention is given to data manipulation, data visualisation with high-quality graphs, and the interpretation and reporting of results.
Lingua Insegnamento
INGLESE
Altre informazioni
Announcements and course materials are published on the course's Google Drive folder (http://bit.ly/3E6sH8u).
Students with disabilities or specific learning disorders may agree on compensatory or dispensatory measures with the lecturer, through the dedicated University service.
Students with disabilities or specific learning disorders may agree on compensatory or dispensatory measures with the lecturer, through the dedicated University service.
Corsi
Corsi
PSYCHOLOGY, NEUROSCIENCE AND HUMAN SCIENCES
Laurea Magistrale
2 anni
No Results Found