Guesstimate is an informal English portmanteau of guess and estimate, first used by American statisticians in 1934^[1] or 1935.^[2] It is defined as an estimate made without using adequate or complete information,^[3][4] or, more strongly, as an estimate arrived at by guesswork or conjecture.^[2][5][6] Like the words estimate and guess, guesstimate may be used as a verb or a noun (with the same change in pronunciation as estimate). A guesstimate may be a first rough approximation pending a more accurate estimate, or it may be an educated guess at something for which no better information will become available.

The word may be used in a pejorative sense if information for a better estimate is available but ignored.^[7][8]

Guesstimation techniques are used:

• in physics, where the use of guesstimation techniques to solve Fermi problems is taught as a useful skill to science students;^[9]
• in cosmology, where the Drake equation is a well-known guesstimation method;^[10]
• in economics, where economic forecasts and statistics are often based on guesstimates; ^[11] and
• in software engineering, where new development of features and release timelines are based on effort guesstimates of tasks.

Lawrence Weinstein and John Adam's 2009 book Guesstimation: Solving the World's Problems on the Back of a Cocktail Napkin, based on the course "Physics on the Back of an Envelope" at Old Dominion University, promotes guesstimation techniques as a useful life skill. It includes many worked examples of guesstimation, including estimating the total number of miles that Americans drive in a year (about 2 trillion)^[12] and the amount of high-level nuclear waste that a 1 GW nuclear power plant produces in a year (about 60 tons).^[13]