Leverage and evaluation effectiveness

Weaknesses in evaluations often can be traced to structural limitations in the positions of evaluation researchers. Conventional human relations techniques often are an insufficient basis for securing strong support for evaluation research. Strategies for increasing evaluation research leverage are reviewed. Alignment of evaluation research with regulatory bodies with authority to suspend public program expenditures is advocated. Several likely obstacles in the development of the regulatory evaluation model are anticipated and addressed.     

Das Stabilitätsproblem in der Ökonometrie

Statistical Papers - Ein allgemeines ökonometrisches Modell M wird eingeführt. Für dieses werden die Begriffe Relevanzzeitraum und Relevanzregion definiert. Der Begriff des...     

TESTING THE EQUALITY OF PARAMETERS IN THE DISTRIBUTIONS WHEN THE RANGE DEPENDS UPON THE PARAMETER

The authors derive the null and non-null distributions of the test statistic v=y_min/y_max (where y_min= min x_ij, y_max= max x_ij, J=1,2, …, k) connected with testing the equality of scale parameters θ₁, θ₂, …θ_k in certain, class of density functions given by      

THE THEORY OF UNIVARIATE SAMPLING ON SUCCESSIVE OCCASIONS UNDER THE GENERAL CORRELATION PATTERN1,2

The present paper is concerned with the various results developed for the theory of successive sampling. The different correlation patterns and the different sampling procedures assumed in the theory are described and further an attempt has been made to derive results for the general correlation pattern. Accordingly, an expression for the best (minimum variance linear unbiased) estimator is presented for the general correlation pattern where the sampling procedure adopted is a restricted one. When the special correlation pattern assumed in the derivation of results breaks down on a particular occasion, its effect on the estimator employed for that occasion is examined. Furthermore, an expression for the variance of the estimator, which is best under a special correlation pattern, is derived when that correlation pattern does not hold good. The expression so obtained is comparable with that furnished by Patterson (1950).     

Other Voices

This column is devoted to informing VGQ readers of important articles in other journals. All articles are published by the American Personnel and Guidance Association unless otherwise noted. Single copies of back issues may be ordered from APGA Publication Sales, Two Skyline Place, Suite 400, 5203 Leesburg Pike, Falls Church, Va. 22041