NMAK15020U Statistical Computing

Volume 2015/2016
Education

MSc programme in Statistics
MSc programme in Mathematics-Economy

Content

The course will be on computational aspects of data analysis and cover the following topics:

  • Likelihood computations.
  • Numerical MLE. Smooth optimization. The EM-algorithm and variations.
  • Simulation algorithms. MCMC and bootstrapping.
  • Numerical linear algebra in statistics. Sparse and structured matrices.
  • Univariate and multivariate smoothing.
  • Practical implementation of statistical computations and algorithms.
  • R/C/C++ and RStudio statistical software development.

 

 

Learning Outcome

Knowledge:

  • algorithms for statistical data analysis
  • R packages that implement some of these algorithms
  • or are useful for developing novel implementations.

 

Skills: Ability to

  • implement
  • test
  • debug
  • benchmark
  • profile
  • and optimize statistical software

 

Competences: Ability to

  • select appropriate numerical algorithms for statistical computations
  • evaluate implementations in terms of correctness, robustness, accuracy and memory and speed efficiency.
Statistik 2 or similar knowledge of statistics. Linear algebra and the multivariate normal distribution are essential prerequisites. Some experience with R usage.
4 hours of lectures per week for 7 weeks.
2 hour presentation and discussion of a weekly assignment.
Every week an assignment on the implementation of a solution to a statistical computing problem will be given. Students will in turn present solutions in class followed by a plenary discussion of the solutions. The student's own solutions will form the basis for his or her oral examination.
  • Category
  • Hours
  • Exercises
  • 14
  • Lectures
  • 28
  • Preparation
  • 164
  • Total
  • 206
Credit
7,5 ECTS
Type of assessment
Oral examination, 25 min
During the course there will be a total of 6 weekly assignments. Each student prepares a presentation of the solutions during the course. At the oral exam a random selection of one of the 6 assignments must be presented without preparation. Based on the presentation the student then has to participate in a discussion with the examinator within the topics of the course.
Aid
All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
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.