Most of them are, of course, borrowed from mathematical statistics. But when were they first used, and who first coined these names?
The distingushed statistician Herbert David has written widely on various aspects of the history of statistics. One of his papers, "First (?) Occurrence of Common Terms in Mathematical Statistics", American Statistician, 1995, 49(2), 121-133. You can download a preprint version of the paper here.
As David notes:
That said, here are some of my personal favourites:"Of course, establishing a first occurrence is hazardous; hence the question mark in the title. Some listings are, in fact, unlikely to be firsts but should provide good upper bounds."
- "Method of least squares" - Legendre (1805)
- "Standard error" - Yule (1897)
- "Heteroscedastic / Homoscedastic" - K. Pearson (1905)
- "Estimator" - Pitman (1938)
- "P-Value" - Brownlee (1960)
(Full references appear in David's paper.)
© 2013, David E. Giles