Epidemiology Biostatistics Statistical Software Training Course

Duration 10 days 20 modules · 65 contact hours
Level Intermediate Certificate on completion
Who attends Epidemiologists, Public Health Officers and others
Fee from USD 2,200 KSh 190,000 for Kenyan organisations
Where 52 cities + online See dates by city
Next start 9 Nov 2026 Course code SD-PH-030

Before you join: Participants should have experience working with health, programme, survey, clinical or administrative data and understand basic tables, percentages and charts.

Dates & prices

Two start dates a month in every city, and live online on weekdays or weekends. Fees are per participant; classroom fees include tuition, materials, lunch and refreshments, and the certificate.

Suggest a date or city

Showing the next six months. Later dates, other cities and private deliveries for your team are available on request.

Course overview

Public-health teams must turn incomplete surveillance, survey, facility and programme data into defensible decisions. This requires more than producing charts or running statistical tests. Analysts need to frame answerable questions, select an appropriate study design, manage data quality, quantify uncertainty, interpret bias and confounding, and communicate findings that programme managers can act upon. The same demands arise in outbreak response, immunisation coverage reviews, maternal-health studies, non-communicable disease monitoring, humanitarian assessments and service-quality improvement.

This course develops applied epidemiology and biostatistics skills alongside practical use of ODK, Excel, SPSS, R, Python, Stata, NVivo, Power BI and GIS. Participants work from a public-health question through protocol design, electronic data collection, cleaning, descriptive analysis, hypothesis testing, regression modelling, survival analysis, outbreak investigation, spatial analysis and mixed-methods interpretation. Attention is given to effect measures, sampling, missing data, confounding, model diagnostics, data visualisation, ethical data handling and reproducible reporting.

Instruction combines short technical briefings with guided case analysis, software-based group work, scenario simulations and structured review of outputs. Participants use realistic datasets drawn from surveillance, household surveys, clinical services and programme monitoring. By the end of the course, each participant has produced and presented an analysis package containing a study question, data collection form, cleaned dataset, analysis plan, statistical outputs, dashboard or map, interpretation and decision-focused recommendations.

The course suits public-health professionals who already work with health or social data and need stronger analytical judgement as well as practical command of common research and reporting tools. It is appropriate for staff in ministries of health, hospitals, NGOs, research units, development programmes, insurers and corporate health teams.

What you will be able to do

  • Formulate epidemiological questions using PICO, case definitions and measurable outcomes
  • Design surveys and observational studies with appropriate sampling and bias controls
  • Build ODK forms with validation rules, skip logic and coded response options
  • Clean, document and analyse health datasets using Excel, SPSS, R, Python and Stata
  • Calculate and interpret incidence, prevalence, risk ratios, odds ratios and confidence intervals
  • Fit and diagnose regression and survival models for public-health research questions
  • Produce GIS maps, Power BI dashboards and NVivo coding outputs for mixed-methods reporting
  • Present a complete epidemiological analysis with methods, findings, limitations and recommendations

Benefits of attending

For you

  • Confidence selecting defensible study designs and statistical methods
  • Practical scripts and workflows for repeatable health-data analysis
  • Stronger interpretation of effect estimates, uncertainty and model outputs
  • Ability to produce maps, dashboards and evidence-based briefing materials
  • A completed analysis portfolio for professional appraisal or project use

For your organisation

  • More reliable interpretation of surveillance, survey and service-delivery data
  • Faster production of decision-ready outbreak and programme analysis
  • Improved data quality through validated electronic collection forms
  • Clearer reporting of uncertainty, bias, limitations and recommendations
  • Reduced dependence on external analysts for routine public-health studies

Course modules

20 modules over 10 days

Participants can frame a public-health question and identify the evidence needed to answer it.

  • PICO questions structured around populations, exposures, comparators and measurable outcomes
  • Case definitions specified by person, place, time and clinical criteria
  • Causal pathways mapped using directed acyclic graphs and plausible mechanisms
  • Public-health indicators distinguished from research outcomes and operational measures
  • Denominators selected for coverage, incidence, mortality and service-use calculations
  • Evidence sources assessed for relevance, timeliness, completeness and measurement quality

Participants can calculate and interpret core epidemiological measures for health data.

  • Incidence proportion, incidence rate and prevalence calculated from population data
  • Attack rates compared during outbreaks using exposed and unexposed groups
  • Risk ratios, rate ratios and odds ratios interpreted correctly
  • Risk difference and attributable fraction applied to prevention priorities
  • Crude, specific and age-standardised rates compared between populations
  • Confidence intervals used to express precision around estimated measures

Participants can select an observational or experimental design and anticipate major threats to validity.

  • Cross-sectional studies matched to prevalence, coverage and service-assessment questions
  • Case-control designs used for rare outcomes and outbreak source investigations
  • Cohort studies planned for incidence, prognosis and exposure follow-up
  • Randomised trials distinguished from quasi-experimental programme evaluation designs
  • Selection bias, information bias and recall bias identified systematically
  • Confounding assessed through causal reasoning, stratification and multivariable adjustment

Participants can develop a sampling approach and justify a sample size for a health study.

  • Target populations, sampling frames and eligibility criteria defined precisely
  • Simple random, systematic and stratified sampling methods compared
  • Cluster sampling planned for household surveys and community studies
  • Design effects incorporated when sampling clustered populations
  • Sample sizes estimated for proportions, means and comparative studies
  • Non-response allowances documented within fieldwork and recruitment plans

Participants can prepare a data-management process that meets ethical and analytical requirements.

  • Informed consent procedures aligned with study risks and participant rights
  • Data dictionaries define variables, labels, codes, ranges and missing values
  • Unique identifiers designed to link visits without exposing personal identities
  • De-identification methods applied before analysis, sharing and secondary use
  • File naming, version control and audit trails documented consistently
  • Data management plans assign access, retention, backup and destruction responsibilities

Participants can build and test an ODK form for a structured public-health data collection process.

  • ODK XLSForm structure created using survey, choices and settings sheets
  • Question types selected for symptoms, dates, locations and numeric values
  • Skip logic built with relevant expressions and conditional sections
  • Constraint rules prevent invalid ages, dates and clinical measurements
  • Repeat groups capture household members, visits and treatment episodes
  • Forms tested on mobile devices before controlled field deployment

Participants can prepare and analyse a health dataset using Excel functions and pivot tools.

  • Raw data separated from cleaning, analysis and reporting worksheets
  • Data validation controls standardise codes, dates and categorical entries
  • COUNTIFS, SUMIFS and XLOOKUP functions support routine indicator calculations
  • PivotTables summarise cases by age, sex, facility and reporting period
  • Duplicate records identified using identifiers, dates and logical checks
  • Charts selected to show trends, distributions, comparisons and denominators

Participants can manage variables and run standard inferential tests in SPSS.

  • Variable View configured with labels, value codes and measurement levels
  • Recode procedures create age groups, binary outcomes and derived indicators
  • Frequencies and Explore procedures identify outliers and missingness patterns
  • Chi-square tests compare categorical outcomes between defined groups
  • Independent and paired t-tests assess differences in continuous measures
  • SPSS output tables annotated with estimates, intervals and interpretation

Participants can use R scripts to import, transform, analyse and visualise health data.

  • RStudio projects organise scripts, inputs, outputs and documentation files
  • readr imports CSV files while preserving explicit variable specifications
  • dplyr verbs filter, mutate, group and summarise surveillance records
  • tidyr functions reshape repeated measures into analysis-ready structures
  • ggplot2 charts display time trends, distributions and group comparisons
  • R Markdown reports combine code, results, tables and narrative

Participants can use Python to inspect, clean and analyse structured health datasets.

  • Jupyter notebooks combine executable code, outputs and analytical commentary
  • pandas DataFrames import, inspect and transform health-service records
  • Missing values classified as structural, accidental or analytically informative
  • Boolean filters isolate case definitions, reporting periods and study cohorts
  • groupby operations calculate facility indicators and demographic summaries
  • matplotlib and seaborn produce interpretable statistical graphics

Participants can manage epidemiological data and run common analyses in Stata.

  • Stata do-files record repeatable data preparation and analysis commands
  • describe, codebook and tabulate commands inspect variable structures quickly
  • merge and append procedures combine facility, survey and follow-up datasets
  • egen functions create group summaries and standardised analytical variables
  • svy commands account for weights, strata and cluster sampling
  • estimates tables compare models using consistent reporting formats

Participants can describe health data accurately and select clear visual displays.

  • Mean, median and mode selected according to distributional characteristics
  • Standard deviation, interquartile range and percentiles describe variation
  • Histograms and boxplots reveal skewness, outliers and distribution shape
  • Epidemic curves display onset dates, peaks and potential exposure periods
  • Run charts distinguish ordinary variation from meaningful performance changes
  • Table shells planned before analysis to answer specified study questions

Participants can fit, assess and interpret regression models for common public-health outcomes.

  • Linear regression models continuous outcomes such as blood pressure
  • Logistic regression estimates adjusted odds ratios for binary outcomes
  • Poisson regression models counts, rates and person-time denominators
  • Model building follows conceptual frameworks and pre-specified covariates
  • Interaction terms assess effect modification across population subgroups
  • Residuals, collinearity and influential observations inform model diagnostics

Participants can analyse follow-up data where timing and censoring affect the outcome.

  • Time origins, event definitions and censoring rules specified clearly
  • Kaplan-Meier curves estimate event-free probability across follow-up periods
  • Log-rank tests compare survival distributions between exposure groups
  • Cox proportional hazards models estimate adjusted hazard ratios
  • Proportional hazards assumptions checked using plots and residual methods
  • Person-time calculated for cohorts with unequal follow-up durations

Participants can analyse outbreak data and prepare evidence for response decisions.

  • Outbreak verification distinguishes observed increases from reporting artefacts
  • Line lists structure patient, exposure, laboratory and outcome information
  • Descriptive epidemiology examines cases by time, place and person
  • Epidemic curves generate hypotheses about transmission and incubation
  • Case-control comparisons identify probable exposures and risk factors
  • Surveillance thresholds trigger alerts, verification and field investigation actions

Participants can map health events and interpret spatial patterns with appropriate caution.

  • Geographic coordinates cleaned, projected and checked for location errors
  • Point maps display cases, facilities, exposures and service catchments
  • Choropleth maps use rates rather than unadjusted case counts
  • Administrative boundaries joined to health indicators and population denominators
  • Buffer analysis examines access to clinics, water points and hazards
  • Spatial patterns interpreted alongside reporting completeness and population distribution

Participants can build a Power BI report that monitors public-health indicators and trends.

  • Power Query cleans source tables and standardises field formats
  • Data models link facility, population, service and calendar tables
  • DAX measures calculate coverage, dropout, positivity and reporting timeliness
  • Slicers filter dashboards by district, facility, period and population
  • KPI cards highlight targets, actual performance and variance values
  • Drill-through pages support investigation from national to facility results

Participants can code qualitative material and integrate it with quantitative findings.

  • Qualitative research questions distinguish experiences, mechanisms and implementation barriers
  • NVivo projects organise transcripts, field notes, documents and coding structures
  • Deductive codes derived from interview guides and programme frameworks
  • Inductive coding captures unanticipated themes within participant accounts
  • Framework matrices compare themes by site, role and participant group
  • Joint displays integrate qualitative themes with quantitative indicator patterns

Participants can prepare an analysis plan and communicate findings with appropriate limits.

  • Statistical analysis plans specify populations, outcomes, models and missing-data rules
  • STROBE reporting items structure observational study methods and results
  • CONSORT principles distinguish trial reporting requirements from observational reporting
  • Results tables separate descriptive findings, crude estimates and adjusted models
  • Limitations address bias, precision, generalisability and data-quality constraints
  • Recommendations link findings to feasible programme, policy and research actions

Participants can build, review and present a complete public-health analysis package for a defined decision.

  • Select a decision question from surveillance, service or survey data
  • Prepare an ODK form or documented dataset for analysis
  • Clean variables and document transformations within a reproducible workflow
  • Apply descriptive, comparative or regression methods matched to the question
  • Create a dashboard, map or coded qualitative evidence display
  • Present findings, limitations and prioritised recommendations to a review panel

Exercises and examples are adapted to each cohort's sectors and roles.

What you take back to work

  1. Epidemiological study design and sampling template
  2. ODK XLSForm data-collection template
  3. Data dictionary and cleaning checklist
  4. Reproducible R, Python and Stata analysis scripts
  5. Public-health dashboard and GIS map specification
  6. Statistical analysis plan and reporting checklist

Who should attend

  • Epidemiologists — strengthen analytical design, modelling and interpretation for population-health studies
  • Public Health Officers — convert surveillance and programme data into operational decisions
  • Monitoring and Evaluation Specialists — build credible indicators, analyses and reporting products
  • Health Research Officers — manage study data and produce reproducible statistical findings
  • Programme Managers — assess evidence quality and use results to improve interventions
  • Data Analysts — apply statistical software methods to health and social-care datasets

Skills and tools covered

Study design selectionStatistical modellingHealth data managementOutbreak investigationSpatial epidemiologyMixed-methods analysis

Tools and standards

ODK, R, Stata, QGIS

How the course runs

Training methodology

The course uses short instructor briefings followed by worked examples, software demonstrations, case analysis and structured group tasks. Participants examine realistic public-health datasets, including surveillance line lists, household surveys, facility records and qualitative interview extracts. Simulations cover outbreak response, study-design choices and programme reporting decisions. Trainers provide stepwise support in ODK, Excel, SPSS, R, Python, Stata, NVivo, Power BI and GIS, then guide participants to apply methods to a work-relevant question and review one another’s outputs.

Requirements and prerequisites

Participants should have experience working with health, programme, survey, clinical or administrative data and understand basic tables, percentages and charts. Familiarity with common public-health indicators such as prevalence, coverage or mortality is useful. Participants should be comfortable using a computer, managing files and entering formulas in spreadsheets. Prior use of statistical software is helpful but not required; the course introduces the working steps in each tool. Advanced mathematics, programming experience, prior epidemiology qualifications and previous GIS or qualitative-analysis experience are not required.

A typical training day

08:30 – 10:30First session
10:30 – 10:45Refreshment break
10:45 – 12:30Second session
12:30 – 13:30Lunch and networking
13:30 – 15:00Third session
15:00 – 15:15Refreshment break
15:15 – 16:30Workshop and daily review

Live online deliveries follow the same structure in East Africa Time, with shorter screen blocks and longer breaks.

What the fee includes

  • Instruction by a practitioner facilitator
  • Full course workbook and materials
  • Exercise files, templates and case studies
  • Refreshments and lunch on classroom deliveries
  • Certificate of completion
  • Post-course application plan

Frequently asked questions

Participants should understand basic percentages, tables and common health indicators, and should have worked with data in some form. Prior programming, advanced mathematics and previous use of statistical packages are not required.

Participants should bring a laptop capable of running the required software and, where permitted, a de-identified dataset or work question. Software installation guidance is provided before the course.

It is designed for epidemiologists, public-health officers, researchers, monitoring specialists, analysts and programme managers handling health or social-care evidence. It suits people who need to judge and produce analysis rather than only read reports.

The course starts from public-health questions, study designs, disease measures and surveillance decisions. It then applies statistical methods through several commonly used tools, including electronic data collection, qualitative analysis, dashboards and mapping.

Participants can use the methods for routine surveillance reviews, surveys, outbreak line lists, service-performance reporting and operational research. The final evidence package is structured so it can be adapted to a current workplace issue.

The first week establishes epidemiological reasoning, study design, data management and practical work with collection and analysis tools. The second week develops modelling, outbreak analysis, spatial and mixed-methods reporting, ending with the capstone presentation.

Questions about this course?

Ask about dates, fees, group bookings or running it for your team. Our training team replies by email.

Ask on WhatsApp info@skillsetdevelopment.com

Related courses in Public Health