Certificate programme
Econometric analysis
Econometrics is the discipline that takes you from an observed correlation to the estimation of an effect. It answers the questions descriptive statistics leave open: did this programme really improve beneficiaries' income, or were the beneficiaries already better off at the start? Does schooling increase income, and by how much, all else being equal? These questions are at the heart of impact evaluation, applied research and public policy analysis.
- Duration
- 5 weeks, 8 sessions, 40 hours
- Format
- In person or online
- Credential
- Training certificate
Tuition170,000 XOF
By the end of the programme, you will be able to
- Formulate a research question and specify the econometric model that answers it
- Prepare and document a survey dataset in Stata, with a re-runnable do-file
- Estimate, read and compare simple and multiple linear regressions by ordinary least squares
- Diagnose heteroscedasticity, multicollinearity and autocorrelation, and apply a correction
- Estimate a logit or a probit and compute marginal effects
- Identify an endogeneity problem and test a model with instrumental variables
- Produce a regression table and an interpretation note on your own research question
Who it is for
Target audience
The course is for those who must produce or read econometric results: master's students and doctoral candidates in economics, statistics, demography, public health, quantitative sociology or agricultural economics, researchers, statisticians, monitoring, evaluation and impact evaluation specialists, public policy analysts, and economists in banks and institutions.
Prerequisites
This is the most demanding course in the catalogue. The entry conditions are accordingly stricter:
- Hold at least a three-year post-secondary degree (BAC+3) in a field with quantitative teaching: economics, statistics, mathematics, management, demography, public health, agronomy or quantitative social science
- Master the basics of inferential statistics: mean, variance, distribution, sampling, confidence interval, hypothesis test and p-value
- Have already handled a dataset in some tool — Excel, SPSS, R or Python
- Have a personal laptop, on which Stata 19 will be installed during the first session
No prior experience of Stata is required, nor any previous practice of econometrics. The statistical prerequisites above, however, are not negotiable: without them the theory presented from the third session onwards becomes inaccessible, and the participant ends up copying commands without understanding what they produce.
A ten-minute telephone conversation is offered before enrolment to anyone unsure of their level. It is not an examination but an honest check, meant to avoid an expensive and frustrating enrolment.
Teaching method
The course runs over five weeks: two sessions a week in weeks 1 to 3, then one session in weeks 4 and 5 — eight five-hour sessions and 40 supervised hours. Sessions are held on Saturday and Sunday from 8.30 a.m. to 1.30 p.m., in person or online and live, as each participant prefers, at the same price. Personal work takes two to three hours a week, and three to four during the project weeks.
This course differs from the others on one point: theory matters here as much as practice. You cannot handle a regression properly without understanding what it estimates, under which conditions its result holds, and what invalidates a conclusion. Theory and demonstrations are therefore delivered as video capsules, watched remotely before each session for one to two hours; the sessions themselves are spent practising in Stata on real data — household surveys, project monitoring databases, public health data.
Stata 19 is installed on each participant's computer during the first session, with a genuine licence, checked machine by machine. This matters: the licence gives access to every command and module, allows updates and package installation from the official repositories, and removes any legal risk for the participant and their organisation. Everyone keeps a fully functional, legitimate working environment after the course — which counts particularly for a researcher or doctoral candidate whose results will be defended before a panel or submitted to a journal. Recommended configuration: Windows 10 or later, macOS also accepted, 4 GB of RAM minimum, 8 GB preferred, and 3 GB of disk space.
The cohort is limited to fifteen. That ceiling is pedagogical rather than commercial: individual supervision of the final applied work cannot be done properly beyond it.
Every participant leaves with:
- The pre-recorded video capsules for each session
- The complete theoretical material in PDF, organised session by session, with the demonstrations
- All the Stata do-files used in class, commented line by line
- The practice databases and detailed solutions
- A cheat sheet of the Stata commands most used in applied econometrics
- A diagnostic checklist to apply systematically to any regression
- A regression table template meeting academic journal standards
- An annotated bibliography of reference works, accessible and matched to the level of the course
Detailed program
8 sessions · 40 h of teaching
Week 1 — Foundations and getting to grips with Stata
2 sessions · 10 h- Install Stata 19 and activate the licence on every machine
- Get to grips with the interface, the syntax and the do-file, with a session log
- Import a survey from Excel and CSV, then describe and tabulate it
- Create, recode and label variables, then select, sort and de-duplicate
- Merge two datasets and declare the survey design: strata, clusters and weights
- Exercise: clean a household survey dataset and deliver a commented, re-runnable do-file
- Going further, in the course material: reshaping from wide to long, automating with loops, and Stata's built-in help
- Produce descriptive statistics, overall and by subgroup
- Build cross-tabulations and run the chi-squared test
- Compare means with a t-test and one-way analysis of variance
- Draw histograms, box plots and scatter plots, then export tables and charts to Word
- Exercise: write the descriptive section of a household survey from a real dataset
- Going further, in the course material: correlation matrices and how to read them critically; the power of a test
Week 2 — The linear regression model
2 sessions · 10 h- Estimate a simple regression in Stata, then read the output line by line
- Estimate a multiple regression, compare several specifications and store the results
- Test a joint restriction and a linear combination of coefficients
- Estimate log-log and semi-log models, then interpret the coefficients as elasticities or percentages
- Exercise: estimate the link between years of schooling and income, and present it in three specifications
- Going further, in the course material: variance decomposition, the adjusted coefficient of determination and quadratic terms
- Detect heteroscedasticity graphically, then by test
- Estimate with robust and clustered standard errors, and compare the results
- Compute variance inflation factors and decide what to do about them
- Spot influential observations and apply the Ramsey RESET test
- Exercise: diagnose and correct an income model on survey data
- Going further, in the course material: weighted and generalised least squares; normality of residuals, dummy variables and interactions
Week 3 — Diagnostics, corrections and qualitative models
2 sessions · 10 h- Test for autocorrelation with Durbin-Watson and Breusch-Godfrey
- Declare a time series in Stata and plot the autocorrelation
- Estimate with the Newey-West correction and compare the standard errors
- Apply the diagnostic checklist to an already estimated model
- Exercise: correct the autocorrelation of a time series model and comment on the corrected standard errors
- Going further, in the course material: stationarity, unit roots and the augmented Dickey-Fuller test
- Estimate a logit and a probit, then compare the results
- Compute and interpret odds ratios
- Compute average marginal effects and marginal effects at the mean, then plot them
- Assess predictive quality with the classification table
- Exercise: model the determinants of access to a service and write up the interpretation
- Going further, in the course material: multinomial models, ordered models and count models (Poisson, negative binomial)
Week 4 — Endogeneity and scoping the project
1 sessions · 5 h- Estimate by two-stage least squares in Stata and test the strength of the instrument
- Test for endogeneity and for overidentification
- Compare ordinary least squares with instrumental variables, and comment on the gap
- Scope the project: research problem, research question and available data
- Exercise: handle a case of endogeneity on survey data and defend the choice of instrument
- Going further, in the course material: panel data, fixed and random effects, the Hausman test, difference-in-differences and propensity score matching
Week 5 — Applied project, defences and certificates
1 sessions · 5 h- Finalise the estimation and the publication-standard regression table, on your own question or on one of three supplied cases
- Write the interpretation note, with the proper caveats about causal reach
- A ten-minute defence by each participant, followed by five minutes of questions
- Critical feedback from the trainer and from peers on every piece of work
- Certificates awarded to successful participants, attendance certificates to the others
- Exercise: final synthesis — the complete approach, to be repeated on a new empirical question
- Going further, in the course material: the annotated bibliography of reference works and the applied econometrics templates that extend the course
Assessment and certification
This programme leads to a training certificate rather than a simple attestation. It 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 90 minutes. Two attempts are allowed, seven days apart, and the better one counts.
- The final applied project (30%) — presented in the eighth 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 40 hours, the period, the list of modules completed and the subject of the applied 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 applied project with the following cohort, at no extra cost.
Upcoming sessions
Next dates being prepared
Leave your email: we will let you know as soon as registration opens.
Frequently asked questions
170,000 XOF per participant. Training for a team or an organisation is quoted on request.
5 weeks, 8 sessions, 40 hours.
Yes: you can attend onsite or online, as you prefer.
This is the most demanding course in the catalogue. The entry conditions are accordingly stricter: hold at least a three-year post-secondary degree (BAC+3) in a field with quantitative teaching: economics, statistics, mathematics, management, demography, public health, agronomy or quantitative social science ; master the basics of inferential statistics: mean, variance, distribution, sampling, confidence interval, hypothesis test and p-value ; have already handled a dataset in some tool — Excel, SPSS, R or Python ; have a personal laptop, on which Stata 19 will be installed during the first session ; no prior experience of Stata is required, nor any previous practice of econometrics. The…
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.