On the consequences of overstratification

It is common, in particular in observational studies in epidemiology,to impose stratification to adjust for possible effects of ageand other variables on the binary outcome of interest. Overstratificationmay lower the precision of the estimated effects of interest.Understratification risks bias. These issues are studied analytically.Asymptotic results show that loss of efficiency depends on thetrue effect and on a measure of the average imbalance acrossstrata between exposed and unexposed individuals. Bias dependson the correlation between stratum-specific size imbalancesand event rates in the unexposed. Approximate results are alsogiven. An example is used.     

Split-test Bonferroni correction for QEEG statistical maps

With statistical testing, corrections for multiple comparisons, such as Bonferroni adjustments, have given rise to controversies in the scientific community, because of their negative impact on statistical power. This impact is especially problematic for high-multidimensional data, such as multi-electrode brain recordings. With brain imaging data, a reliable method is needed to assess statistical significance of the data without losing statistical power. Conjunction analysis allows the combination of significance and consistency of an effect. Through a balanced combination of information from retest experiments (multiple trials split testing), we present an intuitively appealing, novel approach for brain imaging conjunction. The method is then tested and validated on synthetic data followed by a real-world test on QEEG data from patients with Alzheimer’s disease. This latter application requires both reliable type-I error and type-II error rates, because of the poor signal-to-noise ratio inherent in EEG signals.     

Effect of trap design, trap size and pheromone dose on male capture of two pine bast scales species (Hemiptera: Matsucoccidae): implications for monitoring and mass-trapping

Abstract 1 The effects of pheromone dose, trap size and trap design on the capture of male Matsucoccus feytaudi were studied in maritime pine forests of Portugal, France and Italy, and Matsucoccus josephi in Aleppo pine stands of Israel. 2 Males of both species respond to racemic mixtures of the respective sex pheromone at a dosage as low as 25 µg. However, for low population densities of M. feytaudi, a 50 µg dosage was needed to guarantee male catches significantly different from the control trap. 3 Male capture increased with increasing dosage up to a threshold level for both species. Overdose repellence was not observed even with baits containing 1600 and 2200 µg of the pheromone of M. josephi and M. feytaudi, respectively. 4 For M. feytaudi, a higher dose–response was observed at medium population densities, whereas lesser captures were registered at low and high population densities, suggesting female competition in the latter case. 5 Catches of M. feytaudi males were not affected by trap design, whereas M. josephi males were caught in significantly greater numbers in delta traps. Large traps caught significantly more males of both species. 6 The relative higher male catches in the marginal zone of the sticky traps is probably related to males landing behaviour in the vicinity of the pheromone source. 7 The shape and size of the trap did not affect the bias of the estimates of male catches. However, the plate traps provided higher precision. Both bias and precision improved with increasing dose.     

On the Estimation of Heritability from Unbalanced Data

The distribution and moments, of ANOVA estimator of heritability are given under unbalanced random model. These expressions are used to investigate the effect of unbalancedness on the bias and variance/MSE of the estimator and also the validity of certain approximations for its variance, numerically. The computed results reveal that the unbalancedness increases both the bias and variance/MSE of the estimator and the Smith-approximation for the variance of the estimator provides better accuracy.     

Atomic Resolution Cryo-EM Structure of β-Galactosidase

1. Download high-res image (381KB)
2. Download full-size image

     

Tension-Induced Error Correction and Not Kinetochore Attachment Status Activates the SAC in an Aurora-B/C-Dependent Manner in Oocytes

1. Download high-res image (193KB)
2. Download full-size image

     

Wald Tests of Location for Symmetric Nonnormal Data

For nonnormal data we suggest a test of location based on a broader family of distributions than normality. Such a test will in a sense fall between the standard parametric and non parametric tests. We see that the Wald tests based on this family of distributions have some advantages over the score tests and that they perform well in comparison to standard parametric and nonparametric tests in a variety of situations. We also consider when and how to apply such tests in practice.     

The Water Framework Directive’s “percentage of surface water bodies at good status”: unveiling the hidden side of a “hyperindicator”

The Water Framework Directive (WFD) has provided the means of standardizing the way surface water bodies are monitored throughout the European Union (EU), using a common evaluation measure, the percentage of surface water bodies at good status, based largely on the structure and functioning of aquatic ecosystems. However, the evaluation of good status is based on the way the WFD is implemented, which differs in each country. In this article, we analyze how the WFD is implemented in France, how the water agencies divide up the water bodies, the areas covered by their monitoring networks, and the modalities of obtaining data to provide the EU with the percentage of water bodies at good status. This analysis reveals that it is this hyperindicator itself that is at stake, obtained by successively aggregating values measured in time and space, from the monitoring station to the River Basin District (RBD), reducing vast amounts of information to a single measure per RBD, while long-term monitoring of the major European rivers and their sedimentary budgets, which show improvements in certain quality aspects, are largely overlooked by the WFD. When drawing up the indicator, the agencies identify certain biases but not others. This raises the question of its use and relevance for managers and politicians, at both national and European level.