Page 149 - FULL FINAL HANDBOOK 20232024

Faculty of Science Handbook, Academic Session 2023/2024

Exploratory analyses: dimensional reduction methods
such as principal components analysis and linear
discriminant analysis. Feature selection.
SIT3022 PROBABILITY THEORY
Supervised learning: artificial neural networks, k-nearest
neighbours, logistic regression, naïve-Bayes, Probability measure and space, sigma field. Lebesgue
classification and regression trees, or support vector integration. Random variables, measurability,
machine. Ensemble methods: bagging, random forest, independence. Distribution functions. Inequalities,
and boosting. Unsupervised learning: K-means and characteristic functions. Various modes of convergence
hierarchical clustering. of sequences of random variables. Classical limit
theorems. Examples of applications.
Assessment:
Continuous Assessment: 50% Assessment:
Final Examination: 50% Continuous Assessment: 50%
Final Examination: 50%
SIT3018 NON-PARAMETRIC STATISTICS
SIT3023 STATISTICAL LABORATORY
Introduction to hypothesis testing, sign test and signed
rank test, Mann-Whittney test, Kruskal-Wallis test, runs Use of functions and commands in statistical packages
test, contingency tables, median test, goodness of fit for exploratory data analysis, modelling and statistical
test, Spearman's rank test, Kolmogorov Smirnov test, inferences. Coding and programming using statistical
permutation test, kernel density estimation, spline software to solve statistical problems.
regression estimation.
Assessment:
Assessment: Continuous Assessment: 50%
Continuous Assessment: 40% Final Examination: 50%
Final Examination: 60%
SIT3024 STATISTICAL CONSULTANCY
SIT3019 INTRODUCTION TO BAYESIAN AND DATA ANALYSIS
STATISTICS
Introduction to consultancy activities and consulting
Bayes' Theorem. Bayesian framework and terminology. methods. Related problems and issues. Exposure to the
Bayesian inference. Prior formulation. Implementation use of primary and secondary data from various sources.
via posterior sampling. Bayesian decision theory. Application of suitable statistical methods such as
Hierarchical models. Application to real-world problems. multivariate analysis, regression and time series in the
analysis of real data. Producing report and presenting
Assessment: the findings that suit the needs of the client.
Continuous Assessment: 40%
Final Examination: 60% Assessment:
Continuous Assessment: 100%
SIT3020 PYTHON FOR DATA SCIENCE
SIT3025 STATISTICAL SCIENCE PROJECT
Description: Introduction to Python programming;
Control statement and program development; Python Subject to supervising lecturer.
data structures, strings and files; Functions; Lists and
Tuples; Dictionaries and sets; Array-oriented Assessment:
programming with NumPy; Pandas series and Continuous Assessment: 100%
DataFrame; Data wrangling; Object-oriented
programming; Python libraries for data analysis such as
Jupyter Notebook, SciPy, mglearn and matplotlib.
Data science: Basic descriptive statistics; Simulation and
static/dynamic visualisation; data mining tools such as
principal component analysis and discriminant analysis.
Big Data and Cloud case study: Deep learning;
convolutional and recurrent neural networks;
Reinforcement learning; Network analysis.
Assessment:
Continuous Assessment: 50%
Final Examination: 50%
SIT3021 INDUSTRIAL TRAINING
Candidates are required to spend a minimum of 16
weeks working with selected companies in selected
areas of industry.
Assessment:
Continuous Assessment: 100%
149