Master of Science in Biostatistics
Duration : 2 Years
Credits : 180
This programme equips students with advanced knowledge and understanding of statistical methods as applied in medical and public health research, and other fields. This is a 2-year programme that is offered through block-release.
Why study this programme?
- The programme is jointly offered by the departments of mathematical sciences, computer science, and population studies at UNIMA and Department of Epidemiology at KUHeS.
- Students in the programme benefit from international scholars the University of Nambibia, Witwatersrand, and South African Medical Research Council through visiting lectureships.
- The programme is part of the Sub-Saharan africa Consortium of Advanced Biostatistics Training
(SSACAB) which is a project within the Developing Excellence in Leadership and Biostatistics Training in Africa (DELTAS) with headquarters at University of Witwatersrand in South Africa.
Admission Requirements
Candidates must have strong Bachelor’s degree majored in Statistics or Mathematics and any other related disciplines from an accredited university. Selected candidates with deficiency in some
Mathematics/Statistics modules will be asked to attend bridging courses prior to enrolment.
Program Structure
This four-semester Master's program is structured around a set of core modules, electives, and a dissertation.
The core modules will be offered to all students and are designed to provide students with the necessary fundamental knowledge needed for
their specialized modules. The electives offer students a wide choice of specializations in the study of Biostatistics. Additionally, where
necessary, bridging modules will be offered for qualifying applicants who missed important undergraduate courses considered crucial for this
program. These modules target computing, data management, and research skills relevant for a master's student. Students will be required to
take a total of at least 180 credits (at least 120 from taught modules and 60 from the dissertation).
It's important to note that one credit point represents the amount of learning achieved through a notional 10 hours of learning time
Core Modules
| Code |
Name |
Year |
Credits |
| STA611 |
Probability and Distribution Theory
|
2 |
3 |
| STA612 |
Generalised Linear Modelling
|
2 |
3 |
| STA613 |
Experimental Designs
|
2 |
3 |
| STA614 |
Statistical Inference
|
2 |
3 |
| STA621 |
Time-to-Event Data Analysis
|
2 |
3 |
| STA622 |
Correlated and Longitudinal Data Analysis
|
2 |
3 |
| STA623 |
Bayesian Biostatistics
|
2 |
3 |
| STA624 |
Principles of Epidemiology
|
2 |
3 |
Optional Courses
| Code |
Name |
Year |
Credits |
|
Non-parametric Methods |
2 |
3 |
|
Programme Monitoring and Evaluation |
2 |
3 |
|
Discrete Data Analysis |
2 |
3 |
|
Multivariate Data Analysis |
2 |
3 |
|
Statistics for Clinical Trials |
2 |
3 |
|
Spatial Statistics |
2 |
3 |
| Description |
The aim of this module is to provide an understanding of principles of probability theory and a thorough mathematical understanding of distribution theory. It covers basic rules of probability, random variables and their distributions, variate transformation and distribution function techniques; moment generating functions, characteristic functions and Cumulants. It also covers distributions of functions of random variables; Inversion theorems, distribution of order statistics, Sampling distributions of the mean and related functions; and limiting Distributions. |
| Semester |
1 |
| Teaching Schedule |
- |
| Description |
The module aims to provide an understanding of generalised linear models and their applications by providing the basic theory associated with general and generalized linear models and practicalities of fitting regression models to data, interpreting and checking their adequacy. The topics covered include an introduction to linear regression and ANOVA, fitting linear models, weighted and generalized least-squares estimation and transformations techniques. It also covers interpretation of the fitted models and parameter estimates, comparison of regression models and modelling using GLIM package.
|
| Semester |
1 |
| Teaching Schedule |
- |
| Description |
This module provides an understanding of experimental designs and an analysis of data arising from experimental designs. The topics of study include principles of good design, general theory of block designs, completely randomised and orthogonal designs, factorial experiments and Taguchi methods. |
| Semester |
1 |
| Teaching Schedule |
- |
| Description |
The aim of the module is to provide students with a thorough mathematical understanding of statistical inference and derivation of various parameter estimation methods. The module covers principles of estimation, testing hypotheses, point and interval estimation, properties of estimators, estimation methods and procedures on formulation of hypotheses.
|
| Semester |
1 |
| Teaching Schedule |
- |
| Description |
The aim of the module is to provide an understanding of statistical methods for analysing time to even data and their applications. This will enable students to derive survival analysis functions, compare intervention groups and provide regression models of survival data. The topics in this module include survivor function, hazard functions and censoring. The module further covers Kaplan-Meier survival curve, log-rank test, Cox’s Proportional Hazards Model, parametric models, assessing model fit, time-varying covariates and competing risks.
|
| Semester |
1 |
| Teaching Schedule |
- |
| Description |
This module provides an understanding of statistical models and methods for the analysis of longitudinal (repeated measurements) data with a strong emphasis on applications. The topics covered include merits and approaches to longitudinal studies, design issues like bias, efficiency and sample size calculations. It also covers topics on exploratory data analysis using graphs and correlation structures, General and generalized linear models for longitudinal data, transition models including covariance structures and handling of missing data and the dropout process and joint modelling of longitudinal and time to event data.. |
| Semester |
1 |
| Teaching Schedule |
- |
| Description |
The aim of this module is to provide an understanding of Bayesian statistical models and demonstrating their usefulness in applied settings where prior sources of knowledge can be incorporated into statistical models for estimation. The topics of study include principles of Bayesian estimation methods, hierarchical modelling, a comparison of classical and Bayesian approaches for similar problems. The module will also include cases studies (each comprising a lecture and laboratory session) largely based on meta-analysis of studies. |
| Semester |
1 |
| Teaching Schedule |
- |
| Description |
The module aims to provide an understanding of various statistical models used in epidemiology. Students will familiarize themselves with different types of study designs in epidemiology, analyse data from different study designs and will further appreciate the concept of risk and its measurement. The module will cover, in detail, concepts and measures of effect in epidemiology, statistical methods of analysing data from cross-sectional, prevalence, cohort and case-control study designs. The module will also cover issues of measurement error, confounding and interaction effects. |
| Semester |
1 |
| Teaching Schedule |
- |
This module is offered at MSc. Visit site for department offering module for more info.
This module is offered at MSc. Visit site for department offering module for more info.
This module is offered at MSc. Visit site for department offering module for more info.
This module is offered at MSc. Visit site for department offering module for more info.
This module is offered at MSc. Visit site for department offering module for more info.
This module is offered at MSc. Visit site for department offering module for more info.
