Maximum likelihood

Ti Wikipédia, énsiklopédia bébas
Luncat ka: pituduh, paluruh
Panneau travaux.png Artikel ieu keur dikeureuyeuh, ditarjamahkeun tina basa Inggris.
Bantosanna diantos kanggo narjamahkeun.

Dina statistik, métodeu maximum likelihood, dimimitian ku ahli genetika/ahli statistik Sir Ronald A. Fisher, mangrupa métodeu titik estimasi, nu digunakeun keur nga-estimasi anggota populasi nu teu ka-observasi tina paraméter ruang nu di-maksimal-keun ku fungsi likelihood. Tingali p ngalambangkeun paraméter populasi teu ka-observasi nu bakal di-estimasi. Tingali X ngalambangkeun random variable nu di-observasi (which in general will not be scalar-valued, but often will be a vector of probabilistically independent scalar-valued random variables. The probability of an observed outcome X=x (this is case-sensitive notation!), or the value at (lower-case) x of the probability density function of the random variable (Capital) X, as a function of p with x held fixed is the likelihood function

For example, in a large population of voters, the proportion p who will vote "yes" is unobservable, and is to be estimated based on a political opinion poll. A sample of n voters is chosen randomly, and it is observed that x of those n voters will vote "yes". Then the likelihood function is

The value of p that maximizes L(p) is the maximum-likelihood estimate of p. By finding the root of the first derivative one will obtain x/n as the maximum-likelihood estimate. In this case, as in many other cases, it is much éasier to take the logarithm of the likelihood function before finding the root of the derivative:

Taking the logarithm of the likelihood is so common that the term log-likelihood is commonplace among statisticians. The log-likelihood is closely related to information entropy.

If we replace the lower-case x with capital X then we have, not the observed value in a particular case, but rather a variabel acak, which, like all random variables, has a probability distribution. The value (lower-case) x/n observed in a particular case is an estimate; the variabel acak (Capital) X/n is an estimator. The statistician may take the nature of the probability distribution of the éstimator to indicate how good the éstimator is; in particular it is desirable that the probability that the éstimator is far from the paraméter p be small. Maximum-likelihood éstimators are sometimes better than unbiased estimators. They also have a property called "functional invariance" that unbiased éstimators lack: for any function f, the maximum-likelihood éstimator of f(p) is f(T), where T is the maximum-likelihood éstimator of p.

However, the bias of maximum-likelihood éstimators can be substantial. Consider a case where n tickets numbéréd from 1 through to n are placed in a box and one is selected at random, giving a value X. If n is unknown, then the maximum-likelihood éstimator of n is X, even though the expectation of X is only n/2; we can only be certain that n is at léast X and is probably more.