Probability distributions and orthogonal parameters
作者： V. S. Huzurbazar
DOI: 10.1017/S0305004100025743
关键词:
摘要: Let f(x, α i ) be the probability density function of a distribution depending on n parameters (i = 1,2,..., n). Then following Jeffreys(1) we shall say that are orthogonal if E(∂ 2 /∂α ∂α j × logf) ≡ 0 for all i, (i≠j).
harvard.edu
sci-hub.se 参考文章(3)
Harold Jeffreys, R. Bruce Lindsay, Theory of probability ,(1939)
The Law of Error and the Combination of Observations Philosophical Transactions of the Royal Society A. ,vol. 237, pp. 231- 271 ,(1938) , 10.1098/RSTA.1938.0008
Luther P. Eisenhart, Riemannian Geometry ,(1950)