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:
“Our ego ideal is precious to us because it repairs a loss of our earlier childhood, the loss of our image of self as perfect and whole, the loss of a major portion of our infantile, limitless, ain’t-I-wonderful narcissism which we had to give up in the face of compelling reality. Modified and reshaped into ethical goals and moral standards and a vision of what at our finest we might be, our dream of perfection lives on—our lost narcissism lives on—in our ego ideal.”
—Judith Viorst (20th century)
“When Western people train the mind, the focus is generally on the left hemisphere of the cortex, which is the portion of the brain that is concerned with words and numbers. We enhance the logical, bounded, linear functions of the mind. In the East, exercises of this sort are for the purpose of getting in tune with the unconscious—to get rid of boundaries, not to create them.”
—Edward T. Hall (b. 1914)
“and Olaf, too
preponderatingly because
unless statistics lie he was
more brave than me: more blond than you.”
—E.E. (Edward Estlin)