Introduction to cause-effect reasoning in biomedicine through the study of the principale survey designs. Provide an overview of data analysis techniques in environmental and clinical epidemiology.
Introduction to cause-effect reasoning in biomedicine through the study of the principale survey designs. Provide an overview of data analysis techniques in environmental and clinical epidemiology. At the end of the course the students will have acquired sufficient theoretical knowledge to identify and apply the most appropriate models for the analysis of biomedical data. In particular:
- adequacy of the model;
- satisfaction of the hypotheses of applicability of the model;
- representation and interpretation of the results;
- implementation of the models in a high-level programming language.
The teaching takes place mainly through frontal lessons. A significant part of the hours is dedicated to PC exercises using the statistical methodologies implemented on the SAS software, applied to real cases from the environmental and clinical epidemiological sector.
Introduction. Analysis of the causal relationship in biomedicine and epidemiology.
Epidemiological methodology. Observational investigations. Geographical studies and cross-sectional investigation. Analytical cohort and case-control studies. Experimental investigations in clinical epidemiology. Frequency of health outcomes: prevalence, incidence, survival, mortality. Relative frequency indices of health outcomes: rate, risk and odds.
Statistical methods. Review of simple and multiple linear regression with continuous and categorical predictors. Introduction to multiplicative models. The log-normal regression model, the ratio of median values and the median percent change. The Poisson model for the analysis of health event rates in geographic epidemiology and the analysis of the temporal trend. Average percentage change. Heterogeneity in the counts and the negative binomial model. Evaluation of the diagnostic performance of a binary clinical test: signal and noise, conditional probabilities and Bayes formula: sensitivity, specificity, predictive values and prevalence. Evaluation of the diagnostic performance of a clinical test measured on an ordinal or continuous categorical scale: construction and interpretation of a ROC curve. The logistic model for binary health events with application to the case-control study. Evaluation of the statistical performance of a logistic model through the ROC curve. Models for survival time analysis: limit product method and Cox regression.
Fontana V , Parodi S, Puntoni M, Tazzer C, Viarengo P. Dispensa del Corso di Metodi Statistici in Ambito Biomedico, Parte 1 e 2 (distribuita gratuitamente)
Ricevimento: By appointment via email.
CRISTINA CAMPI (President)
EVA RICCOMAGNO
VINCENZO FONTANA (President Substitute)
GIACOMO SIRI (President Substitute)
The class will start according to the academic calendar.
Three weeks before the exam date, the student is provided with a dataset that has to be elaborated according to some proposed questions. The exam is structured as a presentation and discussion of about 30 minutes of the obtained results.
Students with DSA certification ("specific learning disabilities"), disability or other special educational needs are advised to contact the teacher at the beginning of the course to agree on teaching and examination methods that, in compliance with the teaching objectives, take account of individual learning arrangements and provide appropriate compensatory tools.
The exam is aimed at verifying the student's skills in applying the statistical methods for analyzing the data provided, according to the proposed questions.
Students who have valid certification of physical or learning disabilities on file with the University and who wish to discuss possible accommodations or other circumstances regarding lectures, coursework and exams, should speak both with the instructor and with Professor Sergio Di Domizio (sergio.didomizio@unige.it), the Department’s disability liaison.
