Joint one-sided tests of linear regression coefficients

DOI10.1016/0304-4076(86)90020-5MaRDI QIDQ1089716zbMATH OpenOpenAlexFDO

Authors Maxwell L. King, Murray D. Smith

Publication date 1986

Published in Journal of Econometrics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0304-4076(86)90020-5

zbMATH Keywords

Empirical power comparisonsexact one-sided likelihood ratio testF-testnew testone-sided t-testpower envelopeUMPI

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Linear regression; mixed models (62J05) Applications of statistics to economics (62P20)

Review text

The main example of the class of problems considered below is that of testing whether a subset of regression coefficients are jointly zero assuming knowledge of the coefficients' signs. If this knowledge is ignored, the likelihood ratio, Wald, and Lagrange multiplier tests are each equivalent to the F-test. We propose a new test which can be applied as a one-sided t-test and which is UMPI in a subspace of the parameter space. Empirical power comparisons with the power envelope, the F-test, and the exact one-sided likelihood ratio test show that the new test can have exceptionally good power over a wide range of the parameter space.

Recommendations

• Joint tests for zero restrictions on nonnegative regression coefficients
• Locally optimal one-sided tests for multiparameter hypotheses
• Testing joint hypotheses when one of the alternatives is one-sided
• scientific article; zbMATH DE number 964727
• Testing Whether One Regression Function is Larger Than Another

Cites work

• A joint test for serial correlation and heteroscedasticity
• A new test for fourth-order autoregressive disturbances
• A Note on Representations of the Doubly Non-Central t Distribution
• A point optimal test for autoregressive disturbances
• Joint tests for zero restrictions on nonnegative regression coefficients
• Likelihood Ratio Test, Wald Test, and Kuhn-Tucker Test in Linear Models with Inequality Constraints on the Regression Parameters
• On choosing the optimal level of significance for the Durbin-Watson test and the Bayesian alternative
• Series Representations of the Doubly Noncentral t-Distribution
• Tables of the Power of the F-Test
• Testing for autoregressive against moving average errors in the linear regression model
• TESTING FOR MOVING AVERAGE REGRESSION DISTURBANCES

Cited in

(9)

• Hypothesis testing with a restricted parameter space
• One-sided tests for independence of seemingly unrelated regression equations
• Halfline tests for multivariate one-sided alternatives
• Joint LM test for homoskedasticity in a one-way error component model
• On the Test of Significance of Linear Multiple Regression Coefficients
• Joint tests for zero restrictions on nonnegative regression coefficients
• Locally optimal one-sided tests for multiparameter hypotheses
• Testing joint hypotheses when one of the alternatives is one-sided
• A simple test for comparing regression curves versus one-sided alternatives

This page was built for publication: Joint one-sided tests of linear regression coefficients

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1089716)