Hierarchical Bayesian estimation

From DDL Wiki

Revision as of 13:59, 12 December 2007 (view source) Sina (Talk | contribs) ← Older edit		Revision as of 14:53, 12 December 2007 (view source) Sina (Talk | contribs) Newer edit →
Line 1:		Line 1:
-	Mike sys write this only!	+	Hierarchical bayesian is an estimation procedure used to estimate coefficients (βs) of behavioral models like mixed logit. Therefore, hierarchical bayesian is ''not'' a new behavioral model beside logit and probit, but only an alternative to for example maximum likelihood method.
-	the ''&beta;''<sup>2</sup>s are very important	+	HB (Hierarchical Bayesian) method has root in the Bayesian probability [http://en.wikipedia.org/wiki/Bayesian_probability]. However, according to Bermstein-Von Mises Theorem it can be interpreted completely in the classical probability perspective [http://en.wikipedia.org/wiki/Classical_definition_of_probability].
-		+
-	<math> \beta^2 = \eta_{ni} </math>	+

---

Revision as of 14:53, 12 December 2007

Hierarchical bayesian is an estimation procedure used to estimate coefficients (βs) of behavioral models like mixed logit. Therefore, hierarchical bayesian is not a new behavioral model beside logit and probit, but only an alternative to for example maximum likelihood method.

HB (Hierarchical Bayesian) method has root in the Bayesian probability [1]. However, according to Bermstein-Von Mises Theorem it can be interpreted completely in the classical probability perspective [2].