NMAK13017U Multiple Testing and Bootstrap Techniques

Volume 2013/2014
Education
MSc Programme in Mathematics
MSc Programme in Statistics
Content
Introduction to multiple testing, and parametric and non-parametric bootstrap techniques in relation to multipe testing. The course will discuss different concepts, p-value, q-value, False Discovery Rate (FDR) and False Non-discovery Rate (FNR), discuss multiple testing in Bayesian and frequentist settings and apply the techniques to genetic and genomic data sets containing thousands or millions of variables.
Learning Outcome

Knowledge
At the end of the course the student will have knowledge about different procedures to correct for multiple testing and different bootstrap procedures for simulating empirical distibutions of test statistics. The student will have the knowledge to
* explain basic issues in relation to multiple testing
* explain different procedures for multiple testing and the rationale behind them
* explain p-value, q-value, FDR and FNR
* explain frequentist and Bayesian settings of multiple testing
* explain different parametric and non-parametric bootstrap procedures

Skills
The student will acquire the skills to apply and decide among different procedures for multiple testing, and to conduct different parametric and non-parametric bootstrap procedures on large data sets. The student will have the skills to utilize theoretical results in practical analysis.

Competencies
At the end of the course the students will have the competence to
* carry out statistical analysis in (selected) multiple testing settings
* understand and use in practical situations the concepts of p-value, q-value, FDR, and FNR
* interpret multiple testing results in frequentist and Bayesian settings
* perform different parametric and non-parametric bootstrap methods for simulating test distributions
* use bootstrap methods in multiple testing settings
* correct for dependencies between test statistics
* apply the techniques to real-world genomic data sets
Stat2 or similar.
4 hours of lecturing, 3 hours of exercise classes per week for 7 weeks.
  • Category
  • Hours
  • Exam
  • 45
  • Lectures
  • 28
  • Practical exercises
  • 12
  • Preparation
  • 112
  • Theory exercises
  • 9
  • Total
  • 206
Credit
7,5 ECTS
Type of assessment
Written examination, 24 hrs
24 hours take-home exam.
Aid
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
One internal examiner.
Re-exam
30 minuttes oral exam with several internal examiners.
Criteria for exam assesment

The student must in a satisfactory way demonstrate that he/she has mastered the learning outcome of the course.