Pre - Conference Workshops
Prof Saralees Nadarajah
University of Manchester
Prof Nadarajah is a Reader in the Department of Mathematics, University of Manchester, UK. His research interests include climate modeling, extreme value theory, distribution theory, information theory, sampling and experimental designs, and reliability.
Extreme values & financial risk
The course will give some probabilistic and statistical details of univariate and bivariate extreme value theory. The topics covered will include: fundamental of univariate extreme value theory, the three extreme value distributions, various models for univariate extremes, fundamentals of bivariate extreme value theory, and various models for bivariate extremes. The course will contain material on applications of the models to finance.
Date: 30 November 2021
Time: 13:30 – 15:30 & 16:00 – 17:30
Dr Ali Joglekar
University of Minnesota
Dr Joglekar’s current research focuses on the spatially-explicit characterization of farming and its implications on agricultural productivity throughout the developing and developed world. She is also a Research Associate of the GEMS (genomic, environmental, management and socio-economic) information center.
Explicitly Accounting for Location in Agriculture: Spatial Data Analysis in R
Abstract: TBA
Date: 30 November 2021
Time: 14:00 – 15:30 & 16:00 – 18:00
Dr Marcel Dunaiski
Stellenbosch University
Dr Dunaiski is a lecturer at Stellenbosch University at the Computer Science division and researcher for the School of Data Science and Computational Thinking. He is interested in anything to do with data science but specialises in the field of Scientometrics and ranking algorithms.
Practical Introduction to Natural Language Processing
This workshop will introduce you to the basics of NLP using R. It will introduce you to R libraries using practical NLP applications to process text (lemmatization, POS tagging, and stemming) and extract information from unstructured text (named entity recognition, terminology extraction, and summarization).
Date: 30 November 2021
Time: Full day workshop
Prof Kanshukan Rajaratnam
Stellenbosch University
Prof Rajaratnam is the Director of the School for Data Science and Computational Thinking and an Associate Professor in the Department of Statistics and Actuarial Science at Stellenbosch University. His research interests are in the intersection of Data Science, Operations Research and Banking/Finance.
http://www.sun.ac.za/english/data-science-and-computational-thinking/Pages/Our-director.aspx
Basic Python Programming
In this workshop, we introduce basic Python syntax which may then be used to analyse and plot data. The workshop is open to anyone with a basic programming knowledge. It is also aimed at Grade 10 and 11 school students with a keen interest in Data Science, Computation and / or Mathematics.
Date: 29 & 30 November 2021
Time: 13:30 – 15:30, 16:00 – 17:00
Riana Coetsee
Stellenbosch University
Riana is the Manager: International funding and capacity development at the Division for Research Development of Stellenbosch University. In this capacity, she has vast experience of grant writing and annually present this workshop for university staff and post graduate students.
The Fundamentals of Grant Proposal Writing
Although funding organisations and their application requirements differ, there are important elements expected from all funding agencies, whether it relates to small or to large grants.
The following elements will thus be discussed and practised in the workshop:
• Basic structure of a grant proposal
• Market your research and market yourself
• Why grant proposals fail
• Explaining peer review panels
• Common core components of grant proposals
• The budget
• Where to look for funding
Participants will understand the following:
• What basic and core components an application should have to make it competitive
• What pitfalls should be avoided when writing grant proposals
• What elements should be included in the budget
• Where to start looking for funding
Although a recording of the course will not be made available afterwards, at the end of the course you will receive a document summarising the content of the workshop, as well as additional reading materials. The course material will only be provided to registered participants.
Date: Session 1 - 29 November 2021
Session 2 - 30 November 2021
Time: 09:00 – 10:30 & 11:30 – 13:00
Multivariate Data Analysis Group
Date: 29 November 2021
Time: Full day workshop
This workshop is a compendium of five presentations on different topics in multivariate data analysis.
| 08:30-10:00 | Sean van der Merwe (UFS) | Multivariate Data Analysis via Stan Modelling Software |
| 10:15-11:45 | Divan Burger (UP) | Bayesian linear and nonlinear mixed-effects regression models for zero-inflated and highly skewed longitudinal count data |
| 12:00-13:00 | Nicolene Cochrane (ARC) | Best cultivar recommendations for crops for a particular area by calculating yield probability percentages |
| 13:00-13:15 | MDAG AGM | MS Teams link will be sent to all MDAG members. |
| 14:00-15:00 | Raeesa Ganey (WITS), Johané Nienkemper-Swanepoel (SU) & Carel van der Merwe (SU) | Aspects of multidimensional visualisation |
| 15:15-16:45 | Invited speaker: Angelos Markos (Greece) | Joint Dimension Reduction and Clustering in Practice |
More information on all sessions to follow soon:
Session: Joint Dimension Reduction and Clustering in Practice
Instructor: Assoc. Prof. Angelos Markos, Democritus University of Thrace, Greece.
Description: Joint dimension reduction and clustering (JDRC) refers to a class of multivariate data analysis methods that perform simultaneous dimension reduction and clustering of continuous, categorical or mixed-type data. The key idea of JDRC is that both clustering of objects and a low dimensional subspace reflecting the cluster structure are simultaneously obtained. This online short course explains the main features of this class methods, with illustrations to real data in a variety of contexts.
Background:
Markos, A., Iodice D’Enza, A., & van de Velden, M. (2019). Beyond tandem analysis: Joint dimension reduction and clustering in R. Journal of Statistical Software (Online), 91(10). URL: https://github.com/amarkos/JDRCinPractice
van de Velden, M., Iodice D'Enza, A., & Markos, A. (2019). Distance‐based clustering of mixed data. Wiley Interdisciplinary Reviews: Computational Statistics, 11(3), e1456.
Software:
R, open source, with the R package “clustrd” installed
Course Material. All course materials, including the data and R scripts for the examples, will be made available for workshop participants.