# Journal of the Royal Statistical Society

Опубликовано на портале: 20-07-2004

*Nancy Cleave*,

*Philip J. Brown*,

*Clive D. Payne*Journal of the Royal Statistical Society. 1995. Vol. 158. No. 1. P. 55-72.

In ecological inference one uses data which are aggregated by areal units to investigate
the behaviour of the individuals comprising those units. Aggregated data are readily
available in many fields and within a wide variety of data structures. In the structures
considered, the aggregate data are characterized by the absence of available data
in the internal cells of a cross-classification. The aim of the ecological methods
is to estimate the expected frequencies of such internal cells, which may be conditional
on chosen covariates. Four methods of ecological inference are reviewed and their
properties and appropriateness considered. These methods are then applied to data
for which the internal cells are known and their performances compared.

Опубликовано на портале: 20-07-2004

*J.N.K. Rao*,

*Jun Shao*Journal of the Royal Statistical Society. 1996. Vol. 91. No. 433. P. 343-348.

Establishment surveys based on list frames often use stratified random sampling with a small number of strata, H, and relatively large sample sizes, n_h, within strata. For such surveys, a grouped balanced half-sample (GBHS) method is often used for variance estimation and for construction of confidence intervals on population parameters of interest. In this method the sample in each stratum is first randomly divided into two groups, and then the balanced half-sample (BHS) method is applied to the groups. We show that the GBHS method leads to asymptotically incorrect inferences as the strata sample sizes n_h \rightarrow \infty with H fixed. To overcome this difficulty, we propose a repeatedly grouped balanced half-sample (RGBHS) method, which essentially involves independently repeating the grouping T times and then taking the average of the resulting T GBHS variance estimators. This method retains the simplicity of the GBHS method. We establish its asymptotic validity as \min n_h \rightarrow \infty and T \rightarrow \infty. We also study an alternative method by forming substrata within each stratum, consisting of a pair of sampling units, and then applying the BHS method on the total set of substrata, treating them as strata. We establish its asymptotic validity as \min n_h \rightarrow \infty. We provide simulation results on the finite-sample properties of the GBHS, RGBHS, the jackknife, and the alternative BHS method. Our results indicate that the proposed RGBHS method performs well for T as small as 15, thus providing flexibility in terms of the number of half-samples used. The alternative BHS method has also performed well in the simulation study.

Опубликовано на портале: 06-10-2003

*David J. Hand*,

*W. E. Henley*Journal of the Royal Statistical Society. 1997. Vol. 160. No. 3. P. 523-541.

Credit scoring is the term used to describe formal statistical methods used for classifying
applicants for credit into "good" and "bad" risk classes. Such methods have become
increasingly important with the dramatic growth in consumer credit in recent years.
A wide range of statistical methods has been applied, though the literature available
to the public is limited for reasons of commercial confidentiality. Particular problems
arising in the credit scoring context are examined and the statistical methods which
have been applied are reviewed.

Опубликовано на портале: 03-10-2003

*John Custanset*,

*Hillary Hillier*Journal of the Royal Statistical Society. 1998. Vol. 161. No. 3. P. 281-290.

This paper describes the background to the development of a new offical set of national
indicators of sustainable development--one of the first in the world to be published.
The paper discusses the role of statisticians in helping to define sustainable development,
and the problems of monitoring and reporting progress. The Minister of State for
the Environment has announced his ambition of developing a very small set of headline
indicators. This paper is intended to help to stimulate the debate over what they
should be.

**Statistics and Agriculture**[статья]

Опубликовано на портале: 19-07-2004

*J. C. Gower*Journal of the Royal Statistical Society. 1988. Vol. 151. No. 1. P. 179-200.

The relationship between statistics and agricultural research is reviewed. From the
end of the 18th century until the present, three main periods are identified:
from the beginnings of scientific agriculture in the Age of Improvement until the
first world war, which saw the use of field experiments to give information on plant
nutrition and which lead to a recognition of the need to handle variability,
the interwar years, dominated by R. A. Fisher, which saw the founding of experimental
design as a statistical discipline, the clearer understanding of the different contributions
to variability, the application of the new ideas to new areas associated with agriculture
(e.g. bioassay and multivariate analysis) and outside agriculture (e.g. medicine
and industry) and the development of mathematical statistics, and the post-war
years, initially concerned with an elaboration and unification of earlier ideas but,
more recently, with new methodology encouraged in response to new directions in agricultural
research (e.g. molecular biology, modelling), new forms of measurement provided by
novel instrumentation, and by computing developments (agricultural statisticians
have been prominent in developing statistical software). Over the 200 years covered
by the review, agricultural production of all kinds has dramatically increased and
it is held that statistics has played its part, usually indirectly, by encouraging
the efficient use of limited research resources and, occasionally, by discouraging
unjustified research. Increased production is currently less of a priority but many
agricultural research problems remain to which statisticians can and should contribute
(e.g. food quality, efficiency, environmental impact, stability of production).

Опубликовано на портале: 19-07-2004

*Anne Harrop*,

*Ian Plewis*Journal of the Royal Statistical Society. 1995. Vol. 158. No. 1. P. 91-106.

Secondary analysis of General Household Survey and Labour Force Survey data shows
how the structure of families in Great Britain has changed over the last 20 years.
Dependent children are now less likely to be living in a couple family and more likely
to be living with a lone mother who is either single or divorced. Families in simple
households with just two generations have become more common over time. Lone mothers
are now more likely to be living in simple households. The paper also considers how
the number and ages of dependent children are associated with family and household
type. Log-linear models are used both to smooth the data and to predict family structure
in the year 2000. Gaps in our knowledge about current family structures are discussed
together with implications of the findings for social policy.