Entry requirements

120 credit points including Analysis of Regression and Variance or corresponding course

Learning outcomes

In order to pass the course (grade 3) the student should

have a thorough knowledge about statistical techniques that have been developed during the last decades due to increasing computer capacity;

understand the theoretical foundation of Markov Chain Monte Carlo methods and be able to use such techniques;

understand the principles behind random number generators;

be able to use simulation methods such as Bootstrap and SIMEX;

be able to use computer-intensive non-linear statistical methods;

be familiar with EM methods;

be able to use non-parametric statistical models;

have some experience of applications from image analysis and financial mathematics;

be able to use statistical software, preferably R.

Content

Resampling techniques, Jack-knife, bootstrap. Non-linear statistical methods. EM algorithms. SIMEX methodology. Markov Chain Monte Carlo (MCMC) methods. Random number generators. Smoothing techniques. Kernel estimators, nearest neighbour estimators, orthogonal and local polynomial estimators, wavelet estimators. Splines. Choice of bandwidth and other smoothing parameters. Applications. Use of statistical software.

Instruction

Lectures, problem solving sessions and computer-assisted laboratory work.

Assessment

Written and, possibly, oral examination (4 credit points) at the end of the course. Assignments and laboratory work (6 credit points) during the course.