Some Properties of Tests for Specification Error in a Linear Regression Model

Thursby, Jerry G.; Schmidt, P. Henry

doi:10.2307/2286231

Cited by 109 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another possibility is to use the FM-OLS residuals of the original equation (2) and to perform a Lagrange Multiplier RESET type test in an auxiliary regression. Note here that the original RESET test of Ramsey (1969) as well as similar tests by Keenan (1985) and Tsay (1986) use powers of the fitted values, whereas Thursby and Schmidt (1977) use polynomials of the regressors and it is this approach that we also follow since this leads to simpler test statistics.…”

Section: Specification Testing Based On Augmented and Auxiliary Regrementioning

confidence: 99%

Cointegrating Polynomial Regressions: Fully Modified Ols Estimation and Inference

2015

View full text Add to dashboard Cite

This paper develops a fully modified OLS estimator for cointegrating polynomial regressions, i.e. for regressions including deterministic variables, integrated processes and powers of integrated processes as explanatory variables and stationary errors. The errors are allowed to be serially correlated and the regressors are allowed to be endogenous. The paper thus extends the fully modified approach developed in Phillips and Hansen (1990). The FM-OLS estimator has a zero mean Gaussian mixture limiting distribution, which is the basis for standard asymptotic inference. In addition Wald and LM tests for specification as well as a KPSS-type test for cointegration are derived. The theoretical analysis is complemented by a simulation study which shows that the developed FM-OLS estimator and tests based upon it perform well in the sense that the performance advantages over OLS are by and large similar to the performance advantages of FM-OLS over OLS in cointegrating regressions.

show abstract

Section: Specification Testing Based On Augmented and Auxiliary Regrementioning

confidence: 99%

Cointegrating Polynomial Regressions: Fully Modified Ols Estimation and Inference

2015

View full text Add to dashboard Cite

show abstract

“…' The t th period regressors X, in the non-augmented regression are defined to be (1, x,). And, following Thursby and Schmidt (1977) the additional variables in the augmented regression are the squared. cubed, and fourth powers of x,.…”

Section: Datamentioning

confidence: 99%

Autocorrelation and the sensitivity of reset

Porter

Kashyap

1984

Economics Letters

View full text Add to dashboard Cite

“…There must therefore be serious doubts (that require further study) about the power of RESET to detect any 'better' non-linear expression lurking in all those least squares residuals. Such doubts motivated Thursby and Schmidt (1977) to favour the more conventional method of adding powers of individual variables, each with their own unconstrained coefficients.…”

Section: 'Use Of the Regression Specification Error Test As A Criterimentioning

confidence: 99%

The Abuse of Regression in the National Health Service Allocation Formulae: Response to the Department of Health’s 2007 ‘Resource Allocation Research Paper’

Galbraith

Stone

2011

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

Summary. Weighted capitation formulae for the allocation of funds to England's regional health authorities go back decades. In 2006, a paper in the Journal of the Royal Statistical Society, Series A, criticized the formula that has been used, with little change, from 2003 to 2009. The Department of Health has responded tangentially in a report from a team of academics whose remit was to revise the formula for its continued use beyond 2009. The Series A critique is here renewed and strengthened by analysis of the role of some elementary statistical tools in the construction of the latest formula. The conclusion is that, if the force of the extended critique is accepted, other approaches will have to be considered.

show abstract

Some Properties of Tests for Specification Error in a Linear Regression Model

Cited by 109 publications

References 0 publications

Cointegrating Polynomial Regressions: Fully Modified Ols Estimation and Inference

Cointegrating Polynomial Regressions: Fully Modified Ols Estimation and Inference

Autocorrelation and the sensitivity of reset

The Abuse of Regression in the National Health Service Allocation Formulae: Response to the Department of Health’s 2007 ‘Resource Allocation Research Paper’

Contact Info

Product

Resources

About