Certificate programme
Statistical analysis
Many professionals can produce a frequency table and a mean. Very few know how to choose the test that suits their data, check its conditions of use, correctly interpret a probability value and write a conclusion that stands up to a statistician's review.
- Duration
- 5 weeks, 10 sessions, 50 hours
- Format
- In person or online
- Credential
- Training certificate
Tuition150,000 XOF
By the end of the programme, you will be able to
- Build an analysis plan tied to a research question and to hypotheses
- Prepare, clean and document a dataset ready for analysis
- Produce sound descriptive statistics and readable charts
- Read a confidence interval and a p-value without over-reading them
- Choose and run the comparison test that suits the variables at hand
- Run a one-way analysis of variance and a linear regression, with residual diagnostics
- Estimate a logistic regression and read its odds ratios
- Write up and defend the results of a complete analysis of your own dataset
Who it is for
Target audience
The certificate is for professionals whose work rests on quantitative data: monitoring and evaluation officers, demographers, epidemiologists, economists, researchers, doctoral candidates and master's students, public health managers, staff of statistical services, consultants and research managers.
Prerequisites
Three requirements:
- Hold at least a two-year post-secondary degree (BAC+2), in any discipline, provided the participant works with data
- Be able to use a computer and a spreadsheet at the level of entry, sorting and simple formulas
- Have a laptop with at least 4 GB of RAM and 15 GB of free disk space
No advanced mathematical background is required. Formulas are presented to be understood, never to be proved. A ten-minute telephone conversation precedes enrolment, so that the examples can be matched to each participant's field.
Teaching method
The certificate runs over five weeks, with two sessions a week, on Saturday and Sunday from 8.30 a.m. to 1.30 p.m. — ten five-hour sessions and 50 supervised hours. Sessions can be followed in person or online and live, as each participant prefers, at the same price. Personal work comes to two or three hours a week, and three to four during the project week.
The format is hybrid: before each session, participants watch at their own pace, remotely, one to two hours of video capsules given to them on enrolment. Theory and demonstrations are presented there; the sessions are given over to practice. Each session also has a "going further" section covered in the course material.
This is not training in a piece of software but in applied statistics, where the software is a means. The three tools most used in Sahel organisations are taught side by side: SPSS for its speed on surveys, R for its power and the fact that it is free, the spreadsheet for simple processing and formatting. Participants learn to run the same analysis in several environments and to choose the one that fits their workplace. R and RStudio are free and open source; an evaluation version of SPSS is used during the course, and the free equivalents are presented so that everyone can keep working without a licence afterwards.
The course ends with the complete analysis of a dataset, from cleaning through to reporting, defended before a panel. It is that work, not a theoretical examination, on which the certificate rests. The cohort is limited to fifteen, with individual supervision.
Workstation: a laptop with at least 4 GB of RAM, 8 GB preferred, and 15 GB of free disk space. The three environments are installed and configured during the first session, with the trainer's help.
Detailed program
10 sessions · 50 h of teaching
Week 1 — The approach, the data and description
2 sessions · 10 h- Formulate a research question, hypotheses and an analysis plan on a real survey
- Identify population, sample, unit, variable and category in a data file
- Identify the measurement scale of each variable and deduce which methods are possible
- Import the same file into SPSS, R and the spreadsheet, and check how each reads it
- Exercise: write the analysis plan of an existing survey and test it against its data
- Going further, in the course material: the standard analysis plan and the quick-start guides for SPSS, R and the spreadsheet
- Declare types and labels, then spot missing values, duplicates and impossible values
- Recode a variable, create age groups and merge two files on an identifier
- Produce frequencies, mean, median and standard deviation, and choose the right measure
- Draw a readable chart: bars, histogram or box plot
- Exercise: clean a real dataset, produce its data dictionary and its descriptive table
- Going further, in the course material: reshaping a dataset from wide to long and back; cross-tabulations in detail
Week 2 — Uncertainty and statistical tests
2 sessions · 10 h- Simulate samples to reveal the sampling distribution
- Compute a standard error and a confidence interval for a mean and for a proportion
- Read a 95 per cent interval without over-reading it
- Compute a simple sample size and an approximate power
- Exercise: estimate an indicator on the participant's own data and write up the interval
- Going further, in the course material: the binomial and Poisson distributions; computing statistical power in detail
- State the null and alternative hypotheses, then interpret a p-value
- Compare a mean with a benchmark, and two means, independent or paired
- Check normality and homogeneity of variances, then move to Mann-Whitney or Wilcoxon if needed
- Run the chi-squared test of independence, read the residuals and compute Cramér's V
- Exercise: run and write up three comparisons on a real dataset
- Going further, in the course material: Fisher's exact test; McNemar's test; Kruskal-Wallis and Friedman; correcting for multiple testing
Week 3 — Relationships, variance and regression
2 sessions · 10 h- Draw the scatter plot before computing any correlation
- Compute a Pearson correlation and a partial correlation, then discuss causation
- Run a one-way analysis of variance and read the overall test
- Run the multiple comparisons and switch to Welch's alternative where needed
- Exercise: compare an indicator across several areas and write up the result
- Going further, in the course material: planned contrasts; analysis of covariance; two-factor and repeated-measures designs
- Fit a regression line and interpret the intercept and the coefficients
- Bring in a categorical variable through dummies and choose the reference category
- Diagnose the model: residuals, influential observations, multicollinearity
- Compare two models and present a publishable regression table
- Exercise: build, diagnose and write up a complete explanatory model
- Going further, in the course material: interaction terms and non-linear effects; automatic variable selection procedures, and why to avoid them
Week 4 — Qualitative models and multivariate analysis
2 sessions · 10 h- Explain why linear regression fails on a binary variable
- Estimate a binary logistic model and read the odds ratios and their intervals
- Assess classification through the threshold, sensitivity, specificity and the ROC curve
- Model count data with Poisson regression, then with the negative binomial
- Exercise: model a risk factor or a determinant of access to a service, and write up the results
- Going further, in the course material: multinomial and ordinal regression; the Hosmer-Lemeshow test; pseudo R-squared measures
- Read a principal component analysis: eigenvalues, correlation circle and contributions
- Test the reliability of a scale with Cronbach's alpha and build a composite index
- Run a hierarchical or k-means clustering, then name the groups
- Scope the project: choice of dataset, your own or one of four supplied, and an approved analysis plan
- Exercise: build a typology of households or organisations and describe it
- Going further, in the course material: multiple correspondence analysis; axis rotation in exploratory factor analysis
Week 5 — Reporting and applied work
2 sessions · 10 h- Write up a test result, a regression result and a descriptive result to standard
- Build the final tables and apply the rules for rounding and reporting probabilities
- Export tables and charts from SPSS or R to Word and Excel
- Prepare the ten-minute presentation and the answers to the panel's questions
- Exercise: finalise the report on your own dataset, with a one-to-one session with the trainer
- Going further, in the course material: automating repetitive tables; presentation graphics in detail
- Defend your work: ten minutes of presentation, then five minutes of questions
- Defend your methodological choices against the panel's questions
- Review another participant's work with the assessment grid
- Go over the cohort's most frequent mistakes together
- Certificates awarded at the end of the session
- Exercise: defend your applied work and assemble your skills portfolio
- Going further, in the course material: where to go next — Stata, data science and survey methodology
Assessment and certification
The statistical analysis 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 80 minutes. Two attempts are allowed, seven days apart, and the better one counts.
- The applied project (30%) — defended in the tenth 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 50 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.
Participants also receive:
- The complete course material in PDF, module by module
- The decision tree for choosing statistical tests, in a printable version
- SPSS syntax files and R scripts for all the analyses seen in class
- The practice datasets and their codebooks
- Results table templates and a model tabulation plan
- A quick reference for writing up statistical results
- A quality control checklist for an analysis before distribution
Upcoming sessions
Next dates being prepared
Leave your email: we will let you know as soon as registration opens.
Frequently asked questions
150,000 XOF per participant. Training for a team or an organisation is quoted on request.
5 weeks, 10 sessions, 50 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 discipline, provided the participant works with data ; be able to use a computer and a spreadsheet at the level of entry, sorting and simple formulas ; have a laptop with at least 4 GB of RAM and 15 GB of free disk space ; no advanced mathematical background is required. Formulas are presented to be understood, never to be proved. A ten-minute telephone conversation precedes enrolment, so that the examples can be matched to each participant's field.
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.