Technology

Master of Science in Statistical Modelling with Data Science

The Master of Science in Statistical Modelling with Data Science is a postgraduate programme that prepares professionals for advanced practice in statistical modelling, data science, and computational analytics. The programme provides specialised training in statistical modelling, machine learning, data mining, predictive analytics, and computational methods for large-scale data analysis.

Core areas include statistical modelling, data science, machine learning, predictive analytics, data mining, Bayesian methods, stochastic processes, research methods, and thesis. Students engage with both theoretical and practical work through coursework, computing sessions, and research.

The programme is offered by Egerton University and Jomo Kenyatta University of Agriculture and Technology as public institutions, with Strathmore University offering a closely related MSc in Data Science and Analytics as a private institution. The programme is available in full-time and part-time modes over two years, combining coursework with research.

Students develop competencies in statistical modelling, machine learning, data mining, predictive analytics, Bayesian methods, and research. The programme includes coursework, examinations, computing projects, and a supervised research thesis, preparing graduates for data science, statistical modelling, and analytical roles.

JKUAT charges approximately KES 140,000 per year while Egerton charges approximately KES 124,000 per year. Strathmore University (private) charges approximately KES 603,500 per year for a closely related programme. Entry requires at least an Upper Second Class Honours degree in Statistics, Mathematics, Computer Science, or a related field from a recognised institution.

Graduates pursue careers as data scientists, statistical modellers, machine learning engineers, quantitative analysts, research analysts, and lecturers across technology companies, financial institutions, research organisations, government, and universities.

Skills Required

Statistical Modelling and Inference
Machine Learning and Predictive Analytics
Data Mining and Warehousing
Bayesian Methods and Data Analysis
Statistical Computing with R and Python
Big Data Analytics and Processing
Data Visualisation and Communication
Stochastic Processes and Time Series
Research Methods in Data Science
Academic Writing and Thesis Research

Key Subjects

Statistical Modelling and Inference
Machine Learning and Predictive Analytics
Data Mining and Warehousing
Bayesian Methods and Data Analysis
Stochastic Processes and Time Series
Big Data Analytics and Processing
Statistical Computing with R and Python
Data Visualisation and Communication
Research Methods in Data Science
Thesis Research

Certifications

KNBS Professional Membership
ISI Professional Membership

Specializations

Statistical Modelling

Focuses on statistical modelling, covering models, statistics, regression, inference, and managing statistical modelling and inference.

Machine Learning

Examines machine learning, covering learning, algorithms, data, prediction, and managing machine learning and predictive analytics.

Data Mining

Covers data mining, covering mining, data, patterns, algorithms, and managing data mining and pattern discovery.

Predictive Analytics

Focuses on predictive analytics, covering prediction, analytics, models, forecasting, and managing predictive analytics and forecasting.

Bayesian Methods

Examines Bayesian methods, covering Bayesian, statistics, inference, probability, and managing Bayesian methods and data analysis.

Big Data Analytics

Covers big data analytics, covering big, data, analytics, computing, and managing big data analytics and processing.

Duration: 2 years
Public, up to: Ksh 189,650
Private, up to: Ksh 603,500
Job market: High

The programme

What you study, how long it takes, and how it is delivered.

Practicalities

Study mode: Full-time, Part-time
Attachment: 0 months
Average class: 20 students
Award: Masters

What you study

10 subjects

Statistical Modelling and Inference
Machine Learning and Predictive Analytics
Data Mining and Warehousing
Bayesian Methods and Data Analysis
Stochastic Processes and Time Series
Big Data Analytics and Processing
Statistical Computing with R and Python
Data Visualisation and Communication
Research Methods in Data Science
Thesis Research

Modules

12 in the programme

Statistical Modelling and Inference
Year 1Semester 13 creditsCore
Examines statistical modelling, covering models, statistics, regression, inference, and managing statistical modelling and inference.
Machine Learning and Predictive Analytics
Year 1Semester 13 creditsCore
Covers machine learning, covering learning, algorithms, data, prediction, and managing machine learning and predictive analytics.
Data Mining and Warehousing
Year 1Semester 13 creditsCore
Examines data mining, covering mining, data, patterns, algorithms, and managing data mining and pattern discovery.
Statistical Computing with R and Python
Year 1Semester 13 creditsCore
Covers statistical computing, covering computing, statistics, R, Python, and managing statistical computing and programming.
Bayesian Methods and Data Analysis
Year 1Semester 23 creditsCore
Examines Bayesian methods, covering Bayesian, statistics, inference, probability, and managing Bayesian methods and data analysis.
Stochastic Processes and Time Series
Year 1Semester 23 creditsCore
Covers stochastic processes, covering stochastic, processes, probability, modelling, and managing stochastic processes and time series.
Big Data Analytics and Processing
Year 1Semester 23 creditsCore
Examines big data analytics, covering big, data, analytics, computing, and managing big data analytics and processing.
Research Methods in Data Science
Year 1Semester 23 creditsCore
Covers research, methods, data, science, and conducting research in data science, preparing students for their thesis.
Predictive Modelling and Statistical Learning
Year 1Semester 23 creditsCore
Examines predictive modelling, covering prediction, modelling, learning, statistics, and managing predictive modelling and statistical learning.
Multivariate Statistical Analysis
Year 2Semester 13 creditsCore
Covers multivariate analysis, covering multivariate, statistics, analysis, methods, and managing multivariate statistical analysis.
Data Visualisation and Communication
Year 2Semester 13 creditsCore
Examines data visualisation, covering visualisation, data, communication, graphics, and managing data visualisation and communication.
Research Thesis
Year 2Semester 212 creditsCore
Original supervised research thesis on a statistical modelling or data science topic, demonstrating mastery of research methods and data science knowledge, assessed through written submission and oral defence.

Specialisations

Statistical Modelling
Focuses on statistical modelling, covering models, statistics, regression, inference, and managing statistical modelling and inference.
Machine Learning
Examines machine learning, covering learning, algorithms, data, prediction, and managing machine learning and predictive analytics.
Data Mining
Covers data mining, covering mining, data, patterns, algorithms, and managing data mining and pattern discovery.
Predictive Analytics
Focuses on predictive analytics, covering prediction, analytics, models, forecasting, and managing predictive analytics and forecasting.
Bayesian Methods
Examines Bayesian methods, covering Bayesian, statistics, inference, probability, and managing Bayesian methods and data analysis.
Big Data Analytics
Covers big data analytics, covering big, data, analytics, computing, and managing big data analytics and processing.

A day as a student

A typical day during the MSc in Statistical Modelling with Data Science programme combines lectures, computing sessions, seminars, and independent study. Sessions cover statistical modelling, machine learning, data mining, predictive analytics, and Bayesian methods. Statistical modelling sessions examine models, statistics, regression, inference, and managing statistical modelling. Machine learning sessions cover learning, algorithms, data, prediction, and managing machine learning. Data mining sessions cover mining, data, patterns, algorithms, and managing data mining. Predictive analytics sessions cover prediction, analytics, models, forecasting, and managing predictive analytics. Bayesian methods sessions cover Bayesian, statistics, inference, probability, and managing Bayesian methods. Stochastic processes sessions cover stochastic, processes, probability, modelling, and managing stochastic processes. Big data sessions cover big, data, analytics, computing, and managing big data analytics. Computing sessions provide practical experience in R, Python, and MATLAB for statistical modelling and data science. Seminars provide opportunities for presenting research findings and discussing current developments in data science. The programme culminates in a supervised research thesis on a statistical modelling or data science topic.

The trade offs

In its favour

Programme combines statistical modelling with data science, addressing high-demand skills in Kenya and globally.
Programme offered at both public and private universities with different fee options.
Graduates are in high demand in technology, finance, research, and data-driven sectors.
Programme combines theoretical knowledge with practical computing skills using R, Python, and MATLAB.

Against it

Egerton fee data is estimated from a similar programme, not confirmed for this exact programme.
Strathmore offers Data Science and Analytics, not Statistical Modelling with Data Science specifically.
Strathmore fees are significantly higher at KES 603,500/year compared to public universities.
Programme requires strong background in statistics, mathematics, or computing.

What it costs

Tuition at both ends of the market, and how to pay for it.

What it costs, and where

Against 191 technology courses

Public190k to 190k

190k at Egerton University190k at Egerton University

Private604k to 604k

604k at Strathmore University604k at Strathmore University

Annual tuition in Kenyan shillings, rounded. The upright tick is the median for this field, so a bar sitting entirely to its right is an expensive programme by the standards of its own subject.

The fine print

Egerton ~190K/yr (egerton.ac.ke). Strathmore MSc DSA 603.5K/yr (kenyaplex). JKUAT unverified.

HELB postgraduate loans are available for Kenyan students. Universities may offer scholarships for eligible students. ISI and international statistics organisations may offer scholarships and fellowships for data science research and education.

Funding options

HELB Postgraduate Loan
University Scholarship
ISI Scholarship

Scholarships

3 recorded

HELB Postgraduate Loan
LoanKsh 200,000Kenyan
Kenyan students pursuing postgraduate studies at recognised universities.
University Scholarship
ScholarshipKsh 140,000Kenyan
Universities may offer scholarships for eligible postgraduate data science students.
ISI Scholarship
ScholarshipKsh 200,000
ISI and international statistics organisations may offer scholarships for data science research and education.

Getting in

The grades, the alternatives, and who accredits the award.

What you need

KCSE mean grade: N/A (Postgraduate)
Alternative entry: Most universities require at least an Upper Second Class Honours degree in a relevant field. Lower Second Class may be considered with relevant work experience or postgraduate diplomas. Contact respective universities for specific admission requirements.

How you are assessed

4 components

Coursework and Continuous Assessment
Coursework30% of the mark
Continuous assessment through coursework assignments, computing projects, seminar presentations, and class participation.
Written Examinations
Examination70% of the mark
Written examinations covering statistical modelling, machine learning, data mining, Bayesian methods, and stochastic processes.
Computing Project
Project40% of the mark
Practical assessment through computing projects, demonstrating statistical modelling, machine learning, and data analysis skills.
Research Thesis
Research100% of the mark
Original supervised research thesis on a statistical modelling or data science topic, demonstrating mastery of research methods and data science knowledge, assessed through written submission and oral defence.

Accreditation

The programme is accredited by the Commission for University Education (CUE). Egerton University, JKUAT (public), and Strathmore University (private) offer MSc in Statistical Modelling with Data Science or closely related programmes. The programme meets CUE standards for postgraduate training in statistical modelling and data science. Graduates may interact with KNBS for official statistics standards and ISI for international statistics standards. The programme aligns with ISI global statistics and data science frameworks.

Accredited by

Commission for University Education (CUE)
Academic accreditationRequired
Programme accredited by CUE. Egerton University, JKUAT (public), and Strathmore University (private) offer MSc in Statistical Modelling with Data Science or closely related programmes. The programme meets CUE standards for postgraduate training in statistical modelling and data science. Graduates may interact with KNBS for official statistics standards and ISI for international statistics standards. The programme aligns with ISI global statistics and data science frameworks.

Where it leads

The roles it opens, and what you leave with.

Where graduates go

6 roles

Data Scientist
High demandKsh 150,000 to Ksh 500,000
Manages data science projects, covering data, science, analysis, statistics, and managing data science and analytics.
Statistical Modeller
Moderate demandKsh 130,000 to Ksh 450,000
Develops statistical models, covering models, statistics, modelling, and managing statistical modelling and development.
Machine Learning Engineer
High demandKsh 150,000 to Ksh 500,000
Develops machine learning systems, covering learning, algorithms, models, and managing machine learning engineering and development.
Quantitative Analyst
High demandKsh 150,000 to Ksh 500,000
Conducts quantitative analysis, covering quantitative, analysis, finance, statistics, and managing quantitative analysis and modelling.
Research Analyst
High demandKsh 100,000 to Ksh 350,000
Conducts research analysis, covering research, analysis, data, statistics, and managing research analysis and reporting.
Data Science Lecturer
Moderate demandKsh 100,000 to Ksh 400,000
Teaches data science at university or college level, overseeing instruction, research, and academic supervision.

Graduate outcomes

Where these fields lead

8 careers

Tools you will learn

R Statistical Software
SoftwarePrimary
R for statistical modelling and data analysis, covering modelling, statistics, analysis, and managing statistical computing and data processing.
Python
Software
Python for data science and machine learning, covering computing, data, learning, and managing data science and machine learning.
MATLAB
Software
MATLAB for statistical modelling and computing, covering modelling, computing, statistics, and managing statistical modelling and computing.
Tableau
Software
Tableau for data visualisation and analytics, covering visualisation, data, analytics, and managing data visualisation and reporting.

Industry links

Common misconceptions

Statistical modelling with data science is just about using software tools.
The programme covers statistical theory, algorithm development, mathematical foundations, and research methods alongside practical software tools.
This programme is only for computer scientists.
Statistical modelling with data science is for professionals from statistics, mathematics, economics, engineering, and science backgrounds, not just computer scientists.
Data science has limited career prospects in Kenya.
Data science graduates are in high demand in technology companies, financial institutions, research organisations, and data-driven businesses in Kenya.
This programme is the same as general statistics.
Statistical modelling with data science combines statistics with computing, machine learning, and big data analytics, distinct from general statistics.
You need to be a programmer to study data science.
While programming skills are developed during the programme, a background in statistics or mathematics is sufficient for entry.
Data science is only about data analysis.
The programme covers statistical modelling, machine learning, data mining, predictive analytics, and research methods alongside data analysis.