Robustness to the unavailability of data in block designs

We present general results for finding or boundingt _maxB , the maximum number of arbitrary whole blocks of observations which can be removed from a block design, and still leave all of the elementary treatment contrasts estimable. The block sizes may be larger than the number of treatments. The results are applied to BBDs, reinforced BIBDs and BBDs, BTIBDs, and a series of variance balanced incomplete block designs with two block sizes. Also given for most of these designs, are results fort _max, the maximum number of arbitrary, scattered observations that can become unavailable, and still leave all of the elementary treatment contrasts estimable.The work was undertaken while Dr. Whittinghill was visiting Ohio State University, and supported by a grant from the Natural Sciences Division, Colby College, Waterville, Maine.     

Testing equality of variances in the analysis of repeated measurements

The problem of comparing the precisions of two instruments using repeated measurements can be cast as an extension of the Pitman-Morgan problem of testing equality of variances of a bivariate normal distribution. Hawkins (1981) decomposes the hypothesis of equal variances in this model into two subhypotheses for which simple tests exist. For the overall hypothesis he proposes to combine the tests of the subhypotheses using Fisher's method and empirically compares the component tests and their combination with the likelihood ratio test. In this paper an attempt is made to resolve some discrepancies and puzzling conclusions in Hawkins's study and to propose simple modifications.
The new tests are compared to the tests discussed by Hawkins and to each other both in terms of the finite sample power (estimated by Monte Carlo simulation) and theoretically in terms of asymptotic relative efficiencies.     

Monotonizing empirical Bayes estimators for a class of of discrete distributions with monotone likelihood ratio

A procedure is given for the construction of a monotone estimator that dominates a given estimator for a class of discrete distributions with monotone likelihood ratio. This procedure is applied to some empirical Bayes estimators. Monte Carlo results are given that demonstrate the usefulness of monotonizing.     

Aggregation effects on price and expenditure elasticities in a quadratic almost ideal demand system

Abstract.  While it is well known that demand elasticities calculated at the macro level will in general differ from those calculated at the micro level because of aggregation effects, there remain the questions of how large the effects are and how they vary with the degree of inequality in the income distribution. We explore these questions with models based on a quadratic version of the Almost Ideal Demand System. We investigate the elasticity differences theoretically and then calibrate the models and generate numerical results, using income data for seven countries with widely different distributions. The aggregation effects are found generally to be rather small, even with highly unequal income distributions.     

Forecasting first births

This study is concerned with one aspect of the family cycle, namely, the transition from young married to young married with small children. The focus is on developing models to forecast entries into this latter stage for the purpose of marketing research. "Using ordinary least squares, forecasting models were estimated for (1) total number of first births, (2) number of white first births, and (3) number of nonwhite first births." Models are estimated for both the United States and California using data from official sources.     

Forecasting and random processes

On the simple model of a (univariate) random process some general problems of “random logic” are discussed. New random approaches to explorative, normative and systematic (normex) forecasting are developed, and some applications are suggested.     

Institutionalism versus Orthodoxy

A bstract . Orthodox economics has been quite effective in exploiting equilibrium methodology; equilibrium as a heuristic device, as a theoretical norm, and as a prototype of the scientific method. Also, orthodoxy has contrived the dichotomy of equilibrium-anti-equilibrium to depict institutional thought as being muddled and unscientific. Institutionalists have not successfully countered these attacks, nor have they adequately articulated a comprehensive methodological alternative to orthodoxy. Institutionalists have paid too much attention to the methodological components of institutionalism and have neglected the articulation of a guiding, overall methodology. It is proposed that institutionalists recast the methodological debate by expanding the arena from equilibrium-anti-equilibrium analysis to the broader context of closed versus open systems analysis. This would both help expose the methodological weaknesses of orthodox economics, and demonstrate the relevance and power of institutionalism for socioeconomic investigation.     

Consumer mobility and community tax bases : The financing of local public goods

In a model of economic ‘clubs’, size is fixed and members consuming a public good raise the question of composition; with whom would they rather consume? This depends on the way collective consumption is financed, and three results are proven With a poll tax, clubs must be homogeneous in income for all to be satisfied With a marginal benefit (Lindahl) tax, no consumer is ever satisfied with any composition; and with an income tax, at least one consumer in each club is always dissatisfied. Satisfaction implies there exists no club composition preferred to the existing one.     

A comparison of alternative methods of updating input-output coefficients

In recent years there has been a growing number of input-output models of economies ranging in scale from the rural to the national. While offering invaluable insights into the interaction of sectors within an economy, the input-output model suffers from the fact that its coefficient values are altered over time due particularly to technological change. Two of the prominent techniques designed to update these technical coefficients, the RAS and linear programming methods, are compared herein with regard to changes in U.S. national coefficients between 1963 and 1967. Suggestions for improvements to the latter method are outlined.