Definition of Information Matrix: In maximum likelihood estimation, the information matrix is the variance of the score vector. The information matrix is a k x k matrix, where k is the dimension of the vector of parameters being estimated. The vector of parameters is denoted q here:

I(q) = var S(q) = E[(S(q)-ES(q))²] = E[S(q)²]

where the score is S(q) = dL(q)/d(q)

The information matrix can also be calculated by multiplying the Hessian of the log-likelihood function by (-1). (Econterms)

Terms related to Information Matrix:
None

About.Com Resources on Information Matrix:
None

Writing a Term Paper? Here are a few starting points for research on Information Matrix:

Books on Information Matrix:
None

Journal Articles on Information Matrix:
None

<Return to Main Page>