Biostatistics 2
Code
101001
Academic unit
NOVA Medical School | Faculdade de Ciências Médicas
Credits
5
Teacher in charge
Profª. Doutora Ana Luisa Trigoso Papoila da Silva
Teaching language
Portuguese
Objectives
After a hands-on practical revision of all the statistical methodologies introduced in the previous semester in the Biostatistics I curricular unit, focus will be given to the multivariable analysis using, mainly, a practical approach. The aim of the present curricular unit involves the learning of data modelling when the outcome variable follows different types of distributions. More in-depth concepts and knowledge will be given to the following statistical methods: linear, logistic and Cox regression models. Detail will be given to the checking of the assumptions of applicability of each model as well as the use of residual analysis for that purpose. This curricular unit should promote the following skills: a) to identify the distribution of the response variable; b) to identify the independent variables and potential confounders; c) to select and implement the most adequate regression model; d) to verify models assumptions by a residual analysis and e)to interpret the results.
Prerequisites
Previous knowledge of Bioestatistics and SPSS.
Subject matter
Hypotheses tests revision: tests for two independent samples, tests for paired samples, Chi-square test, Fishers exact test and McNemars test. Non-parametric tests for more than two independent (Kruskal-Wallis) and related samples (teste de Friedman). Univariate analysis of variance: general assumptions and multiple comparisons. Multivariate analysis of variance: one-way and two-way, assumption validation. Analysis of variance with repeated measures. Linear regression model: model fitting, residual analysis and interpretation. Logistic regression model: model fitting, residual analysis and interpretation. Cox regression model: model fitting, residual analysis and interpretation.
Bibliography
1. Daniel, W.W. (2008). Biostatistics: A foundation for analysis in the health sciences. 9th edition. John Wiley & Sons.
2. Katz, M. H. (2011). Multivariable Analysis: A Practical Guide for Clinicians and Public Health Researchers (third edition). Cambridge University Press, UK.
3. Kleinbaum, D.G. and Klein, M. (2010). Logistic Regression: A Self-Learning Text (third edition). Springer-Verlag.
4. Kleinbaum, D.G. and Klein, M. (2005). Survival-Analysis: A Self-Learning Text (second edition). Springer-Verlag.
5. Pestana, M. H. e Gageiro, J.N. (2005). Análise de dados para ciências sociais: A complementaridade do SPSS. Edições Sílabo, Lisboa.
Teaching method
Teaching is mainly practical based in the resolution of exercises using SPSS. Interaction between students and teachers is both at the classroom and by e-mail. Classes will take, at most, 120 minutes and will take place at a classroom with computers (1 for each student).
Evaluation method
To assess students performance, a formal written examination will take place where exercises must be solved using SPSS. Additionally, a dataset will be made available to the students to analyse by using the statistical methodologies that were taught.
The teaching evaluation will be performed by the anonymous and voluntary response of a questionnaire, aiming to collect the opinion concerning the learning objectives, syllabus, evaluation methodology, integration of the different themes, as well as the quality and performance of the different teachers.