Statistical Evaluation of the New Zealand Food Safety Authority Sampling Protocol for Imported Food

The New Zealand Food Safety Authority sampling protocol for compliance inspection of imported food products is evaluated for its ability to provide consumer protection. The sampling protocol involves both partial testing of imported consignments and complete skipping inspection of consignments based on the quality history. The risk posed by the strategies of partial testing and skipping inspection of imports is evaluated using the average outgoing quality limit and other performance measures. The cost dimension of sampling inspection is also considered. Suggestions for improvement, which include tightening the skipping inspection parameters, are made.     

Identifying health inequalities between Māori and non‐Māori using mortality tables

Abstract

While there is a need for more detailed information on health inequality to guide public health policy, the most complete and easily available data remain those in mortality tables. We investigate, via a comparative analysis of data from New Zealand on Māori and non‐Māori mortality, whether more detailed information than raw life expectancy may be extracted from the mortality tables. Given a parametric distribution for the mortality capable of fitting irregularities in mortality table data, the curvature of the survival and hazard rates can identify changes in mortality rates, such as infant and late‐life adult mortality, which allows for straightforward comparisons between the two sub‐populations. Our results identify an exogenous effect in earlier mortality among Maori, which correlates well with many published observations of health and health‐care inequalities between Māori and non‐Māori. This “proof of concept” for our method of analysis indicates that examination of bulk data such as those in mortality tables has a potential role in the design of more detailed studies involving causes of mortality.     

‘It’s who we are’: eco-nationalism and place in contesting deep-sea oil in Aotearoa New Zealand

ABSTRACT

Given near consensus among the scientific community about the anthropogenic nature of climate change, there is pressing concern about how to mobilise enough people to care and demand wider socio-political change. In this article we explore this urgent issue, drawing on recent conflicts over deep-sea oil exploration and drilling in Aotearoa New Zealand. We explore how some activist groups are attempting to mobilise care and concern around deep-sea oil drilling and climate change through the use of narratives that entwine aspects of national identity with the non-human world. We suggest that these activist groups are not concerned about a retreat of the state, but rather, are in direct conflict with the state, and state interventionism, over fossil fuel development trajectories in Aotearoa New Zealand. In drawing upon eco-nationalism, and particularly a way of life related to place, activists have called into question the common sense of business as usual and thereby sought to expand space for ‘ordinary’ Aotearoa New Zealanders to care about climate change.     

Combined continuous lot by lot acceptance sampling plan

For production processes involving low fraction non-conforming, the sample sizes of the usual attribute inspection plans are very large. A continuous sampling plan for such processes would also require either a large clearance interval or a large sampling fraction. This paper simplifies the approach of combining the lot by lot and continuous sampling plans recommended by Pesotchinsky (1987) and provides various performance measures for the combined plan. A discussion of the choice of the parameters is also given.     

Modeling lactation curves: classical parametric models re-examined and modified

A large number of methods for modeling lactation curves have been proposed – parametric and nonparametric, mathematically or biologically oriented. The most popular of these are methods that express the milk yield in terms of time via a parametric nonlinear functional equation. This is intuitive and allows for relatively easy mathematical and biological interpretations of the parameters involved. Interestingly, as far as we are aware, all such models generate nonzero milk yields on the whole positive time half-line, even though real lactation curves always have finite range, with spans of approximately 300 days for dairy cows. For this reason, we re-examine a number of existing parametric models, and modify them to produce finite-range lactation curves that fit remarkably well to data of milk yields from New Zealand cows. The use of daily or weekly yields rather than the monthly yields normally considered reveals considerable variation that is usually suppressed. Both individual and herd lactation curves are examined in the present paper, and median-based procedures explored as alternatives to the usual average-based methods. These suggestions offer further insights into the existing literature on modeling lactation curves.     

Slicing Up the Pie: Allocation of Central Government Funding of Care of Older People

The allocation of central government funds is a critical element in the equitable provision of local authority‐commissioned and ‐provided services. A variety of approaches to allocating funding for social services for older people have been used over the years, most recently founded on ‘needs‐based’ formulae. In 2004, the Department of Health for England commissioned research to help inform the improvement and updating of the formula. The results of individual‐level analyses were compared with the results obtained from analyses of small area (ward‐level) data on service users. Both analyses were affected by problems of data availability, particularly the individual‐level analysis, and the Department of Health and the (then) Office of the Deputy Prime Minister decided that the formula calculations should be based on the results of the small area analysis. However, despite the differences in approach, both methods produced very similar results. The correlation between the predicted relative needs weights for local authorities from the two models was 0.982. The article discusses the strengths and weaknesses of each approach and developments that could allow a normative approach that would incorporate future policy objectives into formulae that, to date, have inevitably been based on historical data and service patterns.     

The Consumer’s Risk and Costs in Zero-Acceptance Number Sampling

The primary purpose of sampling inspection is the protection of consumer’s interests. Although under simple cost models, sampling inspection never serves the producer’s interest, some form of sampling inspection can be beneficial to the consumer under the same assumptions. We consider the case of isolated lot inspection and examine the consumer risk, economic sample design, and errors in the inspection process. Acceptance sampling is shown to be cost-effective to the consumer whenever the lot quality is less than perfect, and even for perfect lot quality in the presence of inspection errors.     

Life expectancy of a bathtub shaped failure distribution

The mean residual life (MRL), or “life expectancy”, encapsulates the entire residual life of the product, and is thus of great interest in many fields, particularly those concerned with warranties, replacement policies, burn-in, and insurance. Estimating the profile of the MRL, let alone constructing confidence bands for it, is a difficult problem. We explore several approaches to estimating the variation in the profile of the mean residual life function, with special attention to a bathtub shaped failure distribution, called the modified Weibull distribution, which has generated considerable interest in reliability engineering. Parametric and non-parametric confidence bands are compared, and the theoretical coverage probabilities verified by simulation. An example application investigating the effectiveness of repairs is given, and possible further research discussed.