Abstracts - faqs.org

Abstracts

Mathematics

Search abstracts:
Abstracts » Mathematics

Estimation and testing of time-varying coefficient regression models in the presence of linear restrictions

Article Abstract:

An extension of the linear regression model with random walk coefficients with linear restrictions between coefficients is evaluated. Results indicate that while the estimation is straightforward, testing for restrictions reveal a nonstandard problem. However, a minor adjustment to the problem eliminated this and test results show significant importance. Significant coefficient variation in price is encountered, although the homogeneity restriction is met satisfactorily.

Author: Leybourne, S.J.
Publisher: John Wiley & Sons, Inc.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1993
Testing, Linear models (Statistics)

User Contributions:

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

CAPTCHA


Forecast combination in a dynamic setting

Article Abstract:

Generalization of forecast combination procedures using the dynamics in the combining regression is pursued. Results indicate that accounting for the dynamics source of forecast cobination regressions improves forecasts with the use of proper restrictions. Moreover, while the variable and its forecasts may be dynamic, cointegration must be considered in combining regressions. Imposing restrictions on combining regression would further improve forecast accuracy.

Author: Coulson, N. Edward, Robins, Russel P.
Publisher: John Wiley & Sons, Inc.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1993
Autoregression (Statistics)

User Contributions:

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

CAPTCHA


Analysis of many short time sequences: forecast improvements achieved by shrinkage

Article Abstract:

An extension of the credibility model in actuarial science for multiple short time series predictions using the shrinkage approach to the mean is evaluated. Results appear to easily generalized for different structural time series models. The accuracy of the model's forecast are compared to those of traditional models. The latter has been found to perform poorly in most cases.

Author: Ledolter, Johannes, Lee, Chang-Soo
Publisher: John Wiley & Sons, Inc.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1993
Insurance agents, brokers, & service, Insurance claims adjustment, Claims adjustment (Insurance)

User Contributions:

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

CAPTCHA


Subjects list: Models, Forecasting, Analysis
Similar abstracts:
  • Abstracts: Estimating deterministic trends in the presence of serially correlated errors. Money, prices, interest rates and the business cycle
  • Abstracts: Estimation of exact linear time-varying constraints, with an application to population projections. Constraining Kalman filter and smoothing estimates to satisfy time-varying restrictions
  • Abstracts: Variance estimation for multivariate dynamic linear models. Bias in the estimation of non-linear transformation of the integrated variance of returns
  • Abstracts: Classification Cramer-Rao bounds on stock price prediction. Judgemental revision of sales forecasts: the relative performance of judgemntally revised versus non-revised forecasts
  • Abstracts: Long-sighted principal and myopic agents. A second welfare theorem for constrained efficient allocations in incomplete markets
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.