A simple variance formula for population size estimators by conditioning

This note considers the variance estimation for population size estimators based on capture–recapture experiments. Whereas a diversity of estimators of the population size has been suggested, the question of estimating the associated variances is less frequently addressed. This note points out that the technique of conditioning can be applied here successfully which also allows us to identify sources of variation: the variance due to estimation of the model parameters and the binomial variance due to sampling n units from a population of size N. It is applied to estimators typically used in capture–recapture experiments in continuous time including the estimators of Zelterman and Chao and improves upon previously used variance estimators. In addition, knowledge of the variances associated with the estimators by Zelterman and Chao allows the suggestion of a new estimator as the weighted sum of the two. The decomposition of the variance into the two sources allows also a new understanding of how resampling techniques like the Bootstrap could be used appropriately. Finally, the sample size question for capture–recapture experiments is addressed. Since the variance of population size estimators increases with the sample size, it is suggested to use relative measures such as the observed-to-hidden ratio or the completeness of identification proportion for approaching the question of sample size choice.

The use of bootstrapped Malmquist indices to reassess productivity change findings: an application to a sample of Polish farms

This article assesses the extent to which sampling variation affects findings about Malmquist productivity change derived using data envelopment analysis (DEA), in the first stage by calculating productivity indices and in the second stage by investigating the farm-specific change in productivity. Confidence intervals for Malmquist indices are constructed using Simar and Wilson's (1999) bootstrapping procedure. The main contribution of this article is to account in the second stage for the information in the second stage provided by the first-stage bootstrap. The DEA SEs of the Malmquist indices given by bootstrapping are employed in an innovative heteroscedastic panel regression, using a maximum likelihood procedure. The application is to a sample of 250 Polish farms over the period 1996 to 2000. The confidence intervals' results suggest that the second half of 1990s for Polish farms was characterized not so much by productivity regress but rather by stagnation. As for the determinants of farm productivity change, we find that the integration of the DEA SEs in the second-stage regression is significant in explaining a proportion of the variance in the error term. Although our heteroscedastic regression results differ with those from the standard OLS, in terms of significance and sign, they are consistent with theory and previous research.

An exploration of the drivers to bio-security collective action among a sample of UK cattle and sheep farmers

At present, collective action regarding bio-security among UK cattle and sheep farmers is rare. Despite the occurrence of catastrophic livestock diseases such as bovine spongiform encephalopathy (BSE) and foot and mouth disease (FMD), within recent decades, there are few national or local farmer-led animal health schemes. To explore the reasons for this apparent lack of interest, we utilised a socio-psychological approach to disaggregate the cognitive, emotive and contextual factors driving bio-security behaviour among cattle and sheep farmers in the United Kingdom (UK). In total, we interviewed 121 farmers in South-West England and Wales. The main analytical tools included a content, cluster and logistic regression analysis. The results of the content analysis illustrated apparent 'dissonance' between bio-security attitudes and behaviour.(1) Despite the heavy toll animal disease has taken on the agricultural economy, most study participants were dismissive of the many measures associated with bio-security. Justification for this lack of interest was largely framed in relation to the collective attribution or blame for the disease threats themselves. Indeed, epidemic diseases were largely related to external actors and agents. Reasons for outbreaks included inadequate border control, in tandem with ineffective policies and regulations. Conversely, endemic livestock disease was viewed as a problem for 'bad' farmers and not an issue for those individuals who managed their stock well. As such, there was little utility in forming groups to address what was largely perceived as an individual problem. Further, we found that attitudes toward bio-security did not appear to be influenced by any particular source of information per se. While strong negative attitudes were found toward specific sources of bio-security information, e.g. government leaflets, these appear to simply reflect widely held beliefs. In relation to actual bio-security behaviours, the logistic regression analysis revealed no significant difference between in-scheme and out of scheme farmers. We concluded that in order to support collective action with regard to bio-security, messages need to be reframed and delivered from a neutral source. Efforts to support group formation must also recognise and address the issues relating to perceptions of social connectedness among the communities involved. (c) 2008 Elsevier B.V. All rights reserved.

A case study of sample design for longitudinal research: young lives

This paper presents a case study to illustrate the range of decisions involved in designing a sampling strategy for a complex, longitudinal research study. It is based on experience from the Young Lives project and identifies the approaches used to sample children for longitudinal follow-up in four less developed countries (LDCs). The rationale for decisions made and the resulting benefits, and limitations, of the approaches adopted are discussed. Of particular importance is the choice of sampling approach to yield useful analysis; specific examples are presented of how this informed the design of the Young Lives sampling strategy.

Comparison of sample size formulae for 2x2 cross-over designs applied to bioequivalence studies

We consider the comparison of two formulations in terms of average bioequivalence using the 2 × 2 cross-over design. In a bioequivalence study, the primary outcome is a pharmacokinetic measure, such as the area under the plasma concentration by time curve, which is usually assumed to have a lognormal distribution. The criterion typically used for claiming bioequivalence is that the 90% confidence interval for the ratio of the means should lie within the interval (0.80, 1.25), or equivalently the 90% confidence interval for the differences in the means on the natural log scale should be within the interval (-0.2231, 0.2231). We compare the gold standard method for calculation of the sample size based on the non-central t distribution with those based on the central t and normal distributions. In practice, the differences between the various approaches are likely to be small. Further approximations to the power function are sometimes used to simplify the calculations. These approximations should be used with caution, because the sample size required for a desirable level of power might be under- or overestimated compared to the gold standard method. However, in some situations the approximate methods produce very similar sample sizes to the gold standard method. Copyright © 2005 John Wiley & Sons, Ltd.

The F test for comparing two normal variances: correct and incorrect calculation of the two-sided p-value?

This article illustrates that not all statistical software packages are correctly calculating a p-value for the classical F test comparison of two independent Normal variances. This is illustrated with a simple example, and the reasons why are discussed. Eight different software packages are considered.

The failure of meta-analytic asymptotics for the seemingly efficient estimator of the common risk difference

We consider the case of a multicenter trial in which the center specific sample sizes are potentially small. Under homogeneity, the conventional procedure is to pool information using a weighted estimator where the weights used are inverse estimated center-specific variances. Whereas this procedure is efficient for conventional asymptotics (e. g. center-specific sample sizes become large, number of center fixed), it is commonly believed that the efficiency of this estimator holds true also for meta-analytic asymptotics (e.g. center-specific sample size bounded, potentially small, and number of centers large). In this contribution we demonstrate that this estimator fails to be efficient. In fact, it shows a persistent bias with increasing number of centers showing that it isnot meta-consistent. In addition, we show that the Cochran and Mantel-Haenszel weighted estimators are meta-consistent and, in more generality, provide conditions on the weights such that the associated weighted estimator is meta-consistent.

A simple variance formula for population size estimators by conditioning

This note considers the variance estimation for population size estimators based on capture–recapture experiments. Whereas a diversity of estimators of the population size has been suggested, the question of estimating the associated variances is less frequently addressed. This note points out that the technique of conditioning can be applied here successfully which also allows us to identify sources of variation: the variance due to estimation of the model parameters and the binomial variance due to sampling n units from a population of size N. It is applied to estimators typically used in capture–recapture experiments in continuous time including the estimators of Zelterman and Chao and improves upon previously used variance estimators. In addition, knowledge of the variances associated with the estimators by Zelterman and Chao allows the suggestion of a new estimator as the weighted sum of the two. The decomposition of the variance into the two sources allows also a new understanding of how resampling techniques like the Bootstrap could be used appropriately. Finally, the sample size question for capture–recapture experiments is addressed. Since the variance of population size estimators increases with the sample size, it is suggested to use relative measures such as the observed-to-hidden ratio or the completeness of identification proportion for approaching the question of sample size choice.

Bayesian sample size for exploratory clinical trials incorporating historical data

This paper presents a simple Bayesian approach to sample size determination in clinical trials. It is required that the trial should be large enough to ensure that the data collected will provide convincing evidence either that an experimental treatment is better than a control or that it fails to improve upon control by some clinically relevant difference. The method resembles standard frequentist formulations of the problem, and indeed in certain circumstances involving 'non-informative' prior information it leads to identical answers. In particular, unlike many Bayesian approaches to sample size determination, use is made of an alternative hypothesis that an experimental treatment is better than a control treatment by some specified magnitude. The approach is introduced in the context of testing whether a single stream of binary observations are consistent with a given success rate p(0). Next the case of comparing two independent streams of normally distributed responses is considered, first under the assumption that their common variance is known and then for unknown variance. Finally, the more general situation in which a large sample is to be collected and analysed according to the asymptotic properties of the score statistic is explored. Copyright (C) 2007 John Wiley & Sons, Ltd.

Adjusted jackknife for imputation under unequal probability sampling without replacement

Imputation is commonly used to compensate for item non-response in sample surveys. If we treat the imputed values as if they are true values, and then compute the variance estimates by using standard methods, such as the jackknife, we can seriously underestimate the true variances. We propose a modified jackknife variance estimator which is defined for any without-replacement unequal probability sampling design in the presence of imputation and non-negligible sampling fraction. Mean, ratio and random-imputation methods will be considered. The practical advantage of the method proposed is its breadth of applicability.