Large samples average out random variation to reveal underlying economic laws
Evidence
The law of large numbers is a statistical theorem broadly to the effect that the greater the number of samples the more likely they are to average out to the mean of the “population” from which they are drawn. In economics this means that the random variations of individual cases will tend “on average” to express the underlying law. — Antonio Gramsci, Selections from the Prison Notebooks, 2687
Categorization
- DEFINE: Defines the law of large numbers as a statistical theorem and its economic application.
- QUESTION: This is likely a foil that Gramsci will critique — how does this statistical thinking relate to his critique of mechanical determinism in economism?
- XREF: connects to: Traders arbitraging model discrepancies directly improved the model’s econometric test results — Donald MacKenzie, An Engine, Not a Camera: How Financial…, 146; A finite sample’s variance cannot distinguish a fat-tailed from an infinite-variance distribution — Donald MacKenzie, An Engine, Not a Camera: How Financial…, 499