<< Chapter < Page Chapter >> Page >

In decision making problems, we know the value of the observation, but do not know the value y . Therefore, it is appealing to consider the conditional density or pmf as a function of the unknown values y , with X fixed at its observed value. The resulting function is called the likelihood function. As the name suggests, values of y where the likelihood function is largest are intuitively reasonable indicators of the true value of the unknown quantity, which we will denoteby y * . The rationale for this is that these values would produce conditional densities or pmfs that place high probability on theobservation X = x .

The Maximum Likelihood Estimator (MLE) is defined to be the value of y that maximizes the likelihood function; i.e., in the continuous case

y ^ ( X ) = arg max y p X | Y ( X | y )

with an analogous definition for the discrete case by replacing the conditional densitywith the conditional pmf. The decision rule y ^ ( X ) is called an “estimator,” which is common in decision problemsinvolving a continuous parameter. Note that maximizing the likelihood function is equivalent to minimizing the negative log-likelihoodfunction (since the logarithm is a monotonic transformation). Now let y * denote the true value of Y . Then we can view the negative log-likelihood as a loss function

L ( y , y * ) = - log p X | Y ( X | y )

where the dependence on y * on the right hand side is embodied in the observation X on the left. An interesting special case of the MLE results when the conditional density P X | Y ( X | y ) is a Gaussian, in which case the negative log-likelihood corresponds to a squared errorloss function.

Now let us consider the expectation of this loss, with respect to the conditional distribution P X | Y ( X | y * ) :

- E [ log p X | Y ( X | y ) ] = log 1 p X | Y ( x | y ) p X | Y ( x | y * ) d x

The true value y * minimizes the expected negative log-likelihood (or, equivalently, maximizes the expected log-likelihood ). To seethis, compare the expected log-likelihood of y * with that of any other value y :

E [ log p X | Y ( X | y * ) - log p X | Y ( X | y ) ] = E log p X | Y ( X | y * ) p X | Y ( X | y ) = log p X | Y ( x | y * ) p X | Y ( x | y ) p X | Y ( x | y * ) d x = KL ( p X | Y ( x | y * ) , p X | Y ( x | y ) ) .

The quantity KL ( p X | Y ( x | y * ) , p X | Y ( x | y ) ) is called the Kullback-Leibler (KL) divergence between the conditional densityfunction p X | Y ( x | y * ) and p X | Y ( x | y ) . The KL divergence is non-negative, and zero if and only if the two densities are equal [link] . So, we see that the KL divergence acts as a sort of risk function in the context of Maximum Likelihood Estimation.

The cramer-rao lower bound

The MLE is based on finding the value for Y that maximizes the likelihood function. Intuitively, if the maximum point is verydistinct, say a well isolated peak in the likelihood function, then the easier it will be to distinguish the MLE from alternativedecisions. Consider the case in which Y is a scalar quantity. The “peakiness” of the log-likelihood function can be gauged byexamining its curvature, - 2 log p X | Y ( x | y ) y 2 , at the point of maximum likelihood. The higher the curvature, the more peaky is the behavior of the likelihood functionat the maximum point. Of course, we hope that the MLE will be a good predictor (decision) for the unknown true value y * . So, rather than looking at the curvature of the log-likelihood function at themaximum likelihood point, a more appropriate measure of how easily it will be to distinguish y * from the alternatives is the expected curvature of the log-likelihood function evaluated at the value y * . The expectation taken over all possible observations with respect tothe conditional density p X | Y ( x | y * ) . This quantity, denoted I ( y * ) = E [ - 2 log p X | Y ( x | y ) y 2 ] | y = y * , is called the Fisher Information (FI). In fact, the FI provides us with an important performance bound known asthe Cramer-Rao Lower Bound (CRLB).

Questions & Answers

what is demand and supply
Lansana Reply
what is liquidity
VICTOR Reply
the ability to easily turn asset or investment to cash
Johnson
liquidity is refers to the ease with which an asset or security, can be converted into ready cash without affecting it's market price. example is milk and checking a account in the bank.
Gyamfua
the meaning PPP is public _private partnership and PPP in economic is purchasing power_parity.
Gyamfua
what is economy production
Miracle Reply
what is Monopoly
Miracle
what is monopoly
Aina Reply
what is the full meaning of gpa?
Eedris Reply
why the firm will be happy to make normal profit?
Anold Reply
1.to make further increase 2.to established the firm 3. to draw and attract more customers 4. to foresee the future of the firm. 5. to get goods in galore
Castino
when marginal utility is zero? what is the total utility?
Scott Reply
definition of choice?
Anick Reply
it refers to the act of selecting one alternative from the other
Donfack
State and explain three advantages and two disadvantages of capitalist economic system
Ghislain Reply
What is cross elasticity of demand
Justice Reply
Is a demand in which the of goods change over time.
Shadrick
How can I join
Shadrick
join what?
Castino
it measure the extend in which the quantity demanded of a good respond to change in price of other good.
Donfack
refers to sensitivity of quantity demanded in change of price of commodity
Daniel
meaning of PPP
OBANYI
What is balance of payments
Bah Reply
what are free good
Maillot Reply
how do you determine price change
Matri Reply
what is economics?
Yaya Reply
what is economic
Nana Reply
Economics is the study of how Individual consumer, institution and society as a whole uses its available finite resources to satisfy infinite needs and wants
Richard
Explain the following concepts using suitable exemple. 1) National budget. 2) National debt
Rosalie
Got questions? Join the online conversation and get instant answers!
Jobilize.com Reply

Get the best Algebra and trigonometry course in your pocket!





Source:  OpenStax, Statistical learning theory. OpenStax CNX. Apr 10, 2009 Download for free at http://cnx.org/content/col10532/1.3
Google Play and the Google Play logo are trademarks of Google Inc.

Notification Switch

Would you like to follow the 'Statistical learning theory' conversation and receive update notifications?

Ask