NGO Data Science and Impact Measurement Training Course

Course overview

NGOs increasingly hold programme monitoring data, beneficiary records, survey results and financial information, yet many teams struggle to convert these sources into credible evidence for decisions, donor reports and programme redesign. Common problems include inconsistent indicator definitions, incomplete Kobo or spreadsheet data, weak baselines, dashboards that show activity rather than outcomes, and impact claims that cannot withstand review. This course equips practitioners to analyse NGO data with appropriate statistical discipline while keeping ethical safeguarding, consent and data-protection obligations central to the work.

Participants learn to build an end-to-end impact measurement workflow: frame a theory of change, define SMART indicators, design a data collection plan, clean and validate programme datasets, explore patterns in Python, calculate disaggregated results, and communicate findings in Power BI. The course covers descriptive statistics, sampling, baseline and endline comparisons, contribution analysis, quasi-experimental design choices, data-quality assessment, and practical approaches to measuring outcomes for different groups. Participants also learn how to distinguish monitoring, evaluation and impact measurement, and how to state evidence limitations honestly.

Delivery combines instructor-led explanation with hands-on analysis of realistic NGO programme datasets covering health, livelihoods, education and protection interventions. Participants work in teams to investigate a programme question, document cleaning decisions, develop an indicator dashboard, and present a defensible findings narrative to a simulated donor review panel. Each participant leaves with an impact measurement project pack: a theory-of-change template, indicator reference sheet, data-quality plan, reproducible analysis notebook, Power BI dashboard and a 90-day implementation plan for their organisation.

The course is designed for monitoring, evaluation, accountability and learning professionals, programme managers, researchers and data specialists who already work with NGO data and need stronger analytical capability for evidence-led programme management.

Course objectives

By the end of this course, participants will be able to:

• Construct a theory of change linking activities, outputs, outcomes and measurable assumptions
• Define disaggregated SMART indicators with calculation formulas, data sources and targets
• Clean, merge and validate programme datasets in Python using reproducible data-processing steps
• Apply descriptive statistics, confidence intervals and subgroup analysis to beneficiary data
• Design baseline, endline and comparison-group measurement approaches suited to NGO programmes
• Assess data quality using completeness, timeliness, accuracy, consistency and integrity checks
• Build a Power BI impact dashboard with disaggregated indicators, filters and evidence notes
• Produce an impact measurement project pack containing findings, limitations and action recommendations

Benefits of attending

Target competencies

Who should attend

• Monitoring, Evaluation, Accountability and Learning Officers — who need to turn routine monitoring data into credible programme evidence
• Programme Managers — who must use outcome data to adapt delivery and justify resource decisions
• Impact Measurement Specialists — who need reproducible analytical methods for donor-facing reporting
• NGO Data Analysts — who clean, analyse and visualise programme, survey and beneficiary datasets
• Research and Evaluation Officers — who design studies and need practical quasi-experimental measurement options
• Grant and Donor Reporting Managers — who must present defensible results, disaggregation and evidence limitations

Requirements and prerequisites

Participants should have experience working with NGO programme data, such as beneficiary registers, monitoring spreadsheets, survey exports or indicator reports. They should understand basic spreadsheet tasks including filtering, sorting, formulas and charts, and be comfortable interpreting percentages, averages and simple tables. Prior exposure to a results framework, logframe or theory of change is helpful. No prior Python programming, Power BI development, advanced statistics or formal evaluation qualification is required; these are taught through guided exercises. Participants should bring a laptop on which they can install or access the required course tools.

Training methodology

The instructor uses short technical briefings followed by guided work on realistic NGO datasets, including beneficiary registrations, KoboToolbox survey exports and routine monitoring records. Participants build analysis steps in Python, test data-quality rules, calculate indicators and develop Power BI visuals rather than only reviewing examples. Case discussions examine ethical data use, donor evidence requests and misleading impact claims. Small groups critique one another's theories of change and findings narratives. The final day is an applied studio in which each participant completes an implementation plan for a live or proposed organisational measurement challenge.

Course outline

Day 1: Impact measurement foundations for NGOs

• Monitoring, evaluation, accountability and learning distinctions
• Theory of change causal pathways
• Outputs, outcomes and impact definitions
• Assumptions, risks and external factors
• Results frameworks and logframe alignment
• Evidence standards for donor reporting
• Ethical principles for beneficiary data

Workshop: Participants map a theory of change for a livelihoods programme and identify measurable causal assumptions.

Day 2: Indicators and measurement design

• SMART indicator specification
• Indicator reference sheet components
• Numerators, denominators and calculation formulas
• Disaggregation by sex, age, disability and location
• Target setting and baseline values
• Output versus outcome indicator selection
• Data collection frequency and ownership

Workshop: Participants create an indicator reference sheet for three outcomes in a selected NGO programme.

Day 3: Data collection, protection and quality

• Survey instrument design principles
• KoboToolbox form logic and validation constraints
• Sampling frames and respondent selection
• Informed consent and safeguarding protocols
• Personally identifiable information minimisation
• Data-quality dimensions and verification checks
• Data management plans and access controls

Workshop: Participants review a KoboToolbox-style household survey form and produce a data-quality and safeguarding checklist.

Day 4: Preparing programme data in Python

• Jupyter Notebook workflow and documentation
• Importing CSV and Excel programme exports
• Data types, missing values and duplicate records
• Pandas filtering, grouping and joins
• Standardising categories and location names
• Outlier detection and plausibility rules
• Reproducible data-cleaning audit trails

Workshop: Participants clean and merge beneficiary registration and attendance files in a documented Python notebook.

Day 5: Exploratory analysis and disaggregation

• Frequency tables and cross-tabulations
• Means, medians and distribution shapes
• Subgroup analysis and equity questions
• Programme reach versus participant completion
• Missing-data pattern assessment
• Trend analysis across reporting periods
• Interpretation pitfalls in small subgroups

Workshop: Participants analyse who accessed and completed an education programme, producing a disaggregated results table.

Day 6: Measuring change and statistical confidence

• Baseline and endline comparison design
• Percentage-point and relative change calculations
• Confidence intervals for proportions and means
• Statistical significance and practical significance
• Sample size considerations for NGO surveys
• Paired and independent group comparisons
• Plain-language interpretation of uncertainty

Workshop: Participants assess endline change in household income outcomes and write an evidence statement with confidence limits.

Day 7: Attribution, contribution and evaluation design

• Attribution versus contribution claims
• Comparison groups and counterfactual logic
• Difference-in-differences design basics
• Propensity score matching use cases
• Contribution analysis evidence chains
• Process tracing for programme assumptions
• Threats to validity and mitigation

Workshop: Participants select and defend an evaluation design for a cash-transfer programme operating across multiple districts.

Day 8: Impact dashboards in Power BI

• Power BI data model fundamentals
• Relationships between programme datasets
• DAX measures for indicator calculations
• Disaggregated visuals and slicers
• Targets, benchmarks and conditional formatting
• Dashboard accessibility and visual integrity
• Evidence notes and methodological caveats

Workshop: Participants build a Power BI dashboard showing reach, outcome progress and equity gaps for a health programme.

Day 9: Communicating evidence for decisions

• Findings narratives for programme managers
• Donor reporting evidence tables
• Data visualisation selection rules
• Communicating null and negative results
• Stating limitations without undermining credibility
• Recommendation prioritisation and ownership
• Learning questions for adaptive management

Workshop: Participants prepare a five-slide donor and management briefing from their dashboard findings and receive peer review.

Day 10: Applied NGO impact measurement studio

• Scoping an organisational measurement challenge
• Selecting priority decisions and users
• Defining a minimum viable dataset
• Sequencing data collection and analysis tasks
• Assigning governance and quality responsibilities
• Building a 90-day implementation roadmap
• Presenting an evidence-based action case

Workshop: Participants present their completed impact measurement project pack and 90-day implementation plan to a simulated leadership panel.

Tools & standards covered

Python, Jupyter Notebook, Power BI, KoboToolbox

A typical training day

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

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

What the fee includes

How you can take this course

Certification

Participants who complete the full five days receive the Skillset Development Certificate of Completion, stating the course title, course code, dates and delivery format — suitable for professional-development records and employer reimbursement.

Frequently asked questions