Über eine Eigenschaft der normalen Verteilungsfunktion

By H. Cramér. 1936

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Causal inference by using invariant prediction: identification and confidence intervals (2015, methodology): “It follows from Cramér’s theorem (Cramér 1936) that Ak0 " 1 k0 must be normally distributed.”
Nonlinear causal discovery with additive noise models (2008, background): “Because x is the sum of two independent random variables (g(y) and ̃), Cramér’s theorem [20] tells us that g(y) and ̃ are normally distributed, too.”
Efficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence (2020, methodology): “It beneﬁts from the following Cram ´ e r’s decomposition theorem [34]: Theorem 1 (Cram ´ e r’s decomposition theorem): Let a random variable ζ from normal distribution and permit a decomposition as a sum ζ = ζ 1 + ζ 2 of two independent random variables.”
Conditionally independent private information in OCS wildcat auctions (2000, background): “As a matter of fact, from Cramer (1936) , none of these distributions can be log-normal.”