Simulation for the complex Bingham distribution

The complex Bingham distribution is relevant for the shape analysis of landmark data in two dimensions. In this paper it is shown that the problem of simulating from this distribution reduces to simulation from a truncated multivariate exponential distribution. Several simulation methods are described and their efficiencies are compared.     

A continuous sampling plan using CUSUMs

A Continuous Sampling Plan, CSP-CUSUM, is proposed based on the use of Cumulative Sums (CUSUMs) for deciding when to switch between the phases of sampling inspection and 100% inspection. The Geometric CUSUM, also termed the Run-length CUSUM, is chosen for this purpose, and two separate CUSUMs are to be operated, one for each inspection phase. The conventional measures of performance for CSPs such as average outgoing quality, average fraction inspected, and average proportion passed under sampling inspection are evaluated for CSP-CUSUM, and comparisons with some standard CSPs are presented. An additional performance-measure, Average Cycle Length, is proposed. A table is provided to aid the choice of parameters for the operation of CSP-CUSUM. It is recommended that a Geometric CUSUM control chart be maintained in parallel with CSP-CUSUM to detect significant upward shifts in the incoming fraction defective.     

Structural and Behavioural Changes in the Short TermPreventive Check in the Northwest Balkans in the 18th and19th Centuries

Fertility responded negatively to grain insufficiency(proxied by grain price increases), and mortality respondedpositively in Croatia-Slavonia-Srem in the 18thand 19th centuries, as in most of Europe. Shiftsin the intensity and timing of these responsesoccurred over time as social and economic structureschanged. Shifts in the elasticity of fertility withrespect to grain supply inversely mimic and lagchanges in the elasticity of mortality. Both appear tobe induced by increasing land shortage, the collapseof feudalism, and differences in the patterns ofadjustment to post-feudal conditions among former civiland military serfs. Generally, responses are strongerfor civil and former civil serfs, who may have been inless favourable economic circumstances than themilitary. Fertility responses in the year of a priceshock come to dominate those in the year following,suggesting a shift from contraception to abortion aseconomic and social conditions apparently worsened andstrategies of control intensified. Analysis of monthlyresponses supports the conjecture based on the annualresponses. The shift to the preventive check and strength of thepreventive check in the same year as the price shockis unusual in Europe and beyond. Analysis is based on25 parishes and employs lagged annual and monthly timeseries analysis with corrections for autocorrelation,in combination with ethnographic and historical data.     

Urban versus Rural: Fertility Decline in the Cities and Rural Districts of Prussia, 1875 to 1910

Marital fertility in 54 Prussian cities and 407 Prussian Kreise (administrative areas) is analyzed using unusually rich and detailed socioeconomic and demographic data from eight quinquennial census between 1875 and 1910. Pooled cross-section time series methods are used to examine influences on marital fertility level and on marital fertility decline, focusing particularly on fertility differences according to level of urbanization. Increases in female labour force participation rate and income, the growth of financial services and communications, improvement in education, and reduction in infant mortality account for most of the marital fertility decline in 19th century Prussia. In 1875, rural and urban fertility were similar but by 1910, urban fertility was far lower than rural in part because the values of some of these variables changed more rapidly in the cities, and in part because some of these variables had stronger effects in urban settings.     

Statistical approaches for conducting network meta-analysis in drug development

We introduce health technology assessment and evidence synthesis briefly, and then concentrate on the statistical approaches used for conducting network meta-analysis (NMA) in the development and approval of new health technologies. NMA is an extension of standard meta-analysis where indirect as well as direct information is combined and can be seen as similar to the analysis of incomplete-block designs. We illustrate it with an example involving three treatments, using fixed-effects and random-effects models, and using frequentist and Bayesian approaches. As most statisticians in the pharmaceutical industry are familiar with SAS? software for analyzing clinical trials, we provide example code for each of the methods we illustrate. One issue that has been overlooked in the literature is the choice of constraints applied to random effects, and we show how this affects the estimates and standard errors and propose a symmetric set of constraints that is equivalent to most current practice. Finally, we discuss the role of statisticians in planning and carrying out NMAs and the strategy for dealing with important issues such as heterogeneity.     

MODEL-ASSISTED HIGHER-ORDER CALIBRATION OF ESTIMATORS OF VARIANCE

In survey sampling, interest often centres on inference for the population total using information about an auxiliary variable. The variance of the estimator used plays a key role in such inference. This study develops a new set of higher‐order constraints for the calibration of estimators of variance for various estimators of the population total. The proposed strategy requires an appropriate model for describing the relationship between the response and auxiliary variable, and the variance of the auxiliary variable. It is therefore referred to as a model‐assisted approach. Several new estimators of variance, including the higher‐order calibration estimators of the variance of the ratio and regression estimators suggested by Singh, Horn & Yu and Sitter & Wu are special cases of the proposed technique. The paper presents and discusses the results of an empirical study to compare the performance of the proposed estimators and existing counterparts.     

The RL2 chart versus the np chart for detecting upward shifts in fraction defective

The use of the np chart for monitoring fraction-defective is well-established, but there are a number of relatively simple alternatives based on run-lengths of conforming items. Here, the RL₂ chart, based on the moving sum of two successive conforming run-lengths, is investigated in order to provide SPC practitioners with clear-cut guidance on the comparative performance of these competing charts. Both sampling inspection and 100% inspection are considered here, and it is shown that the RL₂ chart can often be considerably more efficient than the np chart, but the comparative performance depends on the false-alarm rate used for the comparison. Graphs to aid parameter-choice for the RL₂ chart are also provided.     

The De/Repoliticization of Cooperation and the Discourse of Conversion1

Abstract In recent years, several agricultural cooperatives have undergone significant restructuring. Some have been taken through a conversion process and have been reorganized as “investor-oriented firms” (IOFs). This phenomenon has attracted the interest of agricultural economists, but it has not been analyzed by sociologists. This article examines the discourse with which agricultural economists have approached the conversion issue. Drawing upon Fraser's discussion of “needs talk,” and inspired by Kloppenburg's analysis of the agricultural scientific complex, an argument is made that a reprivatization discourse of neoclassical economics has effectively depoliticized discussion about the future of cooperative enterprise. It is further argued that a repoliticization of cooperation is necessary in order to assure the protection of extra-economic values and oppositional discourse that is embedded in the historical development of cooperative practices and institutions. We focus here on the role of expert discourse as it relates to the reinvention of cooperative institutions in the agricultural economy. It is argued that this discourse would be improved by greater attention to historical and sociological forces, rather than remaining narrowly focused on economism.     

What is to be done about unemployment?

The rate of unemployment in Britain has been rising, and will doubtless continue to rise for the foreseeable future. On present trends any significant fall in the rate of unemployment appears improbable. We face the prospect of unemployment in the 1980s as severe as that experienced in the 1930s when only at its worst did the rate rise to the equivalent of nearly four million in today's terms. Against this background it is natural to despair of solutions. Certainly we cannot provide a policy which will produce an immediate return to ‘full employment’. but there are opportunities available for appreciably improving employment prospects. Particular policies are discussed and recommended in this paper, and the initiative has to be taken now.     

Lorenz non-consistent welfare and inequality measurement

Typical welfare and inequality measures are required to be Lorenz consistent which guarantees that inequality decreases and welfare increases as a result of a progressive transfer. We explore the implications for welfare and inequality measurement of substituting the weaker absolute differentials and deprivation quasi-orderings for the Lorenz quasi-ordering. Restricting attention to distributions of equal means, we show that the utilitarian model – the so-called expected utility model in the theory of risk – does not permit one to make a distinction between the views embedded in the differentials, deprivation and Lorenz quasi-orderings. In contrast it is possible within the dual model of M. Yaari (Econometrica 55 (1987), 99–115) to derive the restrictions to be placed on the weighting function which guarantee that the corresponding welfare orderings are consistent with the differentials and deprivation quasi-orderings respectively. Finally we drop the equal mean condition and indicate the implications of our approach for the absolute ethical inequality indices.