Isye 2027

# Let now a c a then because cos is monotone

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: − λt)e−λt , dλ the likelihood is increasing in λ for 0 ≤ λ ≤ 1 , and it is decreasing in λ for λ ≥ 1 , so the likelihood t t is maximized at 1 . That is, λM L (t) = 1 . t t Example 3.7.2 Suppose it is assumed that X is drawn at random from the uniform distribution on the interval [0, b], where b is a parameter to be estimated. Find the ML estimator of b given X = u is observed. (This is the continuous-type distribution version of Example 2.8.2.) Solution: The pdf can be written as fb (u) = 1 I{0≤u≤b} . Recall that I{0≤u≤b} is the indicator b function of {0 ≤ u ≤ b}, equal to one on that set and equal to zero elsewhere. The whole idea now is to think of fb (u) not as a function of u (because u is the given observation), but rather, as a 1 function of b. It is zero if b < u; it jumps up to u at b = u; as b increases beyond u the function decreases. It is thus maximized at b = u. That is, bM L (u) = u. 3.8 3.8.1 Functions of a random variable The distribution of a function of a random variable Often one random variable is a func...
View Full Document

## This note was uploaded on 02/09/2014 for the course ISYE 2027 taught by Professor Zahrn during the Spring '08 term at Georgia Tech.

Ask a homework question - tutors are online