Simultaneous modeling of multivariate heterogeneous responses and heteroskedasticity via a two-stage composite likelihood

Multivariate heterogeneous responses and heteroskedasticity have attracted increasing attention in recent years. In genome-wide association studies, effective simultaneous modeling of multiple phenotypes would improve statistical power and interpretability. However, a flexible common modeling system for heterogeneous data types can pose computational difficulties. Here we build upon a previous method for multivariate probit estimation using a two-stage composite likelihood that exhibits favorable computational time while retaining attractive parameter estimation properties. We extend this approach to incorporate multivariate responses of heterogeneous data types (binary and continuous), and possible heteroskedasticity. Although the approach has wide applications, it would be particularly useful for genomics, precision medicine, or individual biomedical prediction. Using a genomics example, we explore statistical power and confirm that the approach performs well for hypothesis testing and coverage percentages under a wide variety of settings. The approach has the potential to better leverage genomics data and provide interpretable inference for pleiotropy, in which a locus is associated with multiple traits.     

Optic flow in the natural habitats of zebrafish supports spatial biases in visual self-motion estimation

1. Download : Download high-res image (188KB)
2. Download : Download full-size image

     

Social and environmental determinants of malaria in space and time in Viet Nam

The malaria burden in Viet Nam has been in decline in recent decades, but localised areas of high transmission remain. We used spatiotemporal analytical tools to determine the social and environmental drivers of malaria risk and to identify residual high-risk areas where control and surveillance resources can be targeted. Counts of reported Plasmodium falciparum and Plasmodium vivax malaria cases by month (January 2007-December 2008) and by district were assembled. Zero-inflated Poisson regression models were developed in a Bayesian framework. Models had the percentage of the district’s population living below the poverty line, percent of the district covered by forest, median elevation, median long-term average precipitation, and minimum temperature included as fixed effects, and terms for temporal trend and residual district-level spatial autocorrelation. Strong temporal and spatial heterogeneity in counts of malaria cases was apparent. Poverty and forest cover were significantly associated with an increased count of malaria cases but the magnitude and direction of associations between climate and malaria varied by socio-ecological zone. There was a declining trend in counts of malaria cases during the study period. After accounting for the social and environmental fixed effects, substantial spatial heterogeneity was still evident. Unmeasured factors which may contribute to this residual variation include malaria control activities, population migration and accessibility to health care. Forest-related activities and factors encompassed by poverty indicators are major drivers of malaria incidence in Viet Nam.     

Spatial distribution of Tephrocactus aoracanthus (Lem.) Lem. in relation to shrubs in the hyperarid regions of west‐central Argentina

The spatial intraspecific and interspecific distribution of Tephrocactus aoracanthus (Lem.) Lem. was studied using univariate and bivariate point pattern analysis, at landscape scale in four different physiographic units and at microscale in terms of the shrubs found in those units. The influence of shrubs on photosynthetically active radiation and on soil temperature under their canopies was analysed. Results show a high environmental variability in light and temperature under shrubs that generally has no influence on the distribution of T. aoracanthus. Apparently, this cactus has great ability to adapt to different conditions of both photosynthetically active radiation and temperature. However, intraspecific distribution was highly clustered in all physiographic units, independently of bushes. Possibly, the mode of seed dispersal and the rooting of cladodes at small scale are the main processes that determine the strong intraspecific clustering of T. aoracanthus.     

Rank Tests for correlated Random Variables

In this paper we consider the asymptotic distribution of linear rank-statistics allowing certain dependencies between the random variables. General theorems will be given, from which the results contained in SEN (1967a, 1967b, 1968), MEHRA /SEN (1969) and PURI /SEN (1971) can be derived. Applying these theorems we can derive ranktests for the two-sample problem for tied observations, for the two-factor mixed model with random interaction and for a hierarchical design. The distribution of the proposed teststatistics for small sample sizes is considered by Monte-Carlo studies.     

Published GMO studies find no evidence of harm when corrected for multiple comparisons

A number of widely debated research articles claiming possible technology-related health concerns have influenced the public opinion on genetically modified food safety. We performed a statistical reanalysis and review of experimental data presented in some of these studies and found that quite often in contradiction with the authors’ conclusions the data actually provides weak evidence of harm that cannot be differentiated from chance. In our opinion the problem of statistically unaccounted multiple comparisons has led to some of the most cited anti-genetically modified organism health claims in history. We hope this analysis puts the original results of these studies into proper context.     

Lognormal distribution of firing time and rate from a single neuron?

Even a single neuron may be able to produce significant lognormal features in its firing statistics due to noise in the charging ion current. A mathematical scheme introduced in advanced nanotechnology is relevant for the analysis of this mechanism in the simplest case, the integrate-and-fire model with white noise in the charging ion current.     

Simple Test Statistics for a Fixed Number of Matched Samples with Ordinal Outcome Variables

In a preceding paper, we (Nurminen et al. 1981) advocated the use of the sole referent series as the basis of estimating moments in the construction of test statistics for comparative studies. Three simple test statistics, two metric approaches and one procedure based on ranks, incorporating this principle are introduced for small matched samples with ordinal outcome variables. Associated methods for computing an “exact” probability value are derived. The techniques are illustrated by real data from a study in the field of occupational health epidemiology.