| |
:: Course SummaryThis 2-day hands-on workshop presents classical techniques to design efficient experiments as well as the tools to analyze their results.
The principles of sample size calculations, strategies to remove undesirable sources of variability like the use of blocks and controls, as well as the most commonly used experimental designs are discussed.
The statistical analysis of designed experiments is progressively introduced, starting with the t-test method used to compare two groups. Then, the analysis of variance technique (ANOVA) is extensively covered from simple one-factor experiments to more advanced multi-factor situations where the interaction between factors needs to be considered. Multiple comparisons techniques used to locate differences are also presented.:: Learning ObjectivesUpon completion of this training course, participants will be able to:
Understand why planning an experiment is important and the benefits in R&D
Learn the experimental designs most widely used in practice
Choose an appropriate experimental design based on the study objectives
Construct and implement the design selected
Analyze the data collected based on the design used and its underlying assumptions
Interpret the results of the experiment and report the conclusions:: Target AudienceThis applied training session in statistics is aimed at all scientific staff who wish to design and implement efficient studies and experiments and who must make decisions based on the data collected.:: PrerequisiteParticipants should have an excellent working knowledge of the following topics:
Mechanism underlying the calculation and the interpretation of accurate and robust estimators of centrality and dispersion such as: mean, median, standard deviation, standard error, coefficient of variation, quartiles, interquartile range
Understand how a box-plot is constructed and how to use it
The hypothesis testing approach
The construction and interpretation of confidence interval and p-values
α and β risks and their impact on the scope and the precision of the results
Power and sample size
If this is not the case, participants must attend the training session Fundamental Tools in Statistics. This training course is held the day before « Introduction to the Design of Experiments ». :: Notes and Other InformationSome association members are entitled to discounted registration fees. During the online registration process, do not forget to mention the association name, your membership number and the registration fees will be adjusted if you are entitled to a discount. | | |
:: Topics Covered
- Sources of Variability
- Why Plan an Experiment: Measurement Variability and Measurement Error
- The Notion of Experimental Unit
- Controlling and Minimizing Variability: Replication, Randomization, Blocking and Controls
- Integrating Experimental and Budgetary Constraints into the Experimental Design
- Constructing Experimental Designs
- Two-Sample Designs (Complete Randomized Design, Paired Comparison Design)
- Factorial Designs for more than Two Groups (Unreplicated and Replicated)
- Statistical Analysis Tools
- Exploratory Analysis
- Student's T-Test (Independent and Paired T-Test) : to compare two groups or treatments: principle, illustration & interpretation
- Analysis of Variance (ANOVA) / F-Test: to compare more than two groups or treatments: principle, illustration & interpretation
- The Notion of Interactions between Factors
- Locating Statistical Differences: Multiple Comparison Techniques
- Understanding and Interpreting Results from Real Data
:: Course Content
Statistics is the art of gathering, presenting, analyzing and utilizing data in order to facilitate decision making and problem solving.
Statistics play an important role in all steps of the experimental process and too often is the use of statistics confined to the post-experimental phase, namely the analysis of results. Statistical involvement at pre and post stages of the experiment actually facilitates the research process, while ensuring the reliability and the precision of the results as well as maximizing the power of the statistical tests.
This 2-day training provides an overview of Design of Experiments (DOE) and the issues involved in implementing a design. The purpose and applications of the DOE are reviewed. The different sources of error and variability as well as the tools available to minimize this variability – repetition, randomization, blocking and controls – are discussed.
Experimental designs, from simple to complex designs, are reviewed -comparison of two samples (independent or paired), factorial designs for more than two samples – along with the corresponding statistical tool – Student t-test, Analysis of Variance (ANOVA) F-test. The notion of breaking down the components of variability when performing an ANOVA is emphasized. Moreover, the notion of an interaction between two factors and how to test for one will also be explained in detail.
The principle of multiple comparisons will also be covered, illustrated by the Least Significant Difference method.
Following this training session, the design and implementation of studies with several experimental variables will be facilitated by the use of powerful and efficient statistical tools. Consequently, the analysis of the data collected will provide faster, more reliable and accurate results.
| |
