Estimation of the mean in ranked set sampling with non responses

The estimation of the population mean when ranked set sampling [rss] is used for selecting the sample and non responses [nr] are present, is studied. The nr stratum is sub sampled using simple random sampling with replacement. Two strategies are analyzed. One of them is based on the selection of a sub sample from the nr in each cycle. The other uses sub samples selected among the nr in each rank.  The accuracy of the proposed estimators is characterized by the corresponding expected variances. Simulations and real life data are used for analyzing the behavior of them. Acknowledgements: This paper was developed partially during the visit of the author to Université des Antilles et Gouyane. The author gratefully acknowledges the helpful suggestions of the referees and thanks the support of DAAD for visiting Humboldt University where a version of the paper version was made.     

Efficient Liability Rules: Complete Characterization

Received May, 18, 2000; revised version received March, 19, 2001     

A Conceptual Model of the Household's Housing Decision–Making Process: The Economic Perspective

At some stage in every household's family life cycle, the household is likely to make certain decisions with regard to its housing environment. Although the household's housing decisions essentially comprise the decision to move, and the selection of a new residence, the process from which these decisions are derived is very complex because varying circumstances could produce a multitude of different housing decisions. Due to the sheer complexity of the household's housing decision–making process, researchers have generally focused on individual decision–making stages rather than on the process as a whole. This paper therefore attempts to conceptualize the entire household housing decision–making process using theoretical concepts from the economic perspective, and then tests the conceptual model with empirical evidence drawn from the moving population within the multi–racial society in Singapore.     

PROCYCLICAL RETAIL LABOUR PRODUCTIVITY*

The influence of lagged adjustment and consumer spending on retail labour productivity is investigated. Both influences result in a procyclical productivity pattern.     

Varietal Licensing Standards and Canadian Wheat Exports

Canada's wheat grading system is largely based on visual criteria and it is based on relatively high quality standards. A strict varieties licensing system exists to maintain the integrity of the grade standards. One of the consequences of the licensing system is that higher yielding, lower or different quality wheats have not been grown in Canada until recently. The basic objective of this paper is to examine some of the consequences of the regulatory strategy of limiting wheat production to the traditional high quality wheats. This question is analyzed in the context of important changes in the international grain markets. Using a partial equilibrium trade model this paper estimates that if higher yielding wheats were permitted to be grown, annual producer gains would be 5 to 17 percent of current net farm income.
Le classement des blés au Canada est basé sur des critères visuels qui sont de hautes qualités. Le système actuel d'homologation des variétés est tel que l'intégrité de ce système est maintenue. En conséquent, ce système n'a pas encouragé la cultivation des blés de hauts rendements ou des varietés différentes que tout récemment. L'objectif principal de cette étude est d'examiner quelques unes des conséquences de la stratégic de la réglementation visant à limiter la production du blé aux variétés de hautes qualités. Cette question est adressée dans le contexte des changements importants qui ont eu lieu dans le marché international des grains. A l'aide d'un modèle d'équilibre partiel des échanges, la présente étude démontre gu'en permettant la production des blés de hauts rendements, le gain annuel aux producteurs serait de 5 à 17 pourcent du revenue agricole net.     

On the generalization of Rao,Hartley and Cochran's scheme

Summary The problem considered in this paper is a generalization of the usual Rao, Hartley and Cochran (RHC) scheme. In the usual RHC scheme the population ofN units is randomly divided inton groups wheren is the size of the sample. In this paper we propose to divide the population under consideration into (n+k) random groups wherek is some positive integer. Then a sample ofn groups is selected by using simple random sampling without replacement (SRSWOR). The expressions for the unbiased estimator of population total, its variance and the unbiased estimate of variance have been obtained under the proposed sheme. The condition under which the proposed sheme is more efficient than the usual RHC scheme has also been investigated.