Experimental Design & Causality
Correlation vs. causation, experimental anatomy (IV/DV/control), factorial designs, threats to internal and external validity, A/B testing, quasi-experiments, and how AI is transforming experimentation in 2026.
Chapter Section Outline (9 Sections)
Topics and managerial frameworks covered in Experimental Design & Causality:
- 1. Correlation Is Not Causation (And Why That Matters for Marketing)
- 2. The Anatomy of an Experiment
- 3. Factorial Designs: Testing Multiple Variables Simultaneously
- 4. Threats to Validity: What Can Go Wrong
- 5. A/B Testing: The Marketer's Everyday Experiment
- 6. Quasi-Experiments: When Randomization Isn't Possible
- 7. Ethical Issues in Experimentation
- 8. Case Application — ZenBrew Tea Packaging Factorial Experiment
- 9. Putting It All Together: From Research Question to Experimental Design
Interactive Concept Mini-Widgets Embedded in This Chapter (4)
Students manipulate these interactive visual simulations directly inside the chapter reading before answering gated check-in questions:
Real Experiment, or Just ‘Trying It’?
The student flips three design switches on a real scenario — Manipulate an IV? Control/comparison group?
Teaches: "experiment" used loosely (just "trying it") can tell you WHAT happened but never cleanly WHY. All three requirements are needed.
Randomize-or-Not Confound Catcher
A study tests whether an "independent brewer" beer label raises willingness- to-pay. The student runs it under SELF-SELECTED assignment (label shown to craft-festival attendees; no-label outside a grocery store) vs.
Teaches: random assignment balances the variables you didn't even measure — without it, an extraneous variable masquerades as your effect.
Factorial Design Builder
Choose 2 factors (2–3 levels each), name their levels, enter cell means, see signed main effects, an interaction plot and the interaction computed automatically.
Validity Threat Spotter
Two sets behind one switch: 8 research scenarios, each with one threat to internal validity, and 4 studies whose result may not travel (external validity). Student names the threat.
Paired Browser-Based Analytics Calculators (5)
This chapter connects directly to these full MktPraxis analytical apps (with pre-loaded business case scenarios, CSV upload, and reproducible Python export):
🅰️ A/B Proportion Test
Compare conversion rates between two variants.
Pre-loaded Business Scenarios: StudyFlow Newsletter CTA Test · Retargeting Banner Offer Test · Loyalty Partner Offer Test · Social Post CTA Test (Raw Data)
⚖️ A/B Sample Size Planner
Plan n for comparing two groups.
🐙 Multi-Arm A/B Calculator
Plan n for A/B/C/D tests.
⚖️ Propensity Score Matching
Match treatment and control groups to estimate causal effects.
Pre-loaded Business Scenarios: Loyalty Program Enrollment Effect on Annual Spend · Email Marketing Campaign Impact on Conversion · Display Ad Exposure Effect on Brand Awareness · Influencer Content Exposure Effect on Purchase Conversion · Free Trial Activation Effect on Paid Subscription · Premium Coupon Effect on Purchase Conversion · Brand Event Attendance Effect on Post-Event Spend · App Feature Adoption Effect on 30-Day Retention
🏙️ Difference-in-Differences
Estimate whether a campaign, launch or price change really moved results, by comparing the markets that got it with similar markets that didn't.
Pre-loaded Business Scenarios: The Textbook App Launch: In-Store Mobile App Rollout · Hearthstone Coffee: Regional TV Campaign Flight · Pinnacle Fitness: Member App Rollout & The Selection Trap · Oakline Furniture: Showroom Remodels & The Transition Dip