Course Topics
Module 1 - Introduction to the course; Data distribution. Error types. Dependent and independent variables; quantitative and qualitative factors; fixed and random factors; Experimental designs for agricultural sciences. Module 2 - Introduction to R. Data exploration. Data representation. Module 3 - Student’s t Test; Introduction to lineal models; ANOVA: assumptions, data transformation, one- and two-ways. Post-hoc test. for multiple comparisons. Missing data. Linear mixed models: Analysis of repeated measurements in time and space. Analysis of split-plot designs and nested models. Introduction to the analysis of covariance. Module 4 Least Squares linear regression and correlation, multiple linear regression, breaking point analysis. Module 5 - Experimental designs for environmental sciences. Non-parametric test and non-parametric post-hoc tests. Module 6 - Alpha, beta and gamma diversity. Cluster analysis. Principal Coordinate Analysis (PCA). Principal component analysis of communities (PCoA). Non-metric Multi Dimensional Scaling (NMDS). Permutational multivariate ANOVA (PERMANOVA). Module 7 - Introduction into the statistical analysis of non-experimental data (e.g., surveys): cross-sections, time series and panel data analysis.

Teaching format
frontal lessons and exercises

Educational objectives
Knowledge and understanding Knowledge and understanding of main concepts and statistical methods for agricultural and environmental research. Applying knowledge and understanding Ability to choose the most suitable statistical approach to be used for tackling statistical problems in agricultural and environmental sciences. Ability to check the requisites a dataset should possess to become suitable for statistical analysis. Making judgements Ability to choose the most suitable statistical approach to be used for tackling statistical problems. Communication skills Ability to prepare graphs and tables using outcomes from statistical analysis. Learning skills. Ability to autonomously adapt the methods and tools to tackle novel statistical questions also taking advantage of the open-source software “R “.

Assessment
After the frontal teaching part, students must complete five class assignments, each of them on one teaching module, which will prove the students’ command on statistical procedures using R.

Evaluation criteria
Skills in critical thinking. Ability to choose suitable statistical approaches. Ability to correctly choose the statistical model and to understand the results of a statistical analysis.

Required readings

Handouts of the material presented and R scripts made available to the students. 

Supplementary readings

Gomez, K.A. and Gomez, A.A. (1984) Statistical Procedures for Agricultural Research. 2nd Edition, John Wiley and Sons, New York, 680 p.

Further information
Students are required to install Rstudio software on their computer RStudio (https://posit.co/download/rstudio-desktop/). R (“The R Project for Statistical Computing” at https://www.r-project.org)