Semiparametric Regression in Size-Biased Sampling

Summary .  Size-biased sampling arises when a positive-valued outcome variable is sampled with selection probability proportional to its size. In this article, we propose a semiparametric linear regression model to analyze size-biased outcomes. In our proposed model, the regression parameters of covariates are of major interest, while the distribution of random errors is unspecified. Under the proposed model, we discover that regression parameters are invariant regardless of size-biased sampling. Following this invariance property, we develop a simple estimation procedure for inferences. Our proposed methods are evaluated in simulation studies and applied to two real data analyses.     

Analysis of Multiply Matched Retrospective Studies When Risk Factor Under Study is Discrete,With Two or More Levels

The odds ratio is known to closely approximate the relative risk when the disease is rare. Logistic regression models are often used to estimate such odds ratios, but here a different model is used which avoids the assumptions implicit in logistic modelling; it also has the advantage of providing a test of homogeneity for odds rat os in situations where the logistic model cannot.     

Body size and area‐incidence relationships: is there a general pattern?

Aim This paper tests firstly for the existence of a general relationship between body size of terrestrial animals and their incidence across habitat patches of increasing size, and secondly for differences in this relationship between insects and vertebrates. Location The analysis was based on the occupancy pattern of 50 species from 15 different landscapes in a variety of ecosystems ranging from Central European grassland to Asian tropical forest. Methods The area‐occupancy relationship was described by incidence functions that were calculated using logistic regression. A correlation analysis between body size of the species and the patch area referring to the two given points of the incidence function was performed. In order to test for an effect of taxon (insects vs. vertebrates), an analysis of covariance was conducted. Results In all species, the incidence was found to increase with increasing patch area. The macroecological analysis showed a significant relationship between the incidence in habitat patches and the body size of terrestrial animals. The area requirement was found to increase linearly with increasing body size on a log‐log scale. This relationship did not differ significantly between insects and vertebrates. Conclusions The approach highlighted in this paper is to associate incidence functions with body size. The results suggest that body size is a general but rather rough predictor for the area requirements of animals. The relationship seems valid for a wide range of body sizes of terrestrial animals. However, further studies including isolation of habitats as well as additional species traits into the macroecological analysis of incidence functions are needed.     

Comparing Stochastically Restricted Linear Estimators in a Regression Model

Conditions for superiority of the minimum dispersion estimator over another with respect to the covariance matrix are derived when the vector parameter of a regression model is subject to competing stochastic restrictions. The restrictions may also consist both of a deterministic part and a stochastic part.     

Comparison of Southern Appalachian high-elevation outcrop plant communities with their Northern Appalachian counterparts

Abstract. Southern Appalachian high-elevation outcrops harbour six regionally rare Northern Appalachian taxa usually considered relicts of a Pleistocene alpine flora. For five of the six taxa, minimum elevation in the south was 367–1113 m higher than in the north. While habitats compared between the two regions share only 9% of their total flora, individual plots had up to 70% of their species occurring in the opposite region. The northern affinity of southern outcrops increased with elevation, slope steepness, soil Cu, B and SO₄ and decreased with potential solar radiation and soil Na. As a result, communities above 1600 m on felsic bedrock, and above 1350 m on mafic bedrock, were most northern in composition. Northern affinity of southern outcrops also increased with latitude, which may partly result from closer geographic proximity to past communities that provided progenitors for the current northern flora. Northern treeless habitats increased in southern affinity with increased slope steepness, perennial seepage, vegetation height, shade, soil pH, Al, Mn, Na and decreased elevation and organic matter. As a result, northern outcrop communities below treeline were most similar to those on southern outcrops. This suggests that southern outcrop vegetation may be more similar to Pleistocene outcrop vegetation than to Pleistocene alpine vegetation. Partial constrained ordination showed that while compositional differences between the Northern and Southern Appalachian habitats were largely explained by environmental differences, there was a significant component of residual variation explained by north or south position that was unrelated to environment. These residual compositional differences may result from historical influences on community structure involving stochastic extinction and colonization processes.     

Effect of pea bacterial blight (Pseudomonas syringae pv. pisi) on the yield of spring sown combining peas (Pisum sativum)

Field trials to examine the effect of pea bacterial blight (Pseudomonas syringae pv. pisi) (Psp) on the yield of combining peas were carried out at five sites (HRI Wellesbourne, ADAS Rosemaund, ADAS Terrington, PGRO, SASA East Craigs) in the UK in 1990, 1991 and 1992. Healthy seed, cv. Solara, and seed naturally infected with Psp Race 2 was sown in large plots (c. 200 m²) in the open or under nets to prevent bird damage by pigeons. Despite relatively low disease severity levels (< 15% leaf area) and separation by at least 12 m of cv. Consort (resistant to Race 2) between plots there was considerable spread of disease into plots sown with healthy seed. Regression analysis demonstrated a significant relationship between yield and disease. Of the disease measurements examined, disease severity on the leaves (stipules) at growth stage 208 was found to be the best predictor of yield. A model containing environmental and bird damage terms, in addition to disease, suggested that a yield loss of 0.98 t/ha would be expected for a disease severity score of 1, equivalent to 5% leaf area affected, at growth stage 208.     

A Cysteine Endopeptidase (“Dionain”) Is Involved in the Digestive Fluid of Dionaea muscipula (Venus’s Fly-trap)

The carnivorous plant Dionaea muscipula (Venus’s flytrap) secretes proteinases into the digestive fluid to digest prey proteins. In this study, we obtained evidence that the digestive fluid contains a cysteine endopeptidase, presumably belonging to the papain family, through inhibitor studies and partial amino acid sequencing of the major SDS–PAGE band protein. The name “dionain” is proposed for the enzyme.     

Seemingly Unrelated Generalized Linear Models

By using deviance standardized residuals, the seemingly unrelated regression estimation procedure is extended to generalized linear models, and fitted by an iterative procedure. The matrix of cross products of standardized residuals is asymptotically multivariate normal, and can be used for further multivariate analyses and for hypothesis testing.     

Estimation of Individual Growth Curves by Empirically Weighted Least Squares

The simultaneous estimation of individual growth curves and a mean growth curve is accomplished by weighted least squares. A polynomial curve is fitted for each individual and the polynomial parameters are linear functions of parameters corresponding to covariates. A simple, computationally efficient variance-covariance estimator is derived. The resultant estimate is used in the weighted least squares estimation. The results are compared to empirical Bayes estimation.     

pathmatrix: a geographical information system tool to compute effective distances among samples

pathmatrix is a tool used to compute matrices of effective geographical distances among samples using a least‐cost path algorithm. This program is dedicated to the study of the role of the environment on the spatial genetic structure of populations. Punctual locations (e.g. individuals) or zones encompassing sample data points (e.g. demes) are used in conjunction with a species‐specific friction map representing the cost of movement through the landscape. Matrices of effective distances can then be exported to population genetic software to test, for example, for isolation by distance. pathmatrix is an extension to the geographical information system (GIS) software arcview 3.x.