- Oggetto:
- Oggetto:
Elaborazione dei dati sperimentali
- Oggetto:
Ecological Data Management and Analysis
- Oggetto:
Anno accademico 2015/2016
- Codice dell'attività didattica
- SVB0035
- Docente
- Dott. Valentina La Morgia (Titolare del corso)
- Corso di studi
- Laurea Triennale in Scienze Naturali D.M. 270
Laurea Magistrale in Evoluzione del Comportamento Animale e dell'Uomo (ECAU) D.M. 270 - Anno
- 3° anno
- Periodo didattico
- Secondo trimestre
- Tipologia
- A scelta dello studente
- Crediti/Valenza
- 4
- SSD dell'attività didattica
- BIO/05 - zoologia
- Modalità di erogazione
- Mista
- Lingua di insegnamento
- Inglese
- Modalità di frequenza
- Lezioni facoltative e esercitazioni obbligatorie
- Tipologia d'esame
- Prova pratica
- Prerequisiti
- There are no major requirements to follow this course. Having followed beforehand an introductory statistics course would however be helpful. We will anyway revise basic statistical concepts in the first lessons.
- Oggetto:
Sommario insegnamento
- Oggetto:
Obiettivi formativi
This course intends to gently introduce data management and modern analysis techniques and concepts to students in the Natural Sciences. While we will mostly use examples in the fields of Evolutionary and Behavioural Ecology, the course can be followed by students from other scientific domains. Classical, maximum- likelihood and Bayesian approaches will be introduced. The course will not be heavy on mathematics and statistical theory, trying instead to explain the concepts behind modern statistical tools mostly in a graphical and engaging way using interesting ecological examples. The teaching philosophy will be problem-solving oriented, and therefore students will have the chance to practically apply all the acquired concepts and methods to real data using the open-source statistical language “R” and the friendly “RStudio” interface. An introductory “R-Lab” will provide the necessary know-how in the use of these powerful tools. Specifically developed tutorials and interactive exercises will assist the student during the whole learning process.
- Oggetto:
Risultati dell'apprendimento attesi
At the end of the course it is expected that students will have acquired: 1) the essential tools to correctly manage and process field and experimental data before analysis; 2) a sufficient “statistical literacy” to autonomously judge which methods are most appropriate to use in a range of data analysis problems typically encountered in the natural sciences; 3) a good understanding of widely used modern statistical concepts and methods such as: Confidence and Credibility intervals, AIC, MCMC, maximum likelihood, etc.; 4) the ability to apply the learned theoretical concepts and methods to their own data using the powerful statistical language “R”; 5) the confidence to autonomously explore further more complex approaches;
- Oggetto:
Modalità di verifica dell'apprendimento
40 % of the final note will be based on a written exam with multiple choice and open answers and short statistical problems to solve using R (similar to those you will encounter as exercises during the course, but generally easier!). The remaining 60 % of the final note will be based on a short essay on an analysis of ecological data performed by each student. Students are encouraged to find on their own the ecological problem and data to analyse (it could for example be an analysis of data collected for their final thesis, or a re-analysis, with a different approach, of already published data). Links to online sources of open-access ecological data will be provided during the course. Suitable data analysis projects will be discussed beforehand with the instructor.
- Oggetto:
Programma
• What is data and how to handle it;
• Probability theory in a nutshell;
• Review of basic statistical concepts: Sampling distributions and their properties;
• What’s wrong with Null Hypothesis Testing? Shifting focus from “statistical significance” and p-values to effect size and confidence intervals;
• Maximum likelihood and Bayesian approaches to data analysis;
• Classical Linear models (Linear regression and ANOVA);
• Generalised Linear Models;
• Model selection and averaging: Information theoretic approaches;
• The problem of repeated measurements of the same individuals (pseudo-replication) and how to handle it: Introduction to hierarchical models;Testi consigliati e bibliografia
- Oggetto:
There will not be any official textbook for this course, but open access materials, tutorials and relevant review papers will be made available on the Moodle platform. A supplemental non-compulsory list of suggested books and papers will be provided and updated during the course.
- Oggetto:
Orario lezioni
Giorni Ore Aula Lezioni: dal 28/09/2015 al 15/01/2016 Nota: Consultare la tabella degli orari pubblicata sull'apposita pagina.
- Oggetto:
Note
First lesson postponed to Wednesday 22nd October, from 16:00 to 18:00 in Aula Lessona (Palazzo Campana)!
Afterwards lessons will follow the previously agreed schedule (Every Monday 14:00-17:00, Aula Lessona, Palazzo Campana)
Sorry for the inconvenience!
- Oggetto: