Abstracts - faqs.org

Abstracts

Mathematics

Search abstracts:
Abstracts » Mathematics

Likelihood ratio specification tests

Article Abstract:

The potential of using a likelihood rational specification test for acquiring more accurate inference in parametric models is examined. Parametric models are used in microeconomic research in tandem with post-fitting diagnostic tests to determine if there is misspecification. Misspecification tests examine data for failure of moment identities. The research considers a Bartlett correction, which differs from conventional moment tests in which adjustments grounded on second order asymptotic theory may falter.

Author: Smith, Richard J., Chesher, Andrew
Publisher: Blackwell Publishers Ltd.
Publication Name: Econometrica
Subject: Mathematics
ISSN: 0012-9682
Year: 1997
Models, Asymptotic expansions, Maximum likelihood estimates (Statistics), Parameter estimation, Maximum likelihood (Statistics)

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


A mirror image invariance for M-estimators

Article Abstract:

Monte Carlo experiments are widely used to evaluate the accuracy of asymptotic approximations in econometric estimators. Such experiments provide good information, but care must be taken to construct experiments in such a manner as to avoid giving an overly optimistic judgment over the performance of an estimator. A theorem regarding the choice of covariate distribution and which provides a mirror image invariance for M-estimators is presented.

Author: Chesher, Andrew
Publisher: Blackwell Publishers Ltd.
Publication Name: Econometrica
Subject: Mathematics
ISSN: 0012-9682
Year: 1995
Estimation theory, Monte Carlo method, Monte Carlo methods

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


Modelling nonlinear relationships between extended-memory variables

Article Abstract:

The existence of nonlinear relationships between extended memory variables cause modeling errors which are unseen in stationary or linear correlations. To address these problems, several definitions are derived. One, the I(1), is used to demonstrate the use of standard cointegration concepts and linearity tests. Likewise, techniques to develop nonlinear models are discussed for 'the I(1) and general case.

Author: Granger, C.W.J.
Publisher: Blackwell Publishers Ltd.
Publication Name: Econometrica
Subject: Mathematics
ISSN: 0012-9682
Year: 1995
Computer memory, Nonlinear theories, Memory (Computers)

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


Subjects list: Research, Usage, Econometrics
Similar abstracts:
  • Abstracts: Investigating the relationship between gold and silver prices. Economic and statistical measures of forecast accuracy
  • Abstracts: Intrinsic bubbles revisited: evidence from nonlinear cointegration and forecasting. Non-linear forecasts of stock returns
  • Abstracts: Two-person bargaining with verifiable information. Determinacy in linear rational expectations models. A proposal for sharing costs
  • Abstracts: A semiparametric method for predicting bankruptcy. Identifying the time-effect factors of multiple time series
  • Abstracts: Multivariate tests of mean-variance efficiency with possibly non-Gaussian errors: an exact simulation-based approach. part 2
This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.
Some parts © 2025 Advameg, Inc.