Journal.
On people, choices, and the
evidence in between.
Latest articles
174 articles
Market research data analysis: turn the records into a clear decision
Follow a fictional research dataset from raw records through cleaning, response coding, denominators and a wording decision, with copyable data and formulas.
Read article
Conjoint analysis: choose a feasible product and price together
Compare product and price configurations with a transparent bottle choice worksheet. Inspect the design, response source, validation and economics behind a real study.
Read article
What Is Silicon Sampling? AI Synthetic Populations Explained
Inspect silicon sampling studies within their tested scope, then use a fictional five-condition example to see how prompt and profile choices can reverse a recommendation.
Read article
Synthetic personas: model the buying situation that matters
Build synthetic profiles with sourced, derived, assumed and unknown fields. Copy an annotated schema and test how profile choices affect conclusions.
Read article
Monadic pricing: compare one-price reactions and the commercial tradeoff
Compare one price per buyer, then weigh the response against contribution. A worked six-pack example shows the allocation, intent gaps and limits of a three-price test.
Read articleVan Westendorp: use price perceptions to narrow the test
Van Westendorp’s four questions narrow a plausible price range. A worked four-can tea example shows why a crossing starts a price test rather than establishing a revenue or profit optimum.
Read article
MaxDiff: decide which benefits deserve development first
Four meal-planning functions compete for development time. A worked MaxDiff design shows how relative counts guide prototype work and which questions the aggregate scores leave open.
Read articleGabor-Granger: follow the price response into the economics
Gabor-Granger can compare stated buying responses at feasible prices. Follow a six-pack price ladder, then see why revenue and contribution indexes favor different candidates.
Read article
Likert scales: write a clear item, then read the distribution
Ten fictional response records yield 50% agreement among valid ratings and 40% across all records. Reconstruct the difference, then decide what the rating still can’t tell you.
Read articleLeading and double-barreled questions: repair what the survey measures
Repair leading and double-barreled questions with twelve fictional examples, balanced options and a fee-comprehension task you can inspect.
Read article
How to do market research: from lunchbox brief to prototype decision
Follow a complete fictional market research study from exact concept cards and questions to inline response records, a decision rule and a memo.
Read article
Customer segmentation analysis: groups that change the next offer
Work through twelve fictional customer records, reconstruct transparent group rules and summaries, inspect a cutoff change, and decide what the account team should investigate next.
Read article