Data-driven inference for stochastic dynamics

Utbildningsfakta

Kod: MAAD35

Module 1: Stochastic Dynamics <br> The module treats the basic theory and practice of stochastic dynamics. Theoretical key concepts include: stochastic integral, Itô formula, stochastic differential equations (SDE), existence and uniqueness of strong solutions, martingales, Markov property. Practical implementation (in R or Python) of Euler-Maruyama and Milstein methods for numerical solution of SDEs. Module 2: Estimation for SDEs and Markov Chains <br> The module covers the theory of maximum likelihood and quasi-maximum likelihood estimations as well as Bayesian inference. Practical implementation (in R or Python) of Markov Chain Monte Carlo methods and the Metropolis-Hastings algorithm and its variants. Module 3: Bayesian Filtering <br> The module treats the theory and practice of filtering. Theoretical key concepts include Kalman filters, extended Kalman filters, particle filters, and nonlinear filtering. Practical implementation (in R or Python) of filters with various datasets and models.

Behörighet

90 ECTS credits in Mathematics, including 30 ECTS credits at the G2F level, and upper secondary level English 6, or equivalent

Utbildningstillfällen

Varje tillfälle har egna datum och villkor. Avslutade tillfällen behålls som historik och innebär inte att en ny ansökan är öppen.

• Data-driven inference for stochastic dynamics

  Karlstad University

  Karlstad

  Startdatum: 18 januari 2027

  Slutdatum: 6 juni 2027

  Studietakt: 25 %