Bayesian isotonic regression and trend analysis

In many applications, the mean of a response variable can be assumed to be a nondecreasing function of a continuous predictor, controlling for covariates. In such cases, interest often focuses on estimating the regression function, while also assessing evidence of an association. This article proposes a new framework for Bayesian isotonic regression and order-restricted inference. Approximating the regression function with a high-dimensional piecewise linear model, the nondecreasing constraint is incorporated through a prior distribution for the slopes consisting of a product mixture of point masses (accounting for flat regions) and truncated normal densities. To borrow information across the intervals and smooth the curve, the prior is formulated as a latent autoregressive normal process. This structure facilitates efficient posterior computation, since the full conditional distributions of the parameters have simple conjugate forms. Point and interval estimates of the regression function and posterior probabilities of an association for different regions of the predictor can be estimated from a single MCMC run. Generalizations to categorical outcomes and multiple predictors are described, and the approach is applied to an epidemiology application.     

Hypothesis tests for and against a simple order among proportions estimated by pooled testing

The use of pooled testing as a means of estimating the prevalence of rare traits has received considerable attention in recent years, particularly in the areas of public health, genetics, animal-disease assessment, and plant pathology. In pooled-testing applications, observations are made on pools of individuals amalgamated together. In this paper, we examine order-restricted hypothesis tests involving k >2 binomial proportions estimated by pooled testing, extending the earlier work of Tebbs and Swallow (2003, Biometrika, 90, 471-477 and Biometrical Journal, 45, 618-630). In particular, we focus on (i) testing the equality of proportions versus an isotonic alternative and (ii) testing for a violation of isotonicity. We propose new tests for each scenario and provide results which characterize the small-sample performance of our procedures. We illustrate our methods using two data sets; one from an observational HIV study and one from an agricultural experiment.     

Cholinergic- and Adrenergic-Stimulated Inositide Hydrolysis in Brain: Interaction, Regional Distribution, and Coupling Mechanisms

Carbachol and norepinephrine were used as agonists to compare and contrast cholinergic and adrenergic stimulation of inositide breakdown in rat brain slices. Carbachol acts through a muscarinic (possibly M1) receptor and norepinephrine acts through an alpha 1 adrenoceptor. Studies in cerebral cortical slices indicated that both agonists stimulated the production of inositol-1-phosphate and glycerophosphoinositol. Although the initial rates for the stimulation of inositol phosphate release were similar for the two ligands, the response to norepinephrine continued for 60 min and was larger compared with carbachol which plateaued at 30 min. The presence of carbachol did not affect the ED50 for norepinephrine. Concentrations of carbachol near the ED50 in combination with norepinephrine resulted in an additive response whereas maximal concentrations of carbachol and norepinephrine resulted in a less than additive response in the cortex. This negative interaction was also seen in the hippocampus and hypothalamus but not in the striatum, brainstem, spinal cord, olfactory bulb, or cerebellum. Norepinephrine had a larger response than carbachol in the hippocampus, striatum, and spinal cord, but the reverse was true in the olfactory bulb. Manganese (1 mM) stimulated the incorporation of [3H]inositol into phosphatidylinositol (PtdIns) four- to fivefold but not into polyphosphoinositides. The stimulation by manganese of PtdIns labelling increased the nonstimulated release of inositol phosphates but did not affect the stimulated release of inositol phosphates by carbachol or norepinephrine.(ABSTRACT TRUNCATED AT 250 WORDS)     

Interaction between ants and fruits of<Emphasis Type="Italic"> Guapira opposita</Emphasis> (Nyctaginaceae) in a Brazilian sandy plain rainforest: ant effects on seeds and seedlings

This study examines the dispersal system of Guapira opposita in a tropical sandy rainforest in southeast Brazil. Guapira trees produce small fruits with a high protein content (28.4%) and low lipid content (0.3%), and the plant is primarily dispersed by birds. Mature fruits of G. opposita can fall spontaneously with the pulp intact, or be dropped by birds with bits of pulp attached. In either case, ground-dwelling ants rapidly remove the fruits to their nest (93% after 12 h). The ponerine ants Odontomachus chelifer and Pachycondyla striata are the main seed vectors among the ants, and together account for 56% (20 of 36) of the ant-fruit interactions recorded on the forest floor. Individual workers of O. chelifer and P. striata transport single fruits to their nests. Bits of pulp are fed to larvae and worker nestmates, and intact seeds are discarded outside the nest. Germination success in Guapira is higher for cleaned seeds (pulp removed) than for seeds coated by pulp. Guapira seedlings and juveniles are more frequent close to Odontomachus nests than at sites without such nests. Soil samples from Odontomachus nests had greater penetrability, and higher concentrations of P, K, and Ca than random soil samples. Field experiments suggest that the association between G. opposita seedlings and O. chelifer nests can potentially render the plant some protection against herbivores. Results indicate that fruit displacement by ponerine ants play an important role in the biology of G. opposita seeds and seedlings in the sandy forest, and illustrate the complex nature of the dispersal ecology of tropical tree species.