ScholarSignal
Menu
Sign inEvaluate an idea

Evidence · Brand growth

Laws of buyer behaviour: what repeat-buying research shows

Buying in competitive repeat-purchase markets follows a small set of regularities: most people split their purchases across a repertoire of brands, smaller brands have fewer and slightly less loyal buyers, brands share customers roughly in line with their size, and a large part of any brand's sales comes from light buyers. These patterns are summarised by the NBD-Dirichlet model and have been replicated across many categories and countries. They are norms for stable markets; subscription markets and partitioned categories behave differently.

Definition

The laws of buyer behaviour are empirical generalisations about repeat buying that hold across many categories, countries and periods. The main ones are the negative binomial pattern of purchase frequency, double jeopardy, repertoire (split) loyalty, the duplication of purchase law, under which a brand shares its buyers with other brands in proportion to their penetration, and the dominance of light buyers in any brand's customer base. They are called laws because they recur, not because anyone has shown they cannot be broken.

What the research finds

One model describes the brand performance measures

The NBD-Dirichlet model predicts penetration, purchase frequency, share of category requirements and duplication across categories and countries from very few inputs, and it serves as the reference point for the other regularities.[1][2][3]

Double jeopardy is structural

Smaller brands have fewer buyers who are slightly less loyal, a pattern explained by market structure rather than by marketing. It has survived decades of differentiated replication and holds whether loyalty is measured as purchase frequency or as spend per buyer.[4][5][6]

Loyalty is split between repertoire and subscription markets

In repertoire markets such as packaged goods, buyers are loyal to several brands and each brand meets a small share of its buyers' needs. In subscription markets such as banking or telecoms, each brand meets a large share. Few markets sit in between, and the Dirichlet fits both types with very different values of its loyalty parameter.[7][8]

A brand's buyer base is mostly light and unstable

Buyers who purchase a brand once a year or less make up about 62% of its buyers over five years and supply about 31% of its volume. The heaviest 20% of buyers typically contribute not much more than half of sales, and about half of them drop out of the top group the following year; this last evidence comes from a working paper.[9][10]

The regularities reach beyond packaged goods

Similar patterns appear among sport team brands, cigarettes and retail financial services. In banking and insurance, customers share their business between competing brands in line with market share, and brands with similar images do not form separate partitions in actual usage.[11][12][13]

Deviations are systematic and diagnosable

Departures from the model's predictions fall into recurring types that point to non-stationary markets, partitions or brands in growth or decline. One recurring departure is that large brands attract buyers who buy the category less often than buyers of small brands.[14][15]

How strong is the evidence?

These regularities rest on a large body of purchase-panel studies across many categories and countries, several of them in leading journals. Most of the work comes from the Ehrenberg-Bass Institute and allied researchers, so independent replication is thinner than the volume of studies suggests, and some figures on heavy buyers come from a working paper. The laws describe stable, competitive repeat-purchase markets. They say little about why individual consumers choose, and subscription markets, partitioned categories and fast-changing markets need separate treatment.

Claims tested against the evidence

References

  1. Gerald J. Goodhardt, Andrew S. C. Ehrenberg, Christopher Chatfield (1984). The Dirichlet: A Comprehensive Model of Buying Behaviour. Journal of the Royal Statistical Society. Series A (General).
  2. Andrew S. C. Ehrenberg, Mark D. Uncles, Gerald J. Goodhardt (2004). Understanding Brand Performance Measures: Using Dirichlet Benchmarks. Journal of Business Research.
  3. Carl Driesener, Cam Rungie (2022). The Dirichlet Model in Marketing. Journal of Consumer Behaviour.
  4. Andrew S. C. Ehrenberg, Gerald J. Goodhardt, T. Patrick Barwise (1990). Double Jeopardy Revisited. Journal of Marketing.
  5. Charles Graham, Dag Bennett, Katrin Franke, Cathy Lu Henfrey, May Nagy-Hamada (2017). Double Jeopardy – 50 Years On. Reviving a Forgotten Tool that Still Predicts Brand Loyalty. Australasian Marketing Journal (AMJ).
  6. John Dawes, Allison E. Bond, Nicole Hartnett, Byron Sharp (2017). Does Double Jeopardy Apply Using Average Spend per Buyer as the Loyalty Metric?. Australasian Marketing Journal (AMJ).
  7. Byron Sharp, Malcolm Wright, Gerald Goodhardt (2002). Purchase Loyalty is Polarised into Either Repertoire or Subscription Patterns. Australasian Marketing Journal.
  8. Mark D. Uncles, Andrew S. C. Ehrenberg, Kathy Hammond (1995). Patterns of Buyer Behavior: Regularities, Models, and Extensions. Marketing Science.
  9. Afsana Hossain, Zachary William Anesbury, Carl Driesener, Giang Trinh (2023). Valuing the Contribution of Ultra-Light Buyers. Journal of Consumer Behaviour.
  10. Byron Sharp, Jenni Romaniuk, Charles Graham (2019). Marketing’s 60/20 Pareto Law. SSRN Electronic Journal.
  11. Jason P. Doyle, Kevin Filo, Heath McDonald, Daniel C. Funk (2012). Exploring sport brand double jeopardy: The link between team market share and attitudinal loyalty. Sport Management Review.
  12. John Dawes (2014). Cigarette brand loyalty and purchase patterns: An examination using US consumer panel data. Journal of Business Research.
  13. John Dawes (2014). Patterns in competitive structure among retail financial services brands. European Journal of Marketing.
  14. John Scriven, John Bound, Charles Graham (2017). Making Sense of Common Dirichlet Deviations. Australasian Marketing Journal (AMJ).
  15. John Dawes (2020). The Natural Monopoly Effect in Brand Purchasing: Do Big Brands Really Appeal to Lighter Category Buyers?. Australasian Marketing Journal.

Bibliographic details only. Follow the DOI to read each study at its publisher.

Related topics

A synthesis of 15 studies, written by ScholarSignal. Last reviewed 2026-09-26.

Building on this evidence?

ScholarSignal checks a new research idea against the closest existing work and an editor rubric, and tells you whether the contribution is new enough for the journals you target.

Evaluate my idea for free