Business Data Laboratory trains analysts, researchers and technical teams to move from raw data to reproducible machine learning systems — and, when you need it done now, builds the same predictive models, workflows and AI solutions with you. R, Python, SQL, MLflow, Quarto and modern data science tools, on the real data you work with every day.
Built for the people behind routine health data
Business Data Laboratory works three ways — and they reinforce each other. We teach the same data pipelines, dashboards and reporting systems we build for programs in the field, on the data you actually report on.
Our flagship: structured, hands-on tracks that take individuals and whole teams from spreadsheets to reproducible, decision-ready analysis.
Need it done now? We build the same cleaning pipelines, dashboards and reporting systems we teach — production-ready and handed over with documentation.
Analytical support for studies, surveillance and evaluations — from study-ready datasets and indicator design to outbreak analytics and donor-grade reporting.
Take a single course when you need one skill, or enroll in the whole track for everything — including new courses as they ship. Pick a track to see its full curriculum.
One enrollment unlocks every course in the track — plus any new courses added later, free.
Public health graduates, epidemiology students, surveillance and M&E officers, health records officers, NGO program staff, researchers, postgraduate students, doctors, nurses, and anyone who has used Excel but is new to R.
Support entry-level public health data analysis tasks in R — cleaning data, summarising indicators, creating charts, and preparing basic health analysis outputs.
No programming experience required. Microsoft Excel basics, a basic understanding of health indicators, and willingness to learn coding step by step.
What R is and why it matters in public health; installing R and RStudio; scripts, console, environment and files; basic R objects.
LabInstall R/RStudio and run your first public health analysis script.
CSV and Excel files; rows and columns; variables; data types; missing values; common health data structures.
LabImport a sample facility reporting dataset into R.
Cleaning column names; removing duplicates; handling missing values; correcting categories; fixing dates with janitor, dplyr and lubridate.
LabClean a messy immunization, malaria, ANC or facility dataset.
Grouping data; counting cases; calculating percentages; coverage rates; target achievement; facility and district summaries.
LabCalculate monthly health indicators by facility and district.
Person, place and time analysis; age groups; sex distribution; case counts; case fatality rate; attack rate basics.
LabAnalyze a simple disease line list.
Bar charts; line charts; epidemic curves; district comparison charts; chart labels and interpretation.
LabCreate charts for monthly trends, facility performance and disease cases.
Exporting cleaned data; writing summary tables to Excel/CSV; saving charts; organizing folders.
LabExport cleaned data, summary tables and charts for reporting.
Introduction to Quarto; combining text, code, tables and charts; rendering a simple HTML report.
LabCreate a simple health data analysis report using R and Quarto.
Analyze a messy public health dataset end to end: import it into R, clean column names and data types, handle missing values and duplicates, calculate key indicators, summarise by month, facility, district, age group or sex, create charts, export cleaned outputs and prepare a short analysis report.
Public health graduates, M&E assistants, health records officers, research assistants, NGO staff, health data officers, and beginners who want to start using R confidently.
Clean health datasets, calculate indicators, produce summary reports, and use R scripts to repeat routine reporting tasks.
Types of health data; facility, patient and survey data; routine reports; common data quality issues.
LabReview a messy facility reporting dataset.
Missing values; duplicates; inconsistent facility names; date formatting; validation checks.
LabClean a monthly facility dataset in Excel.
RStudio; scripts; packages; importing Excel/CSV files; basic data inspection.
LabImport the same Excel dataset into R.
dplyr, janitor and lubridate; renaming columns; filtering; fixing dates; removing duplicates.
LabRecreate the Excel cleaning workflow in R.
Numerators and denominators; percentages; coverage rates; monthly summaries; facility comparison.
LabCalculate health indicators in Excel and R.
Exporting cleaned data; summary tables; charts; simple reports.
LabProduce a clean report-ready dataset and summary table.
Clean a messy health facility dataset using Excel and R, calculate key indicators, and prepare a monthly health performance report.
M&E officers, public health officers, data analysts, program officers, DHIS2 officers, NGO staff, and health information officers.
Build Power BI dashboards from cleaned health data and use R to prepare reliable, dashboard-ready datasets.
Dashboard use cases; KPIs and indicators; facility comparison; trend monitoring.
LabReview examples of public health dashboards.
Importing data; cleaning columns; creating indicator variables; summarising by facility and month.
LabPrepare a dashboard-ready dataset in R.
Fact and dimension tables; date tables; relationships; health program data models.
LabBuild a simple health data model.
DAX measures; coverage rate; target achievement; monthly trend; facility ranking.
LabCreate health KPI measures in Power BI.
Exporting from R to CSV/Excel; connecting Power BI to prepared data; refreshing reports.
LabUse R output as the backend for a Power BI dashboard.
KPI cards; slicers; maps; trend charts; executive summaries; recommendations.
LabBuild and present a public health dashboard.
Use R to clean and prepare a health program dataset, then build an interactive Power BI dashboard for program monitoring.
DHIS2 officers, M&E officers, health information officers, public health program staff, NGO staff, ministry health data teams, and data officers working with routine health data.
Work with DHIS2 exports, check data quality, calculate indicators, prepare dashboard-ready datasets, and produce program performance reports.
Organisation units; periods; data elements; indicators; reporting rates; metadata.
LabExplore a DHIS2-style export.
Wide vs long format; missing values; inconsistent names; reporting periods; duplicates.
LabClean a DHIS2-style dataset in Excel.
tidyr and dplyr; pivoting data; fixing periods; grouping by facility and district.
LabReshape DHIS2 data from wide to long format in R.
Completeness; timeliness; consistency; outliers; zero reporting; missing facilities.
LabRun data quality checks using Excel and R.
Coverage; service utilization; target achievement; district comparison; trend analysis.
LabCalculate monthly indicator performance.
Exporting R summaries; dashboard-ready data; Power BI visuals; narrative reporting.
LabBuild a DHIS2 performance dashboard.
Analyze a DHIS2-style health program dataset, run data quality checks, calculate indicators, and produce a dashboard-ready performance report.
M&E officers, program officers, health project staff, NGO workers, donor-funded project teams, public health graduates, and career switchers.
Manage indicator tracking, analyze project performance, compare actuals against targets, and prepare professional donor-style reports.
Results frameworks; logframes; indicators; baselines; targets; disaggregation.
LabReview a health project logframe.
Indicator matrix; target vs actual; monthly/quarterly reporting; disaggregation.
LabBuild an indicator tracking sheet.
Importing project data; cleaning beneficiary records; checking duplicates; fixing categories.
LabClean a project monitoring dataset in R.
Target achievement; trend analysis; location comparison; gap analysis; underperformance flags.
LabAnalyze quarterly health project performance.
KPI cards; target tracking visuals; filters; slicers; project performance dashboard.
LabBuild an M&E performance dashboard.
Narrative summaries; recommendations; limitations; evidence-based reporting.
LabPrepare a donor-style M&E report.
Analyze a donor-funded health project dataset, track indicator performance, build a dashboard, and write a quarterly M&E report.
Epidemiology students, public health officers, surveillance officers, disease control teams, emergency response staff, health data analysts, and public health researchers.
Analyze surveillance data, detect unusual trends, calculate outbreak indicators, produce epidemic curves, and communicate findings for public health action.
Case definitions; line lists; suspected vs confirmed cases; reporting dates; locations; outcomes.
LabExplore a disease surveillance line list.
Cleaning dates; duplicates; missing values; age groups; case status; location names.
LabClean an outbreak line list using R.
Person, place and time analysis; age and sex distribution; case fatality rate; attack rate.
LabCalculate outbreak summary statistics.
Epi curves; weekly trends; onset dates; reporting delays; location comparison.
LabCreate an epidemic curve in R.
Tables; charts; situation reports; key findings; limitations; recommendations.
LabPrepare outbreak visuals and summary tables.
Short briefs; public health recommendations; decision-focused communication.
LabWrite a two-page outbreak analytics brief.
Analyze an outbreak line list using R, create an epidemic curve, calculate key epidemiological indicators, and prepare a short outbreak analytics brief.
M&E officers, public health data analysts, epidemiologists, health researchers, NGO reporting officers, DHIS2/data officers, program managers, postgraduate students, consultants, and R users who want professional reporting skills.
Create reproducible analytical reports and dashboards for health programs, surveillance data, research projects, and donor-funded interventions.
What reproducible reporting means; why manual reporting fails; Quarto project structure; .qmd files; YAML basics; rendering reports.
LabCreate your first Quarto health report.
Combining text and code; code chunks and options; hiding code; showing results; adding tables and charts.
LabBuild a monthly health indicator report.
Formatting tables; captions; creating charts; writing findings; explaining limitations; making reports decision-focused.
LabCreate a report with indicator tables, charts and interpretation.
Parameters; reusable templates; facility- and district-level reports; monthly/quarterly reports; automated updates.
LabGenerate district-specific reports from one Quarto template.
Dashboard layout; pages; cards; value boxes; charts; tables; filters; dashboard storytelling.
LabBuild a public health performance dashboard in Quarto.
What Typst is; Quarto Typst output; report styling; title pages; sections; tables; figure captions; exporting polished PDFs.
LabRender a professional public health PDF report using Quarto and Typst.
Folder structure; data, scripts and output folders; naming and versioning reports; reproducible habits.
LabOrganize a complete reporting project folder.
HTML and PDF output; dashboard sharing options; GitHub Pages / Posit publishing overview; exporting final deliverables.
LabPrepare a complete report package for stakeholders.
Build a complete reproducible reporting system: import a health program dataset, clean and summarize it in R, create reusable indicator tables, build charts, create a Quarto report, generate a professional PDF with Typst, build a Quarto dashboard, write an executive summary, and export final deliverables.
Public health students, junior researchers, health data analysts moving into public health, clinicians seeking quantitative fluency, epidemiology trainees, surveillance officers, M&E officers, postgraduate students, and health professionals who want practical statistical analysis skills using R.
Support applied epidemiology and medical statistics tasks in public health programs, research projects, surveillance teams, M&E units and academic settings — cleaning and managing health data, computing core epidemiological measures, interpreting statistical tests, analyzing observational study designs, building regression models, communicating uncertainty, critiquing published evidence, and preparing reproducible reports.
Basic R literacy is required: variables, data frames, importing data, and running scripts. Comfort with Excel is helpful. No prior statistics or epidemiology background is assumed.
Measuring disease in populations — incidence, prevalence, person-time, rates and standardization; data cleaning and management in R — messy health data, missingness, dates, joins, deduplication, reshaping and documentation.
LabSet up an R project, import data and build an age-standardized rate table; then clean a messy multi-file dataset, resolve a many-to-many join, deduplicate and produce a before/after data-quality summary.
Data visualization for epidemiology — grammar of graphics, epidemic curves, age-sex pyramids, heat plots and choropleths; cohort and cross-sectional studies — risk ratios, risk differences, attributable risk and 2x2 tables.
LabBuild an epidemic curve, age-sex pyramid, heat plot and choropleth of disease burden by state; construct 2x2 tables with epitools, compute RR/RD with confidence intervals and directly standardize rates.
Case-control studies, bias and confounding — odds ratios, matching, DAGs, effect modification and Simpson's paradox; probability, hypothesis testing and confidence intervals — distributions, p-values, chi-square, Fisher, t-tests and Wilcoxon.
LabCalculate ORs and CIs with epitools, run Mantel-Haenszel stratified ORs with epiR and build a DAG with ggdag; simulate sampling distributions, run common statistical tests and build descriptive tables with gtsummary.
Linear regression for epidemiological data — simple and multiple regression, confounding adjustment, diagnostics and interactions; logistic regression and multivariable adjustment — binary outcomes, adjusted odds ratios, model building, model fit and STROBE reporting.
LabFit lm() models with diagnostic and coefficient plots and gtsummary regression tables; fit glm(family = binomial), extract adjusted ORs and CIs with broom, and build Table 1 + Table 2 workflows.
Epidemic modelling with EpiEstim and EpiNow2 — Rt, serial interval, reporting delays, nowcasting and short-term forecasting; diagnostic testing and screening — sensitivity, specificity, PPV, NPV, likelihood ratios, ROC curves and AUC.
LabEstimate time-varying Rt with EpiEstim and reproduce it with EpiNow2; build diagnostic 2x2 tables with epiR, create ROC curves and AUC with pROC, and simulate how PPV changes with disease prevalence.
End-to-end applied outbreak/cohort case study integrating cleaning, descriptive epidemiology, 2x2 tables, regression and reproducible reporting; capstone presentations with peer critique and evidence-based feedback.
LabWork through an instructor-led applied outbreak/cohort case study and knit it into a reproducible report; present the independent capstone, respond to peer and instructor critique, and revise the final portfolio submission.
Select a real or provided raw, unclean dataset and produce a complete applied epidemiology analysis from raw data to final communication: a documented cleaning pipeline, a descriptive epidemiology summary with well-designed visuals, an appropriate analytic model (regression, Rt/transmission estimation or diagnostic analysis), a discussion of bias, confounding, assumptions and uncertainty — all knitted into one reproducible report and presented for peer and instructor critique.
A transparent path from your first lesson to a portfolio that proves it — with real feedback at every step, not just video to watch.
Every lesson uses the data you already handle — immunization, malaria, ANC, facility reports, DHIS2 exports and outbreak line lists. No toy datasets.
You don't just watch. Each module ends with a guided lab where you clean, calculate, chart or build — so the skill sticks the first time.
Every course closes with an end-to-end project: import, clean, analyze, visualise and report a complete health dataset from start to finish.
Graduate with cleaned datasets, R scripts, dashboards and reproducible Quarto/Typst reports — ready for your LinkedIn, GitHub and your next role.
Public Health Data Analytics Track └── Course [Completed] · [In progress] · [Locked] └── Module + tool-stack badges ├── Lessons (concepts on real health data) └── Hands-on Lab (clean · calculate · chart · build) └── Capstone → Portfolio output
We hold ourselves to the same standard we teach: clear metrics, transparent rubrics, and evidence you can take into an interview or a board meeting.
End-to-end capstone projects you can show employers and donors
Guided labs on real immunization, malaria, ANC, DHIS2 and outbreak data
Reproducible reporting system — reports that rebuild when your data changes
Tools mastered for the job: R, Excel, Power BI, DHIS2 and Quarto/Typst
Unedited recommendations from learners now working across Imperial College London, the University of Leeds and ministries and teams in Nigeria, Saudi Arabia and beyond.
An outstanding experience. The curriculum covered everything — data visualization, statistical analysis, predictive modeling — and each module built my skills and confidence. The hands-on projects let me apply what I learned in a real-world context. I feel well-prepared to tackle data-driven challenges in my career and highly recommend it to anyone looking to excel in this field.
The depth of knowledge significantly enhanced my data analytics skills. The CEO facilitated the sessions herself and broke complex concepts into understandable, actionable steps. Meticulously organized, with the right mix of theory and hands-on exercises. I wholeheartedly recommend BDL to anyone seeking to master R and SQL.
I've taken various trainings in machine learning and data analytics, but this one stands out for the quality of its content and schedule. The commitment and expertise of the facilitator is quite astonishing. I look forward to more training with the BDL team.
An exceptional introduction to Data Science and Data Analysis — well-structured pre-recorded lessons, engaging live classes, and plenty of practical assignments to reinforce learning. I wholeheartedly recommend BDL to both beginners and those advancing their knowledge.
Want results like these? Get the free curriculum guide and we'll map the right course to the work you do.
Get the curriculum guideWant the full curriculum, training for your team, or a project built with us? Tell us the goal and we'll route you to the right person — with the curriculum, scope or next steps that match.
Still unsure? Grab the curriculum guide — it answers most of it in detail.
No. The track starts with R Introduction, which assumes zero code — only basic Excel and a willingness to learn step by step. Each course lists its starting point so you always know what's expected.
If you're new to R, start with Course 1 (R Introduction). If you already use R or Excel confidently, you can jump straight to the course that matches your work — Power BI dashboards, DHIS2, M&E, surveillance or reproducible reporting.
Everything is free and open or widely available: R and RStudio (or Positron), Quarto and Typst, plus Excel and Power BI Desktop for the relevant courses. We walk you through installing each one in the first module.
Yes. Every lab and capstone uses public health data you'll recognise — immunization, malaria, ANC, facility reports, DHIS2-style exports and outbreak line lists — so what you practise is exactly what you do on the job.
Courses run 4–6 weeks each at roughly 4–6 focused hours per week. You can take a single course or work through the full track at your own pace.
A single course gives you one skill end-to-end. The full track is one all-access enrollment that unlocks every course in the track — and any new courses we add later are included automatically, at no extra cost. It's the best value if you're working through more than one or two courses.
Yes. When a sale is on, you'll see the reduced price and an end date right on the pricing and course cards. The price you see is the price you pay — it's frozen the moment you enroll, even if the sale ends mid-checkout.
Yes. We run private cohorts for ministries, NGOs and programs — with the curriculum tuned to your indicators and datasets, plus a progress dashboard for managers. Get in touch to scope it.
A portfolio of real deliverables: cleaned datasets, R scripts, indicator tables, Power BI and Quarto dashboards, and reproducible Typst/PDF reports — plus capstone projects ready for LinkedIn, GitHub and interviews.
Start with the free curriculum guide, or jump straight into the course that matches your work. Either way, you'll finish with a portfolio that proves it.