Statistics: Master Course - Statistical Methods for Data Science (course package)

Course Package Contents

The following courses are included in the package:

STAN48 Statistics: Programming for Data Science, 7.5 cr.

In this course, you will learn modern statistical computing as viewed in data science through implementations in popular computing platforms such as R and Python. You will learn the R and Python environment, and to use the R packages and Python modules for statistics and working with data frames, arrays, and matrices. You will also learn methods for generating random variables, Monte Carlo methods, and bootstrap and resampling methods. Furthermore, the course will cover Bayesian computing and Markov Chain Monte Carlo methods. Optimisation and other numerical methods are also included.

STAN51 Statistics: Machine Learning from a Regression Perspective, 7.5 cr.

In this course, you will the basics of machine learning and doing so by focusing on those methods that build in one way or another on standard regression analysis. Some of the topics covered are classification based on logistic regression, model selection using information criteria and cross-validation, shrinkage methods such as lasso, ridge regression and elastic nets, dimension reduction methods such as principal components regression and partial least squares, and neural networks. You will find that theoretical studies are interwoven with empirical applications.

STAN52 Statistics: Advanced Machine Learning, 7.5 cr.

The course is a continuation of STAN51 where you will deepen your knowledge in machine learning methods. Some of the topics covered include bootstrapping, ensemble methods such as boosting and random forests, unsupervised machine learning methods such as PCA and clustering algorithms as well as applications of machine learning methods to problems, such as causal inference and text analysis. Theoretical studies are interwoven with empirical applications.

STAN53 Statistics: High-dimensional Data Analysis, 7.5 cr.

The central theme of the course is multivariate and high-dimensional data. Statistical methods presented include both classic multivariate methods, e.g. principal component analysis, factor analysis, discriminant analysis, and cluster analysis, and modern high-dimensional methods using e.g. penalisation, functional analysis, and methods for sparse matrices.

STAN47 Statistics: Deep Learning and AI Methods, 7.5 cr.

This course presents an application-focused and hands-on approach to learning neural networks and reinforcement learning. It can be viewed as first introduction to deep learning methods, presenting a wide range of connectionist models, which represent the current state-of-the-art. It explores the most popular algorithms and architectures in a simple and intuitive style. You will learn the fundamentals of machine learning, and the mathematical and computational prerequisites for deep learning. The course covers feed-forward neural networks, convolutional neural networks, and the recurrent connections to a feed-forward neural network.

STAN49 Statistics: Analysis of Textual Data, 7.5 cr.

The course provides an introduction to statistical analysis of text. You will study both methods based on classic statistical approaches (including Bayesian models) and modern approaches such as deep learning and recurrent neural networks. Topics covered include text representation, text classification, text clustering, topic modelling, sentiment analysis and text summarisation.

STAN40 Statistics: Thesis, 15 cr.

Thesis course where you write a Master’s thesis.

After the Courses

After the courses, you will be well equipped for a career as statistician, data scientist or analyst.

If you complete all the courses, and otherwise fulfil the requirements for the degree, you can apply for a Degree of Master of Science in Statistics (60 credits).