Abstract
MR. TWEEDIE'S demonstration of the relation between the seminvariant-generating (or cumulant-generating) functions of two sets of related distributions is of great interest. However, the word "inverse" is already used in statistical theory, first in the phrase "inverse probability", and secondly in connexion with the problem of finding a distribution with a given characteristic function. If it is used in yet a third sense, some confusion may possibly arise, although "inversion" is already used in geometry and algebra with different meanings, and without inconvenience. It may be added that Mr. Tweedie's letter does not give an alternative solution of the problem raised by my own, since I am concerned with the distribution, not of n, but of R–1n–1;, which gives an unbiased estimate of the probability π.
Similar content being viewed by others
Article PDF
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
HALDANE, J. [Letters to Editor]. Nature 155, 453 (1945). https://doi.org/10.1038/155453b0
Issue Date:
DOI: https://doi.org/10.1038/155453b0
Comments
By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.