Dedika is a platform where you learn by doing: whether it's creating a business proposal, becoming a nail technician, or using a new tool, for example. No matter your goal, the best content on the topic already exists. But it's often in another language, expensive, scattered around, lacks practice activities, or comes in courses that are too long for busy people. That's why Dedika has its own method: we find this material wherever it is, organize what makes sense for your goal, review it with experts who are available to answer your questions, and create practical exercises so you can learn by doing. You are the most important part of your journey and no one knows it better than you: choose the content and course length, decide if you'll study online or offline, and pick your preferred format. It can be video, text, audio, or a summary. Your way, only with what matters to you. Here, every moment you dedicate counts more and gets you to what matters faster.

Our courses include a summary at the end of each chapter, which you can download as a PDF and print.

Over 2 million learners across the globe

Available in more than 180 countries

Certificate valid in your country

Home Page

...

Causal inference Course

All courses

Business and Economics

Economics

Causal inference Course

For all levels

Causal inference Course

Name: Causal inference Course
Price: 8400 KES

Causal Inference gives you the tools to move beyond correlation and answer the questions that actually drive decisions. You'll master the full toolkit — from randomised experiments to instrumental variables, regression discontinuity, and difference-in-differences. This course is built for researchers, data scientists, and analysts who need rigorous, defensible causal conclusions from real data.

Dedika for businesses

What you will learn:

You will build a foundation in causal reasoning, starting with the potential outcomes framework and directed acyclic graphs. Learn to design and analyse randomised experiments, then extend those skills to observational settings using matching, propensity scores, and regression adjustment. The course covers instrumental variables, regression discontinuity, and difference-in-differences, including staggered adoption approaches. Study mediation analysis, heterogeneous treatment effects, and doubly robust estimators. Sensitivity analysis teaches how robust your conclusions are to unmeasured confounding. By the end, you will be able to select the appropriate identification strategy for any empirical problem and communicate causal evidence precisely.

How you study practically Causal inference Course

How you practise Causal inference Course

For companies looking to train their teams

With Dedika for businesses, the course includes exercises and examples tailored to your own business and the way your company needs.

Click here

Course content

8 Chapters • 40 LessonsDuration between 4 and 360 hours (you decide)

Chapter 1See details

Foundations of Causal Thinking

Lesson 1 • Potential Outcomes Framework
Presents the Rubin potential outcomes model as a formal basis for causal effects. Learners learn to express individual and average treatment effects precisely.
Lesson 2 • Causal Assumptions and Identification
Explains what it means for a causal effect to be identified from data. Covers the core assumptions required before any estimation strategy is valid.
Lesson 3 • Directed Acyclic Graphs Basics
Introduces DAGs as a visual language for encoding causal assumptions. Learners learn to read and draw simple graphs representing data-generating processes.
Lesson 4 • Correlation Versus Causation
Contrasts associational and causal claims using real examples. Establishes why standard statistical associations cannot answer causal questions without additional assumptions.
Lesson 5 • The Language of Causality
Introduces formal causal vocabulary including treatments, outcomes, and confounders. Provides the shared terminology used throughout the entire course.

Chapter 2See details

Randomized Experiments as the Gold Standard

Lesson 1 • Experimental Design Principles
Covers core design choices including unit of randomisation, blocking, and stratification. Learners learn how design decisions affect statistical power and validity.
Lesson 2 • External Validity and Generalisation
Addresses when experimental findings transport to new populations or settings. Introduces reweighting methods for improving external validity.
Lesson 3 • Threats to Experimental Validity
Identifies noncompliance, attrition, and spillover as common threats to valid inference. Learners learn to detect and address each threat analytically.
Lesson 4 • Why Randomisation Solves Confounding
Explains how random assignment balances observed and unobserved confounders in expectation. Connects randomisation to the potential outcomes framework from Chapter 1.
Lesson 5 • Estimating Treatment Effects from Experiments
Teaches difference-in-means estimation and regression adjustment for experimental data. Learners compute ATE estimates and construct valid confidence intervals.

Chapter 3See details

Observational Studies and Confounding Control

Lesson 1 • Matching and Stratification
Introduces matching and stratification as nonparametric alternatives to regression adjustment. Learners apply exact, nearest-neighbour, and coarsened exact matching.
Lesson 2 • Propensity Score Methods
Develops propensity score estimation and its use in weighting and matching. Learners implement inverse probability weighting and diagnose overlap violations.
Lesson 3 • Confounding in Observational Data
Defines confounding precisely using DAGs and potential outcomes. Learners diagnose confounding in realistic data scenarios and understand its consequences for naive estimates.
Lesson 4 • Backdoor Criterion and Adjustment Sets
Teaches the backdoor criterion as a graphical rule for valid covariate adjustment. Learners identify minimal sufficient adjustment sets from a given DAG.
Lesson 5 • Regression Adjustment Methods
Covers linear and nonlinear regression for confounding control under the backdoor criterion. Learners implement and interpret regression-adjusted causal estimates.

Chapter 4See details

Instrumental Variables

Lesson 1 • Two-Stage Least Squares Estimation
Teaches 2SLS as the standard IV estimator and its implementation in practice. Learners compute 2SLS estimates and interpret first- and second-stage results.
Lesson 2 • IV Applications and Extensions
Surveys classic and modern IV applications including natural experiments and shift-share designs. Learners evaluate instrument validity in applied research contexts.
Lesson 3 • The IV Identification Strategy
Explains how a valid instrument breaks the endogeneity problem by providing exogenous variation. Learners connect IV logic to the potential outcomes framework.
Lesson 4 • Instrument Validity Testing
Covers empirical tests for instrument strength and overidentification. Learners apply F-statistics, Sargan-Hansen tests, and placebo checks.
Lesson 5 • Local Average Treatment Effects
Introduces the LATE as the causal estimand identified by IV under heterogeneous treatment effects. Learners distinguish compliers, always-takers, and never-takers.

Chapter 5See details

Regression Discontinuity Design

Lesson 1 • Nonparametric RD Estimation
Covers local polynomial regression and bandwidth selection as the standard RD estimation approach. Learners implement and compare estimators using real data.
Lesson 2 • RD Design Logic and Setup
Explains how a cutoff in an assignment variable creates local quasi-random variation. Learners identify RD-applicable settings and define the local average treatment effect at the cutoff.
Lesson 3 • Fuzzy RD and Kink Designs
Extends RD to settings with imperfect compliance and kinked assignment rules. Learners implement fuzzy RD via 2SLS and interpret regression kink designs.
Lesson 4 • RD Validity Tests
Teaches density tests, covariate balance checks, and placebo cutoff tests to validate RD assumptions. Learners apply each test and interpret results correctly.
Lesson 5 • RD Reporting and Limitations
Addresses external validity constraints and best practices for presenting RD findings. Learners produce publication-quality RD plots and result tables.

Chapter 6See details

Difference-in-Differences and Panel Methods

Lesson 1 • Regression Implementation of DiD
Covers the two-way fixed effects regression as the standard DiD estimator. Learners implement TWFE models and interpret treatment effect coefficients.
Lesson 2 • DiD Logic and the Parallel Trends Assumption
Explains how DiD removes time-invariant confounding by comparing changes across groups. Learners formalise the parallel trends assumption and understand when it is plausible.
Lesson 3 • Testing and Validating DiD Assumptions
Teaches formal pre-trend tests and placebo outcome checks for DiD validity. Learners apply these tests and adjust their designs based on results.
Lesson 4 • Synthetic Control Method
Introduces synthetic control as a complement to DiD for single-unit treatment cases. Learners construct a synthetic control and conduct inference via permutation.
Lesson 5 • Staggered Adoption and Heterogeneous Effects
Addresses the bias in TWFE when treatment timing varies across units. Learners apply modern estimators that handle staggered adoption correctly.

Chapter 7See details

Mediation and Heterogeneous Treatment Effects

Lesson 1 • Heterogeneous Treatment Effects Overview
Introduces the concept of treatment effect heterogeneity and its policy relevance. Learners distinguish average effects from conditional average treatment effects.
Lesson 2 • Estimating Mediation Effects
Covers regression-based and nonparametric methods for estimating mediation. Learners implement mediation analysis and construct valid confidence intervals.
Lesson 3 • Causal Mediation Analysis
Defines direct and indirect effects using the potential outcomes framework. Learners decompose total effects into natural direct and indirect components.
Lesson 4 • Policy Targeting with Heterogeneous Effects
Translates CATE estimates into optimal treatment assignment rules. Learners construct and evaluate policy rules using welfare metrics.
Lesson 5 • Machine Learning for Heterogeneous Effects
Applies causal forests and meta-learners to estimate CATEs from high-dimensional data. Learners implement and evaluate these methods using cross-fitting.

Chapter 8See details

Advanced Identification and Sensitivity Analysis

Lesson 1 • Sensitivity Analysis for Unmeasured Confounding
Teaches Rosenbaum bounds, E-values, and partial R-squared methods to quantify robustness. Learners apply these tools to assess how much hidden bias would overturn conclusions.
Lesson 2 • Interference and Network Effects
Extends causal inference to settings where units interact and SUTVA is violated. Learners define exposure mappings and estimate spillover effects.
Lesson 3 • Communicating Causal Evidence
Develops skills for presenting causal findings to technical and nontechnical audiences. Learners produce clear causal claims with appropriate uncertainty quantification.
Lesson 4 • Doubly Robust and Semiparametric Estimators
Introduces augmented IPW and targeted maximum likelihood as doubly robust estimators. Learners implement these methods and understand their efficiency properties.
Lesson 5 • Comparing Identification Strategies
Provides a unified framework for choosing among IV, RD, DiD, and matching designs. Learners map research questions and data structures to appropriate identification strategies.

Certification

Your valid completion certificate

This course is for you:

Academic researcher: needs credible methods to publish empirical findings confidently.
Data scientist: wants to go beyond predictive models into causal explanation.
Policy analyst: must evaluate whether programmes actually produce intended outcomes.
Economist in training: building the applied toolkit expected in graduate-level work.
Product analyst: tired of A/B tests that don't account for interference or bias.
Epidemiologist: seeks formal frameworks to strengthen observational study conclusions.

What our students say

Your lessons are perfect. I purchased the one-year package and finally have the opportunity to follow various topics of my interest without needing to change platforms... I thank you for everything you do, I've already recommended you to other people...