Computer-intensive Statistics

The course is included in the program PHD in science. Registration deadline for PhD students at UiT - The Arctic University of Norway: February 1st.

The course is also available as a singular course.

The course covers stochastic sampling techniques, Monte Carlo simulation, bootstrapping, and optimization methods like the Expectation-Maximization (EM) algorithm and simulated annealing. The course also includes Bayesian inference, Markov chain Monte Carlo (MCMC) methods, and an introduction to the methodology of integrated nested Laplace approximations (INLA).

Oral presentations will be required.

PhD students or holders of a Norwegian master´s degree in Sceince of five years or 3 + 2 years (or equivalent) may be admitted. In your educational background you need statistical courses of at least 30 ECTS credits which includes a thorough discussion of statistical methods and principles.

PhD students from other universities must upload a document from their home institution stating that there are registered PhD students. This group of applicants does not have to prove English proficiency and are exempt from semester fee.

Holders of a Master´s degree must upload a Master´s Diploma with Diploma Supplement / English translation of the diploma. Applicants from listed countries must document proficiency in English.

For more information on accepted English proficiency tests and scores, as well as exemptions from the English proficiency tests.

PhD students at UiT The Arctic University of Norway register for the course through StudentWeb .

External applicants apply for admission through SøknadsWeb.

All external applicants have to attach a confirmation of their status as a PhD student from their home institution. Students who hold a Master of Science degree, but are not yet enrolled as a PhD-student have to attach a copy of their master's degree diploma. These students are also required to pay the semester fee.

Application code 9301 - Enkeltemner på ph.d.-nivå

The course introduces key computational methods for solving statistical problems in both frequentist and Bayesian settings. It provides a solid theoretical foundation for these methods. Upon successful completion of the course, students will be able to

• Implement stochastic sampling techniques, perform Monte Carlo integration, and apply variance-reduction methods.
• Implement and apply bootstrap methods for statistical inference. This includes understanding the bootstrap principle and using bootstrapping to approximate sampling distributions, standard errors, confidence intervals, and perform hypothesis testing.
• Apply the EM-algorithm to maximize likelihood functions or posterior distributions, particularly in problems involving latent or missing data.
• Implement simulated annealing as a stochastic optimization algorithm, including its application to the travelling salesman problem.
• Implement MCMC methods, such as the Metropolis-Hastings algorithm and Gibbs sampling, and assess their convergence and performance.
• Explain the key principles of the INLA methodology and use it to perform approximate Bayesian inference for regression models within the class of latent Gaussian models.

If you pass the examination in this course, you will get an reduction in credits (as stated below), if you previously have passed the following courses:

• STA-3001 Computer-intensive Statistics 10 ects

Language of instruction and examination

Schedule

Re-sit examination