Printable Handouts

PDF

Navigable Slide Index

1. Introduction
2. Outline
3. Why do a microarray experiment?
4. Why design a microarray experiment?
5. Four known design principles
6. A statistical toy model for gene expression
7. Normalization
8. Rephrasing our three questions
9. Pooling reduces biological variation
10. Optimal design in 2-channel microarrays
11. Optimal designs in R: function od
12. Loop designs are often optimal
13. But not always
14. Interwoven loop designs
15. Advantages of interwoven loop designs
16. Dye swap or dye balance?
17. Analysis
18. An example: microarray analysis
19. Keeping track of the model indices
20. Analysis of the data in R
21. Results
22. What does that mean?
23. And if you look at many genes simultaneously?
24. Conclusions
25. More of this in statistics for microarrays

Topics Covered

• Statistics is a vital tool in microarray studies
• From formulating the research questions, via cleaning up the data, to inferring the results, statistics is involved in all aspects of a microarray experiment
• Where the need for statistics comes from
• The omnipresence of artifacts in the data
• The considerable variability between replicates and the general (random) variation of the data

Links

Series:

• Microarrays

Categories:

• Methods

Talk Citation

Publication History

• Published on March 30, 2009
• Archived on February 25, 2021

Financial Disclosures

• Dr. Ernst Wit has not informed HSTalks of any commercial/financial relationship that it is appropriate to disclose.