Certificate programme
Data Analyst
Data analysts are among the most sought-after profiles today, in Burkina Faso as elsewhere. Organisations produce considerable volumes of data, and very few people know how to turn them into information on which management can actually base decisions.
- Duration
- 6 weeks, 12 sessions, 48 hours
- Format
- In person or online
- Credential
- Training certificate
Tuition150,000 XOF
By the end of the programme, you will be able to
- Turn a decision-maker's question into an analysable question and an analysis plan
- Get data at the source with SQL queries, without depending on anyone else
- Clean, make reliable and document a database of several thousand rows
- Automate a recurring process with Python and the pandas library
- Produce the descriptive statistics and bivariate analyses suited to each question
- Build an interactive Power BI dashboard, published and refreshed automatically
- Choose the chart that serves the message and avoid misleading visuals
- Tell a story with data and convince a non-technical audience
- Automate a complete reporting cycle, from source to distribution
- Use artificial intelligence to speed up every stage of the analysis, checking its results and protecting the data
- Carry out an end-to-end analysis project and present it as a portfolio piece
Who it is for
Target audience
The certificate is for people who want to make data analysis their profession or a significant part of their job: monitoring and evaluation officers, research officers, management controllers, database managers, recent graduates in economics, statistics, management, computer science or social sciences, professionals changing career.
Prerequisites
Three requirements:
- Hold at least a two-year post-secondary degree (BAC+2) in any field, or have proven professional experience in data processing
- Master Excel at intermediate level: structured tables, formulas, sorting, filtering, pivot tables
- Have a personal laptop, with 8 GB of RAM recommended, and an internet connection at home, stable enough for video conferencing if following online
No programming experience is required. However, the pace is demanding and requires regular personal work between sessions, estimated at five hours a week. Candidates who cannot free up this time would do better to start with the short courses in the catalogue.
Teaching method
The certificate runs over six weeks, with two four-hour sessions every weekend, on Saturday and Sunday from 3.30 p.m. to 7.30 p.m. — twelve sessions and 48 supervised hours. Personal work of about five hours a week comes on top.
The course can be followed in person in Ouagadougou, entirely online and live, or alternating between the two from week to week: same hours, same trainer, same individual supervision of the project, same certificate. Each cohort is limited to fifteen participants.
Artificial intelligence is part of every session. Used well, it writes a query, fixes a script or offers a first reading of the results in seconds; used badly, it invents figures and exposes confidential data. Every session therefore teaches how to work faster with it while keeping command of the reasoning and checking what it produces.
Every participant leaves with:
- The complete course material in PDF, module by module
- All the files, queries, notebooks and reports produced in class, with comments
- The practice databases and their solutions
- A library of reusable SQL queries and Python scripts for routine reporting
- A Power BI dashboard template ready to adapt
- A cheat sheet for each tool: Excel, SQL, pandas, Matplotlib and Seaborn, DAX
- A guide to using AI as an analyst: model prompts, verification practices and confidentiality rules
- A guide to building the portfolio and preparing for interviews
All the software used is free or used on a free trial — Power BI Pro for publishing, AI assistants in their free versions — except Excel, which participants already own.
Detailed program
12 sessions · 48 h of teaching
Week 1 — The profession and the foundations of analysis
2 sessions · 8 h- What a data analyst really does day to day in an NGO, a bank or a company
- The data cycle, from collection to decision, and where the analyst comes in
- Turning a vague request into an analysable question, the most decisive skill of the profession
- Telling reliable data from doubtful data before analysing it
- Modern lookup functions: XLOOKUP, INDEX and MATCH
- Dynamic array functions: FILTER, SORT, UNIQUE
- Power Query: importing, cleaning, unpivoting, merging, refreshing
- Automatically consolidating several files from a folder
- Advanced pivot tables: calculated fields, grouping, slicers
- AI: generative AI at the analyst's service
- Exercise: build an Excel processing chain that refreshes in one click
- Types of variables and levels of measurement, and which analyses they allow
- Central tendency and dispersion, and when the mean is misleading
- Distribution, quartiles, outliers, skewness
- The cross-tabulation and reading percentages correctly
- Correlation, strength and direction, and the distinction from causation
- The idea of a sample, margin of error and confidence interval
- The statistical test in plain language: what the p-value says and does not say
- Aggregation pitfalls and Simpson's paradox
- Indicators: rates, ratios, indices, changes, and common calculation errors
- AI: have AI explain a statistical result, then check every one of its claims
- Exercise: produce the complete descriptive analysis of a real dataset and write up its interpretation
Week 2 — Getting the data with SQL
2 sessions · 8 h- Relational databases, tables, primary and foreign keys, reading a schema
- Installing PostgreSQL and DBeaver, connecting to a database
- The structure of a query and its real order of execution
- Selecting, renaming, sorting, limiting, removing duplicates
- Filtering: simple conditions, lists, ranges, text patterns
- Handling null values, the number one source of errors
- Conditional logic with CASE
- Counting, summing, averaging, and the difference between counting rows and values
- Grouping by category, on one and then several columns
- Filtering before or after grouping, a decisive distinction
- Inner join, left outer join, full outer join, and which one to choose
- Diagnosing a join that multiplies rows, the costliest mistake
- AI: turn a plain-language question into an SQL query with AI, then read it back and test it
- Exercise: produce a consolidated monitoring table from five tables
- Subqueries in the filter, the selection and the source
- Common table expressions to break down a complex problem
- Window functions, the principle and why they matter to an analyst
- Ranking and numbering within a group
- Running totals, moving averages, comparison with the previous row
- Relating a value to its group total without losing detail
- Creating a view to save a reusable reporting query
- Connecting the database to Excel and Power BI
- AI: have AI debug, explain and optimise a complex query
- Exercise: build a department's monthly reporting queries, then save them as views
Week 3 — Automating with Python
2 sessions · 8 h- Google Colab and the notebook: cells, execution, execution order
- Variables, types, operations, display
- Lists, dictionaries, and how they are really used in analysis
- Conditions, loops, functions
- Reading an error message and fixing it
- Reading and writing Excel and CSV files
- The pandas data frame and how it relates to an Excel sheet
- Exploring: dimensions, types, preview, statistical summary
- Selecting, filtering, sorting
- Missing values: counting them, understanding their pattern, dropping or replacing them
- Duplicates and outliers
- Converting dates and extracting year, month and day of the week
- AI: coding with an AI assistant in Colab — framing the request, understanding and correcting the code it proposes
- Exercise: fully clean a raw survey dataset and document every step
- Grouping and aggregating, the programmed equivalent of the pivot table
- Cross-tabulations in one line of code, and multiple aggregations
- Merging two datasets on a common key, the four types of join
- Stacking several files with the same structure
- Moving from wide to long format and back
- Computing derived indicators: changes, shares, running totals
- Visualising with Matplotlib: lines, bars, histograms, scatter plots, titles and annotations
- Statistical graphics with Seaborn: distributions, box plots, heatmaps, comparisons by group
- Exporting to Excel across several formatted sheets
- Automatically generating a set of tables and charts
- Structuring a reusable script and documenting it
- AI: speeding up script writing with AI without losing command of the code
- Exercise: build the complete production chain for a department's monthly reporting
Week 4 — Presenting with Power BI
2 sessions · 8 h- Choosing the representation that fits the message: comparison, change over time, composition, distribution, relationship
- Charts to avoid and why: the overloaded pie, the truncated axis, three-dimensional effects
- Colour as a signal, not as decoration
- Designing the layout before touching the tool: which decision-maker, which decision, which indicators
- Installation, interface, the Report, Data and Model views
- Connecting to Excel, CSV, a folder, an SQL database
- The star schema, fact tables and dimension tables
- Creating relationships, cardinality, filter direction
- The date table, an essential step in any analysis over time
- Calculated column or measure, the founding distinction
- The essential DAX measures and the CALCULATE function
- AI: writing and understanding DAX measures with AI, an overview of Copilot in Power BI
- Exercise: model and compute the ten indicators of an activity monitoring report
- Building the report pages: visuals, cards, matrices
- Slicers, filters, interactions between visuals
- Drilling down from national level to the municipality
- Bookmarks, buttons and guided navigation
- The report theme in the organisation's colours
- Publishing to the Power BI Service, workspaces and roles
- Scheduled refresh and the data gateway
- Sharing, row-level security, email subscriptions
- Mobile layout and viewing on a phone
- AI: natural-language questions and automatic summaries inside the report
- Exercise: publish a complete dashboard, shared and refreshed automatically
Week 5 — Analysing, telling the story and automating
2 sessions · 8 h- The exploratory approach: what to look at first when facing an unfamiliar dataset
- Spotting an anomaly, a break, a seasonal pattern
- Segmenting a population and comparing the segments
- Comparing two groups and knowing whether the difference is real
- The commonest analytical biases and how to guard against them
- The structure of a data story: situation, complication, question, answer
- Starting with the conclusion, not with the method
- Adapting the same result to three audiences: management, technical staff, funder
- A chart title must state the message, not describe the axis
- Writing a two-page analysis note and a ten-minute presentation
- AI: exploring a dataset with AI and drafting a first version of the analysis note, then checking it
- Exercise: explore a real dataset, then present your findings to three different audiences in front of the group
- Mapping an existing reporting cycle and spotting what repeats
- Chaining SQL, Python and Power BI into a single pipeline
- Scheduling a script to run automatically
- Automatically generating a Word or PDF report from the results
- Automatically sending the report to its recipients
- Automatic quality checks and alerts when something looks wrong
- Documenting a pipeline so that a colleague can take it over
- Versioning your work and organising your files
- AI: have AI draft a first summary of the monthly report, then read it back and correct it
- Launch of the portfolio project: choosing the subject and the scoping note, due before the next session
- Exercise: fully automate a monthly reporting cycle, from the database to the email sent
Week 6 — The portfolio project
2 sessions · 8 h- Review of the scoping note — your own subject or one of five supplied cases: question, sources, method, deliverable, timetable
- Assembling the dataset and checking its quality before committing to it
- Individual validation of the scoping note by the trainer
- Extracting and preparing the data
- Analysis and production of the results
- Building the dashboard or the report
- Cross-checking the figures produced
- The trainer works individually with each participant
- AI: supervised use of AI in the project, declared and documented in the method note
- Deliverable: validated scoping note, verified dataset and first results
- A ten-minute presentation by each participant in front of the group, followed by five minutes of questions, in the room or by video
- Defending the methodological choices and answering questions
- AI: presenting and defending your choices, including the share of the work entrusted to AI and how it was checked
- Critical feedback from the trainer and from peers
- Award of certificates
- Deliverable: project defended, analysis note and dashboard published in the portfolio
Assessment and certification
The Data Analyst certificate is awarded on an admission average out of 20, made up of three components:
- The certification exam (50%) — 25 questions drawn at random from a bank of more than eighty, in 75 minutes. Two attempts are allowed, seven days apart, and the better one counts.
- The portfolio project (30%) — defended in the twelfth session.
- Attendance (20%) — recorded session by session. An absence announced at least three days in advance counts as half; an unannounced absence does not count.
The admission average is 12 out of 20. A mark below 8 out of 20 in the exam is eliminatory: neither the project nor attendance can make up for it. As soon as the average is reached, the certificate is issued automatically and becomes available in the participant's account.
The certificate is issued by Waaldé Impact, signed by the trainer, and states the course title, the 48 hours, the period, the list of modules completed and the subject of the portfolio project presented. Each certificate carries a unique number and a verification code.
Participants who do not reach the average receive a certificate of attendance. They may retake the exam and present their portfolio project with the following cohort, at no extra cost.
Upcoming sessions
- Enrolment closed
Promotion 1 — octobre 2026
October 24, 2026 to December 5, 2026 · Ouagadougou
Frequently asked questions
150,000 XOF per participant. Training for a team or an organisation is quoted on request.
6 weeks, 12 sessions, 48 hours.
Yes: you can attend onsite or online, as you prefer.
Three requirements: hold at least a two-year post-secondary degree (BAC+2) in any field, or have proven professional experience in data processing ; master Excel at intermediate level: structured tables, formulas, sorting, filtering, pivot tables ; have a personal laptop, with 8 GB of RAM recommended, and an internet connection at home, stable enough for video conferencing if following online ; no programming experience is required. However, the pace is demanding and requires regular personal work between sessions, estimated at five hours a week. Candidates who cannot free up this time would do better to start with the short courses in the catalogue. A free pre-test helps you gauge your level before enrolling; its result is only indicative and never prevents enrolment.
Yes: participants who meet the completion requirements receive a Waaldé Impact certificate with a unique number that employers can verify online.
Fill in the online enrolment request: no payment is taken on the site. The firm reviews your application, then contacts you to confirm your place and the payment terms. No session is scheduled yet: leave your email on this page to be told when registration opens.
Join the next cohort
Cohorts are deliberately small to guarantee genuine individual support. Reserve your place or ask us your questions.