1. Types of variables (properties, distribution function, graphical representation). Continues and discrete variables. Categorical variables, order variables and rates. Measurement of continuous variables.
2. Types of association between variables: correlation and dependency. Coefficients of correlation, multiple correlation, regression and determination. Properties of the correlation and regression models.
3. Continuous variables dependent on discrete or categorical variables (ANOVA, random blocks, repeated measures, nested ANOVA, multiday ANOVA). Interaction terms (interpretation).
4. Continuous variables dependent on continuous variables (multiple regression). Choice of terms and order of terms in multiple regression.
5. Continuous variables dependent on continuous and discrete or categorical variables (ANCOVA). Assumptions and limitations of ANCOVA.
6. Fixed and random factors and mixed models.
7. Proportions dependent of continuous variables (logistic models and survival curves)
8. Log-linear models for frequency analysis.
9. Assumptions and limitations of linear models. Variable transformation (linearization, homogeneity of variance, normality)
10. The Generalized linear model
11. Non-linear models and non parametric model fitting
12. Maximum likelihood estimation
13. Parameter estimation through resampling techniques (Jacknife, Bootstrap and Monte Carlo)
14. The general additive model
15. Guidelines for experimental design and data analysis
At least one statistics course at the university level (basic probability theory and distribution of sample statistics)
Capacity to choose appropriate models for a given set of variables. Capacity to use a statistical analysis software package (understanding menu choices and outputs for modelling routines).