Computational Statistics and Data Science is the application of high level techniques to complex data.

Computational statistics describes those areas of statistics that are necessarily highly computational. Researchers in this field usually have training in statistics, mathematics and computing. Research in computational statistics at McMaster includes work in bioinformatics, classification, clustering, EM algorithms, evolutionary algorithms, high-performance computing, latent variable models, mixed models, mixture models, and MM algorithms. From a mathematics and statistics perspective, data science can be viewed as the application of high level techniques to big, or otherwise complex, data. Often, no such high level technique is available and an approach must be developed to address a particular data question; when this happens, the approach developed is often a computational statistics approach; hence, the natural relationship between computational statistics and data science. At McMaster, researchers work on a wide range of data problems in areas such as health, biology, finance, and insurance.

Classification, clustering, computational statistics, data science, machine learning, mixture models

Data science, evolutionary algorithms, high-dimensional problems, machine learning, mixture models