A Caltech Library Service

Parameterization and Two-Stage Conditional Maximum Likelihood Estimation

Lien, Da-Hsiang Donald and Vuong, Quang H. (1985) Parameterization and Two-Stage Conditional Maximum Likelihood Estimation. Social Science Working Paper, 578. California Institute of Technology , Pasadena, CA. (Unpublished)

[img] PDF (sswp 578 - Jul. 1985) - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


This paper considers the case where, after appropriate reparameterization, the probability density function can be factorized into a marginal density function and a conditional density function such that one of them involves fewer parameters. Then, two types of two-stage conditional maximum-likelihood estimators, 2SCMLEI and 2SCMLEII, can be considered according to whether the marginal or the conditional density has fewer parameters. Our first result indicates that, under some identification assumptions, there is a connection between the number of parameters in the marginal (or conditional) density functions under the two reparameterizations. Moreover, conditions for asymptotic equivalence and numerical equivalence between these two-stage estimators and the FIML estimator are obtained. Finally, examples are provided to illustrate our results.

Item Type:Report or Paper (Discussion Paper)
Additional Information:This research was partially supported by National Science Foundation Grant SES-8410 593. We are greatly indebted to D. Rivers and J. Sobel for helpful discussion, and to Shoo Bee Doo for moral support. Remaining errors are ours.
Group:Social Science Working Papers
Series Name:Social Science Working Paper
Issue or Number:578
Record Number:CaltechAUTHORS:20170915-134433552
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:81491
Deposited By: Jacquelyn Bussone
Deposited On:15 Sep 2017 20:59
Last Modified:03 Oct 2019 18:43

Repository Staff Only: item control page