Jeroen Pannekoek

Indexing European bird population trends using results of national monitoring schemes: a trial of a new method

Many European countries have annual breeding bird monitoring schemes based on nationwide samples; most are in northern and western Europe. We have developed a method to produce yearly population indices of bird species across countries by combining the results of existing national schemes. The method takes into account the differences in population sizes per country, as well as the differences in field methods, and the numbers of sites and years covered by the national schemes. In order to test the method, we collected raw data from a number of countries and applied an index method to produce scheme results per country. Data were collected for five farmland species (Lapwing Vanellus vanellus, Linnet Carduelis cannabina, Skylark Alauda arvensis, Whitethroat Sylvia communis and Yellowhammer Emberiza citrinella), from seven countries (UK, Netherlands, Denmark, Germany, Finland, Latvia and Estonia) for a 20-year period (1978–97). The trial demonstrated that it was possible to combine national indices to provide supra-national yearly totals and their standard errors; the results were similar to those produced when the raw data were used. Thus, yearly European indices can be produced by exchanging only limited amounts of information, that is the national yearly indices of each species or, preferably, the yearly population numbers and their standard errors. At a European scale, the populations of the five species selected have changed considerably. In western Europe (UK, Netherlands, Denmark and former West Germany combined), Linnet, Skylark and Yellowhammer have declined and Whitethroat has increased. Most changes occurred during the first ten-year period (1978–88). The changes in eastern Europe (the remaining countries) were less clear, in part because the statistical power of the national schemes is as yet limited.

Calibrated imputation of numerical data under linear edit restrictions

A common problem faced by statistical offices is that data may be missing from collected data sets. The typical way to overcome this problem is to impute the missing data. The problem of imputing missing data is complicated by the fact that statistical data often have to satisfy certain edit rules and that values of variables sometimes have to sum up to known totals. Standard imputation methods for numerical data as described in the literature generally do not take such edit rules and totals into account. In the paper we describe algorithms for imputation of missing numerical data that do take edit restrictions into account and that ensure that sums are calibrated to known totals. The methods sequentially impute the missing data, i.e. the variables with missing values are imputed one by one. To assess the performance of the imputation methods a simulation study is carried out as well as an evaluation study based on a real dataset.

To Work Oneself Out of Poverty: The Dutch Experience 1989-96

This paper investigates the effect of finding work by one of the household members on the probability of escaping from poverty in the Netherlands. For households with non-active heads, finding work by the head of the household is the most important (investigated) event connected with exiting poverty, nearly a third of all poverty endings. However, finding a job by the head of the household does not guarantee one leaving poverty. In practice, the success rate yields 25 percent. A multivariate analysis shows that finding a job by the head of the household increases the chance of leaving poverty with 22 percent points. So, some exits from poverty are a result of other factors or are due to selectivity of the job-finders. This difference is much larger when partners or (adult) children find jobs.

Statistical methods for some simple disclosure limitation rules

To guard the confidentiality of information provided by respondents, statistical offices apply disclosure limitation techniques. An often applied technique is to ensure that there are no categories for which the population frequency is presumed to be small (‘rare’ categories). This is attained by recoding, top‐coding or setting values to ‘unknown’. Since population frequencies are usually not available, the decision that a category is rare is often based on intuitive considerations. This is a time consuming process, involving many decisions of the disclosure limitation practitioners. In this paper it will be explored to what extent the sample frequencies can be used to make such decisions. This leads to a procedure which enables to automatically scan a data set for rare category combinations, whereby ‘rare’ is defined by the disclosure limitation policy of the statistical office.

Automated and Manual Data Editing: A View on Process Design and Methodology

Abstract Data editing is arguably one of the most resource-intensive processes at NSIs. Forced by everincreasing budget pressure, NSIs keep searching for more efficient forms of data editing. Efficiency gains can be obtained by selective editing, that is, limiting the manual editing to influential errors, and by automating the editing process as much as possible. In our view, an optimal mix of these two strategies should be aimed for. In this article we present a decomposition of the overall editing process into a number of different tasks and give an upto- date overview of all the possibilities of automatic editing in terms of these tasks. During the design of an editing process, this decomposition may be helpful in deciding which tasks can be done automatically and for which tasks (additional) manual editing is required. Such decisions can be made a priori, based on the specific nature of the task, or by empirical evaluation, which is illustrated by examples. The decomposition in tasks, or statistical functions, also naturally leads to reuseable components, resulting in efficiency gains in process design.

Comment on “Working with population totals in the presence of missing data comparing imputation methods in terms of bias and precision” by Onkelinx et al. (2016)

In their recent paper, Onkelinx et al. (2016), hereafter called ONK16, present a novel application of multiple imputation (hereafter called MI) techniques to water bird censuses. This presentation is accompanied by a comparison of MI with two existing software packages for bird count analysis: UIndex (Underhill and Prŷs-Jones 1994) and BirdSTATs/TRIM (Pannekoek and van Strien 2005; van der Meij 2013). Although we fully agree that for some use cases, multiple imputation as a method is a useful alternative to analytical approaches, e.g., as used in TRIM, to infer the uncertainty associated with the analysis of trends and/or indices in bird count data, we do believe that the conclusions drawn about UIndex, BirdStats and TRIM are contingent upon a number of misconceptions about these programs. In this Comment, we summarize these, and make a brief assessment of their consequences, where appropriate.