Frederick Mosteller and David L. Wallace are almost always discussed together because they collaborated on one of the most famous studies in the history of statistical authorship attribution.
Their landmark work analyzed the authorship of:
The Federalist Papers.
This study is widely regarded as the foundational moment of modern stylometry—the first time rigorous statistical analysis was applied to determine literary authorship.
Before their research, authorship debates were mainly resolved through historical speculation and literary intuition.
Mosteller and Wallace showed that statistical methods could provide strong empirical evidence.
Their work established the methodological foundation later developed by scholars such as:
- John F. Burrows
- Patrick Juola
- Moshe Koppel
2. Historical Background: The Federalist Papers Problem
The Federalist Papers are a collection of 85 essays written in 1787–1788 defending the proposed United States Constitution.
They were published anonymously under the pseudonym:
Publius
The essays were written primarily by three American founders:
- Alexander Hamilton
- James Madison
- John Jay
However, the authorship of 12 essays became historically disputed.
Historians debated for nearly 150 years whether these essays were written by Hamilton or Madison.
This unresolved debate attracted the attention of statisticians.
3. Biography of Frederick Mosteller
Frederick Mosteller (1916–2006) was one of the most influential statisticians of the 20th century.
He spent much of his career at:
Harvard University.
Academic contributions
Mosteller made major contributions to:
- statistics
- medical research methodology
- educational testing
- data analysis
He helped popularize statistical reasoning across disciplines, including the humanities.
Mosteller believed that statistical methods should be applied to real-world intellectual problems, not only theoretical mathematics.
4. Biography of David Wallace
David L. Wallace (1928–2012) was also a statistician and collaborator of Mosteller.
He worked at:
University of Chicago.
Wallace specialized in:
- Bayesian statistics
- decision theory
- applied probability
He shared Mosteller’s interest in applying statistical methods to practical analytical questions, including literary authorship.
5. Their Famous Book
Their most important work is the book:
Inference and Disputed Authorship: The Federalist (1964)
This book became one of the most famous case studies in applied statistics.
It demonstrates how mathematical analysis can resolve a historical and literary debate.
6. Their Methodological Approach
Mosteller and Wallace introduced a revolutionary approach:
using word frequency statistics to determine authorship.
Instead of analyzing themes or ideas, they focused on small function words, such as:
- the
- of
- to
- upon
- by
These words are especially useful because they:
- occur frequently
- carry little thematic meaning
- reflect unconscious linguistic habits.
7. Their Bayesian Statistical Model
Their study relied heavily on Bayesian probability theory, originally developed by:
Thomas Bayes.
The core idea is to calculate the probability that a particular author produced a given text based on observed linguistic features.
The fundamental rule used is:
by John F. Burrows, which compares word-frequency patterns between texts.
Machine learning stylometry
Later researchers such as:
- Patrick Juola
- Moshe Koppel
applied computational algorithms to authorship attribution.
12. Broader Applications
The methods pioneered by Mosteller and Wallace are now used in many fields.
forensic linguistics
identifying authors of threatening letters.
historical scholarship
resolving disputed documents.
cybersecurity
detecting anonymous online writers.
plagiarism detection
identifying ghostwriting.
13. Their Intellectual Legacy
Their work established several key principles that still guide stylometry.
- Function words are powerful stylistic indicators.
- Statistical models can reveal hidden linguistic patterns.
- Authorship attribution should rely on probabilistic reasoning.
- Quantitative methods can complement humanities research.
14. A Turning Point in the Humanities
The Mosteller–Wallace study represents an early example of what is now called digital humanities.
They demonstrated that mathematical analysis can illuminate questions traditionally studied in literature and history.
This interdisciplinary approach eventually led to modern fields such as:
- computational linguistics
- stylometry
- digital literary studies.
Conclusion
Frederick Mosteller and David Wallace revolutionized authorship attribution by applying Bayesian statistical analysis to literary texts.
Their study of the Federalist Papers showed that:
- writing style contains measurable statistical patterns
- these patterns can reveal authorship
- quantitative analysis can solve historical and literary problems.
Their work laid the intellectual foundations for modern stylometry and computational literary studies, influencing generations of researchers in statistics, linguistics, artificial intelligence, and digital humanities.