Generalized maximum entropy estimation of linear models
Paul Corral
The World Bank
Washington, DC
[email protected]
|
Daniel Kuehn
Urban Institute
Washington, DC
[email protected]
|
Ermengarde Jabir
American University
Washington, DC
|
Abstract. In this article, we describe the user-written gmentropylinear command,
which implements the generalized maximum entropy estimation method for linear
models. This is an information-theoretic procedure preferable to its maximum
likelihood counterparts in many applications; it avoids making distributional
assumptions, works well when the sample is small or covariates are highly
correlated, and is more efficient than its maximum likelihood equivalent. We
give a brief introduction to the generalized maximum entropy procedure, present
the gmentropylinear command, and give an example using the command.
View all articles by these authors:
Paul Corral, Daniel Kuehn, Ermengarde Jabir
View all articles with these keywords:
gmentropylinear, generalized maximum entropy, maximum entropy, linear
Download citation: BibTeX RIS
Download citation and abstract: BibTeX RIS
|
