ASYMPTOTIC NORMALITY OF GOODNESS-OF-FIT STATISTICS FOR SPARSE POISSON DATA

Goodness-of-fit tests for discrete data and models with parameters to be estimated are usually based on Pearson's χ2 or the Likelihood Ratio Statistic. Both are included in the family of Power-Divergence Statistics SDλ which are asymptotically χ2 distributed for the usual sampling schemes. We derive a limiting standard normal distribution for a standardization Tλ of SDλ under Poisson sampling by considering an approach with an increasing number of cells. In contrast to the χ2 asymptotics we do not require an increase of all expected values and thus meet the situation when data are sparse. Our limit result is useful even if a bootstrap test is used, because it implies that the statistic Tλ should be bootstrapped and not the sum SDλ. The peculiarity of our approach is that the models under test only specify associations. Hence we have to deal with an infinite number of nuisance parameters. We illustrate our approach with an application.     

The generalized process manufacturing systems package

Process manufacturing systems should not be considered a simple variation to a discrete manufacturing control system. The change is often quite complex and generally it becomes easier to create a new package customized for the process manufacturer rather than try to change an existing M RP-based-discrete package. This article discusses why a discrete-to-process conversion can be an ineffective way to create a production control system. It describes the types of changes that will be necessary for process manufacturing systems.     

Maximizing product mix profitability - what's the best analysis tool

This paper takes a look at product mix profitability and compares several alternative methodologies for selecting the optimal product mix. It is argued that the optimal product mix is not determined using traditional accounting methodologies and that dropping marginally profitable products based on the accounting rules will give you less than optimal profitability. This paper looks at two different ways for coming up with the optimal product mix: one using theory of constraints (TOC) and another using linear programming.     

Notes on Theory and Practice in Social Work: a Comparative View

Please address reprint requests to Robert van Krieken, Department of Social Work, University of Sydney, Sydney, New South Wales 2006, Australia. Summary There are still a number of problems surrounding the relationshipbetween theories of social work practice and that practice itself.This paper examines the factors underlying those problems andemphasises their roots in the failure to examine the diversityof social work theories and practices. We refer to one attemptto resolve the problems—the distinction between ‘practicetheory’ and ‘theory of practice’—pointout some difficulties with it and suggest an alternative, three-folddistinction within theorising: between (a) materialist socialtheory, (b) strategic practice theory and (c) working concepts. As an example of how those distinctions can be used, we thenbriefly discuss the work of Oskar Negt and its introductioninto the Dutch welfare context, as it was the issues raisedby that which stimulated the ideas in this paper. We concludeby arguing that only this kind of perspective on theorisingcan produce ideas which are of real use to progressive socialwork practitioners.