Finite sample behavior of tests for grouped heteroskedasticity
Article Abstract:
Grouped heteroskedasticity exists when error variances vary across data subsets but remain constant within subsets. Various tests for grouped heteroskedasticity, based on an asymptotic Chi-squared variable, are evaluated using Monte Carlo methods. The results suggest that Bartlett's procedure, despite being the simplest, may be the most efficient test. Should its reliability come into question, its result may be verified using a more powerful method such as the Breusch-Pagan test.
Publication Name: Review of Economics and Statistics
Subject: Mathematics
ISSN: 0034-6535
Year: 1992
User Contributions:
Comment about this article or add new information about this topic:
Finding cointegration rank in high dimensional systems using the Johansen test: an illustration using data based Monte Carlo simulations
Article Abstract:
Data based Monte Carlo simulation methods are used to evaluate the performance of the Johansen (1991) likelihood ratio test for cointegrating vector quantity in small samples. Asymptotic critical values are used to evaluate the validity of inference. Results show that researchers should be cautious when using the Johansen estimator, since it exhibits excessive cointegration when the lag order is misspecified.
Publication Name: Review of Economics and Statistics
Subject: Mathematics
ISSN: 0034-6535
Year: 1996
User Contributions:
Comment about this article or add new information about this topic:
Finite-sample properties of percentile and percentile-t bootstrap confidence intervals for impulse responses
Article Abstract:
A multivariate forecast evaluation method is proposed for the detection and correction of defects found in percentile-t intervals.
Publication Name: Review of Economics and Statistics
Subject: Mathematics
ISSN: 0034-6535
Year: 1999
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: Finite-sample properties of tests for equal forecast accuracy. Can out-of-sample forecast comparisons help prevent overfitting?
- Abstracts: Finite sample prediction and interpolation for ARMA models with missing data. Dynamic Harmonic Regression
- Abstracts: The growing importance of cognitive skills in wage determination. Does the baseball labor market contradict the human capital model of investment?
- Abstracts: On the estimation of demand systems through consumption efficiency. Intertemporal substitution in macroeconomics: consumption, labor supply, and money demand
- Abstracts: How robust is the capital-skill complementarity hypothesis? Sources of the financing hierarchy for business investment