How unlucky is 25-sigma?

Kevin Dowd, John Cotter, Christopher Humphrey, Margaret Woods

Research output: Contribution to journalArticlepeer-review


Purpose - To identify the likelihood of a 25-standard deviation occurring in stock prices over several successive days, in the light of comments by David Viniar, chief financial officer of Goldman Sachs..
Design/methodology/approach - Assumes a bell-curve of market losses and graphs the probability of an event relative to the number of deviations. Calculates using MATLAB for sigmas over 7. Considers whether the losses of US investment banks in 2008 were the result of bad luck or of incompetence.
Findings - Finds that the probability of a 25-sigma event is every 100,000 +130 decimal points years.
Practical implications - Argues that bad luck is usually associated with incompetence, and investors need not choose between them.
Originality/value - Presents the mathematical absurdity of a finance officer's statement, and its implications.
Original languageEnglish
Pages (from-to)76-80
Number of pages5
JournalJournal of Portfolio Management
Issue number4
Publication statusPublished - Jun 2008


Dive into the research topics of 'How unlucky is 25-sigma?'. Together they form a unique fingerprint.

Cite this