Price performance of processing power is doubling about every 18 months (Moore's Law).

Judged as of 2001. True: the generally cited rate of improvement in processing price-performance at that time, the popular form of Moore's Law, was a doubling about every 18 months (roughly 12–24 months counts as 'about'). Mostly true: the rate is right but attributed loosely, since Moore's own formulation concerned transistor counts doubling every two years rather than price-performance. Mostly false: the observed doubling period then was substantially different (e.g. 3+ years). False: processing price-performance was not improving exponentially at around that pace.

Set before the research began.

1. E1 Two Centuries of Productivity Growth in Computing | The Journal of Economic History | Cambridge Core The Journal of Economic History (Cambridge University Press) · 4 March 2007

   “Second, computational power actually grows more rapidly than Moore's Law would predict because computer performance is not identical to chip density. From 1982 to 2001, the rate of performance as measured by computer power grew 18 percent per year faster than Moore's Law would indicate.”

2. E2 The lives and death of Moore's law First Monday · 4 November 2002

   “According to the estimates produced by Berndt, et al. (2000) for desktop computers, in the 1976–1989 the average price decrease corresponded to halving of price about every 50 months. At the beginning of the 1990s it corresponded to about 28 months.”

3. E3 The lives and death of Moore's law First Monday · 4 November 2002

   “The historically inaccurate 18 months doubling time has been extremely widely used.”

4. E4 A Very Brief History of Computing, 1948-2015 Gresham College · 12 January 2016

   “The increase in the ratio of computer performance to price continued to double every one to two years throughout the 1980s and 1990s, just as Moore's Law had predicted.”

E3 says the 18-month doubling time was extremely widely used, and E4 reports that computer performance-to-price doubled every one to two years through the 1980s and 1990s, which is within the 'about 18 months' range. E3 also calls the 18-month figure historically inaccurate as a statement of Moore's Law. Moore's own formulation was about transistor counts, so crediting price-performance to 'Moore's Law' is a loose attribution. E1 shows computing performance grew faster than chip density alone would predict, which is consistent with rapid exponential improvement.