Conditional inference for subject-specific and marginal agreement: Two families of agreement measures

A two-stage procedure is described for assessing subject-specific and marginal agreement for data from a test-retest reliability study of a binary classification procedure. Subject-specific agreement is parametrized through the log odds ratio, while marginal agreement is reflected by the log ratio of the off-diagonal Poisson means. A family of agreement measures in the interval [-1, 1] is presented for both types of agreement. The conditioning argument described facilitates exact inference. The proposed methodology is demonstrated by way of an example involving hypothetical data chosen for illustrative purposes, and data from a National Health Survey Study (Rogot and Goldberg 1966).     

On nonparametric profile analysis of several multivariate samples

A unified development is offered for asymptotically distribution-free profile analysis of several multivariate samples. This includes as special cases procedures based on generalized U-statistics and also those based on linear rank statistics. Furthermore, it includes as special cases analysis of location profiles and also scalar profiles. Finally, asymptotic power and consistency properties are discussed for tests of hypotheses and subhypotheses of interest.     

A note on the asymptotic optimality of a two population sequential probability ratio test

It is shown that a two population sequential probability ratio test studied by a number of recent authors in the context of sequential medical trials is asymptotically optimal.     

Local response to planning mandates. The prevalence and utilization of needs assessment by human service agencies.

Federal and state needs assessment mandates have traditionally been criticized both by their originators and by the local human service agencies that are required to conduct these studies as part of the planning process. This paper presents some preliminary evidence that local opposition to assessment may be shrinking as agencies gain a new appreciation for the varied uses of assessment information. Using data from a sample of Wisconsin agencies the prevalence of assessments between 1979 and 1980 is described and the conditions surrounding the practice of needs assessment are outlined. Particular attention is given to factors that affect the utilization of needs assessment results, including the characteristics of the sponsoring agency, the attributes of the study, and the structure of the assessment process.     

Meta-analysis of the impact of age structure on fertility

The paper uses a meta-analysis to comparatively evaluate the literature addressing the aggregate relationship between a populations age structure and fertility, as hypothesized by Richard Easterlin. The analysis is based on 334 estimated effects retrieved from 19 studies. The results suggest that several factors undermine the empirical support of the Easterlinian age structure/fertility link. These include the neglect of income, the use of relative cohort size to characterize the age structure, mis-specifications of the relevant age-cohorts, as well as the functional form and estimation technique. The results also suggest that the sample of published estimates possibly suffers from two types of publication bias, an under-representation of insignificant effects for small samples, and bias towards supportive effects in the earlier years followed by a bias towards negative effects as the literature matured.All correspondence to: Brigitte Waldorf. The authors appreciate the insightful comments and suggestions from two anonymous reviewers. The research also benefited from discussions with participants of the International Colloquium on Meta-analysis in Economics, Free University, Amsterdam, The Netherlands, December 2002. Finally, we would like to thank David Brown, Meagan Cahill, Angela Donelson, Calvin Farris, and Melaney Seacat from the University of Arizona for their research assistance. Responsible editor: Junsen Zhang.     

On regressing regression coefficients

This paper considers a regression model in which coefficients obtained from a previous regression are themselves the object of analysis. It is shown that the parameters of interest can be obtained in two ways: pooling across observations and subsamples, or a two-stage process of first estimating the coefficients within each subsample, and then using these coefficients as dependent variables in a second stage regression. The relative properties of these estimators are analyzed, and the conditions under which the two estimators are equivalent are derived.     

A formula for P(bi≤Ri≤ai, 1≤i≤m) under a general class of alternatives

Let X_i≤?≤X_m and Y_i≤?≤Y_n be two sets of independent order statistics from continous distributions with distribution functions F and G respectively. Let R_i denote the rank of X_i in the combined order sample. Steck (1980) has found an expression for P(b_i≤R_i≤a_i, all i) when F = h(G), h being the incomplete beta function with parameters (α,β?α+1). An alternative expression for the same probability is obtained which is computationally a substantial improvement on Steck's result.     

Information in experiments and sufficiency

We define measures of information contained in an experiment which are by-products of the parametric measures of Fisher, Vajda, Mathai and Boekee and the non-parametric measures of Bhattacharyya, Rényi, Matusita, Kagan and Csiszár. We use these measures to compare sufficient experiments according to Blackwell's definition. In particular, we prove that if δ_X and δ_Y are two experiments and δ_X≥δ_Y then l_X≥l_y for all of the above measures.     

Can the Augmented Solow Model with Migration Explain the Italian Internal Brain Drain?

We extend the Dolado et al. (1994) model to both inflows and outflows of migrants and assume that they have a human capital endowment that contributes to increase/decrease the stock of human capital in the receiving/sending economy. We derive the conditional convergence equation in which the impact of migration flows on the growth rate is disentangled in a pure quantity effect and in a quality or composition effect of immigration and emigration rates that accounts for the relative human capital endowment of migrants with respect to resident population. Next, we test the model with Italian regional data for the 1970–2005 time period. We find that the model provides a good explanation of the Italian experience. The quantity effect is negative for the immigration rate and positive for the emigration rate, whereas the composition effect is positive for immigration and negative for emigration. Finally, we separate the centre‐north from the south and find that the composition effect of emigration is stronger for the latter. We interpret these results as a clear evidence of a brain drain from the Mezzogiorno to the centre‐northern regions.     

Temporary Contracts,Employment Protection,and Collective Bargaining

This paper examines the effect of employment protection in a matching model with endogenous job destruction, collective bargaining, and two types of employment contracts. Using this framework, we show that (i) the impact on job creation and job destruction caused by reducing the firing costs associated with temporary jobs depends on the labour unions' bargaining strength and the gap in firing costs between contracts; (ii) reducing the firing costs associated with permanent jobs unambiguously decreases equilibrium unemployment if labour unions have strong bargaining power; and (iii) the impact caused by the firing costs differs between collective and individual bargaining.