Loss Functions in Bayesian Statistics
One of the consequences of Bayesian inference is that in addition to experimental data, the loss function does not in itself wholly determine a decision. What is important is the relationship between the loss function and the prior probability. So it is possible to have two different loss functions which lead to the same decision when the prior probability distributions associated with each compensate for the details of each loss function.
Combining the three elements of the prior probability, the data, and the loss function then allows decisions to be based on maximizing the subjective expected utility, a concept introduced by Leonard J. Savage.
Read more about this topic: Loss Function
Famous quotes containing the words loss, functions and/or statistics:
“The poorest children in a community now find the beneficent kindergarten open to them from the age of two-and-a-half to six years. Too young heretofore to be eligible to any public school, they have acquired in their babyhood the vicious tendencies of their own depraved neighborhoods; and to their environment at that tender age had been due the loss of decency and self-respect that no after example of education has been able to restore to them.”
—Virginia Thrall Smith (1836–1903)
“Empirical science is apt to cloud the sight, and, by the very knowledge of functions and processes, to bereave the student of the manly contemplation of the whole.”
—Ralph Waldo Emerson (1803–1882)
“We already have the statistics for the future: the growth percentages of pollution, overpopulation, desertification. The future is already in place.”
—Günther Grass (b. 1927)