Statistics for Experimentation

After reviewing statistical inference (estimation, tests on one or two populations), the course introduces the classic experimental designs used in agronomy for one or two factors and focuses on the usual statistical approaches associated with them (ANOVA, linear Gaussian model with fixed effects). Emphasis is placed on the conditions underlying the application of statistical methods, the validation of the statistical models used, and the interpretation of software outputs. The R software, under the Rcommander interface, is used for statistical processing.

• Be able to propose an experimental design suited to the questions asked and the relevant working environment.
• Be able to conduct statistical research appropriate to the given context and draw well-argued conclusions regarding the questions posed.

Hourly volumes:

            CM: 27

            TD: 27

• Descriptive statistics

Recommended prerequisites:

• Knowledge of probabilistic tools: random variables; discrete and continuous probability distributions; expectation and variance of a random variable.