Experimental Design
Code: 104862 ECTS Credits: 6| Degree | Type | Year |
|---|---|---|
| 2503852 Applied Statistics | OB | 2 |
Contact
- Name:
- Llorenē Badiella Busquets
- Email:
- llorenc.badiella@uab.cat
Teaching groups languages
You can view this information at the end of this document.
Prerequisites
Knowledge in:
• Calculus
• Descriptive Statistics
• Statistical Programming
• Statistical Inference
• Statistical sampling
Objectives and Contextualisation
The objectives of the subject are to learn to design and analyze experiments using the following techniques:
- Analysis of the variance of one and several factors.
- Analysis of the variance with blocks, nested factors, fractional designs with interaction
- Analysis of Covariance and other special designs.
The subject is also intended to familiarize students with the use of SAS software.
Learning Outcomes
- CM09 (Competence) Assess the suitability of the models with the correct use and interpretation of indicators and graphs.
- CM09 (Competence) Assess the suitability of the models with the correct use and interpretation of indicators and graphs.
- CM10 (Competence) Modify the existing software if required by the statistic model, or create new software, if necessary.
- KM12 (Knowledge) Provide the experimental hypotheses of modelling, considering the technical and ethical implications involved.
- KM12 (Knowledge) Provide the experimental hypotheses of modelling, considering the technical and ethical implications involved.
- KM13 (Knowledge) Detect interactions, co-linearity and importance between explanatory variables.
- SM12 (Skill) Interpret the results obtained to formulate conclusions about the experimental hypotheses.
- SM13 (Skill) Compare the degree of adjustment between diverse statistical models.
- SM14 (Skill) Use graphs to visualise the fit and suitability of the model.
Content
Principles of Experimental Design.
• Objective
• Hypothesis
• Variables
• Bias control.
• Common designs
• Calculate sample size
Review Inference 1 and 2 populations:
• 1 Sample, known sigma
• 1 Sample unknown sigma
• 2 independent samples known sigma
• 2 independent samples unknown sigma
• 2 paired samples
1: ANOVA 1 Fully Randomized Factor
• Variance decomposition
• Model and ANOVA Table
• Contrasts
• Separation of Means - LSD / Bonferroni / Scheffe / Tukey
• Verification of the model (Levene Test, Waste Chart, Normality)
2: ANOVA 1 Block
• Fixed / Random Factor
• Variance decomposition
• Model and ANOVA Table
3: ANOVA 1 Factor with Complete Blocks
• Model and ANOVA Table
• Verification of the model
• Cross-Over Studies
4: ANOVA 1 Factor Blocks InComplete
• Latin squares
• Model and ANOVA Table
5: ANOVA 2 Factors
• Model and ANOVA Table
• Separation of Means - SNK / Dunnet / Other methods
6: ANOVA 2 Factors with Interaction
• Model and ANOVA Table
• Interactions
• Separation of Means - SNK / Dunnet / Other methods
7: ANOVA with Sub-Replicates
• Model and ANOVA Table
8: ANCOVA
• Model and ANOVA Table
9: ANCOVA with Interactions
• Model and ANOVA Table
• Interactions
10: Other models
• Basic concepts of Screening Design
• Basic Concepts of Factorial Design 2k
• Basic concepts of the Surface Response method
Software
• R
• SAS System
• SAS Enterprise Guide
Activities and Methodology
| Title | Hours | ECTS | Learning Outcomes |
|---|---|---|---|
| Type: Directed | |||
| Report | 20 | 0.8 | |
| Theory | 60 | 2.4 | |
| Type: Supervised | |||
| Prąctiques | 25 | 1 |
There will be theoretical sessions where the concepts related to the design of studies and experiments will be exposed.
These sessions will be complemented by practical sessions in a computer room where dedistance will be done with Statistical software.
All the above concepts will be applied through a work that can be done in a group.
Annotation: Within the schedule set by the centre or degree programme, 15 minutes of one class will be reserved for students to evaluate their lecturers and their courses or modules through questionnaires.
Assessment
Continous Assessment Activities
| Title | Weighting | Hours | ECTS | Learning Outcomes |
|---|---|---|---|---|
| Exam | 55 | 15 | 0.6 | KM12, KM13, SM12, SM13 |
| Practical Sessions | 15 | 15 | 0.6 | CM09, KM12, KM13, SM12, SM13, SM14 |
| Report | 30 | 15 | 0.6 | CM09, CM10, KM12, KM13, SM12, SM13, SM14 |
Continuous evaluation:
Report 40% (Minimum grade 4)
Practices 15%
Partial Exam 45% (Minimum grade 4)
Reassessed:
Maximum between:
100% final exam
Report 40% + Exam 60% (Minimum grade 4)
Bibliography
References
- Estadística para investigadores – Box, Hunter, Hunter – Ed. Reverté
- Estadística. Modelos y Series Temporales. Daniel Peña – Ed. Alianza
- Principles and procedures of statistics, a biometrical approach 2nd Ed – Steel, Torrie – McGraw Hill
- Biostatistics: A foundation for analysis in the health sdciences. 4th Ed – Steel, Torrie – John Willey & Sons
- Design and Analysis of Experiments – Dean , Voss – Springer-Verlag New York, 1999
- Peña, D. (1998) Estadística. Modelos y Métodos. Tomo I: Fundamentos. Alianza Universidad Textos.
- Montgomery, DC. (2001). Design and Analysis of Experiments. John Willey and sons.
Software
SAS
Language list
| Name | Group | Language | Semester | Turn |
|---|---|---|---|---|
| (PAUL) Classroom practices | 1 | Catalan | second semester | afternoon |
| (PLAB) Practical laboratories | 1 | Catalan | second semester | afternoon |
| (PLAB) Practical laboratories | 2 | Catalan | second semester | afternoon |
| (TE) Theory | 1 | Catalan | second semester | afternoon |