Journal of Agricultural Biological and Environmental Statistics最新文献

Capture-recapture (CRC) experiments conducted over discrete time points motivate the development of models characterizing animal behavioral responses to facilitate estimating sizes of closed animal populations. We propose a multinomial distribution-based CRC modeling framework allowing for flexibly incorporating behavioral response patterns. In the proposed modeling framework, behavioral patterns of animals are reflected by specifying desirable constraints among conditional probabilities used to parameterize overall probabilities of different capture histories. We explicitly introduce various sets of crucial constraints which encode interpretable assumptions of behavioral patterns and lead to a unique estimate of the animal population size. Bias corrections and Bayesian credible intervals previously designed for disease surveillance are adapted to accommodate sparse CRC data which are commonly encountered in ecological studies. The proposed method incorporating minimal constraints is demonstrated to provide comparatively robust estimates in real data applications and simulation studies. To improve estimation when data are sparse, we also illustrate the use of Akaike's information criterion (AIC) to potentially justify additional noncrucial modeling constraints.

This article focuses on the study of lactating sows, where the main interest is the influence of temperature, measured throughout the day, on the lower quantiles of the daily feed intake. We outline a model framework and estimation methodology for quantile regression in scenarios with longitudinal data and functional covariates. The quantile regression model uses a time-varying regression coefficient function to quantify the association between covariates and the quantile level of interest, and it includes subject-specific intercepts to incorporate within-subject dependence. Estimation relies on spline representations of the unknown coefficient functions and can be carried out with existing software. We introduce bootstrap procedures for bias adjustment and computation of standard errors. Analysis of the lactation data indicates, among others, that the influence of temperature increases during the lactation period.Supplementary materials accompanying this paper appear on-line.

Supplementary information: The online version contains supplementary material available at 10.1007/s13253-024-00601-5.

The space-time epidemic-type aftershock sequence (space-time ETAS) is a standard model for the analysis of earthquake catalogs. The model considers a semi-parametric conditional intensity function consisting of a semi-parametric background rate and a parametric aftershock rate. For the estimation procedure, the optimization employs an iterative algorithm where the nonparametric and parametric components are estimated iteratively using, respectively, kernel density estimation and maximum likelihood technique. ETAS and etasFLP are the two R packages that implement such a procedure with different techniques for estimating both the nonparametric and parametric components. The two packages have been studied from different directions and have not been evaluated together. This study examines the common features of the models and algorithms generated from the packages, and then evaluates their performance through simulation study and application to the Sumatran earthquake. For the analysis involving small or medium number of earthquakes, the etasFLP outperforms ETAS in terms of parameter estimation and computing time. For the application, we identify three main areas of high seismic risk: Simeulue Island, Nias Island, and southeast of Siberut Island.

Paleoenvironmental data are essential for reconstructing environmental conditions in the distant past, and these reconstructions strongly depend on proxies and age–depth models. Proxies are indirect measurements that substitute for variables that cannot be directly measured, such as past precipitation. Conversely, an age–depth model is a tool that correlates the observed proxy with a specific moment in time. Bayesian age–depth modelling has proved to be a powerful method for estimating sediment ages and their associated uncertainties. However, there remains considerable potential for further integration into proxy analysis. In this paper, we explore a mathematical justification and a computational approach that integrates uncertainty at the age–depth level and propagates it to the proxy scale in the form of a posterior predictive distribution. This method mitigates potential biases and errors by removing the need to assign a single age to a given proxy measurement. It allows for quantifying the likelihood that proxy data values correspond to modelled ages, thus enabling the quantification of uncertainty in both the temporal and proxy value domains. The use of Bayesian statistics in proxy analysis represents a relatively recent advancement. We aim to mathematically justify incorporating the Markov chain Monte Carlo output from age–depth models into proxy analysis and to present a novel methodology for constructing environmental reconstructions using this approach.

Ecological science and management often require animal population abundance estimates to determine population status, set harvest limits on exploited populations, assess biodiversity, and evaluate the effects of management actions. However, sampling can harm animal populations. Motivated by trawl sampling of an endangered fish, we present a sequential adaptive sampling design focused on making population-level inferences while limiting harm to the target population. The design incorporates stopping rules such that multiple samples are collected at a site until one or more individuals from the target population are captured, conditional on the number of samples falling within a predetermined range. With this application in mind, we pair the stopping rules sampling design with a density model from which to base abundance indices. We use theoretical analyses and simulations to evaluate inference of population parameters and reduction in catch under the stopping rule sampling design compared to fixed sampling designs. Density point estimates based on stopping rules could theoretically be biased high, but simulations indicated that the stopping rules did not induce noticeable bias in practice. Retrospective analysis of the case study indicated that the stopping rules reduced catch by 60% compared to a fixed sampling design with maximum possible effort.Supplementary materials accompanying this paper appear online.

Diversity is vital across various fields like ecology, business, and medicine. From a statistical standpoint, determining diversity presents consistent methodological hurdles, regardless of the specific context. For instance, in ecology, while biodiversity is widely acknowledged as beneficial for ecosystems, there is no universally accepted measure due to diversity’s multidimensional nature. Recent research has introduced functional data analysis to address diversity profiles, which are inherently complex and multidimensional. However, a notable limitation is the need for a precise strategy to identify anomalous ecological communities. This study proposes a novel approach to biodiversity assessment using a functional outlier detection system by extending the functional box plot and outliergram to the context of suitable transformations of Hill’s numbers. This research holds significance in identifying early warning signs preceding biodiversity loss and the presence of potential pollutants or invasive species in ecological communities.

Moments play a crucial role for understanding the mathematical properties and practical applications of Hawkes processes. Here, we derive expectations of Hawkes processes and their intensity functions using a recently introduced Markovian embedding of (generally non-Markovian) linear and nonlinear Hawkes processes via a field-theoretical approach. The necessary and sufficient conditions for the stability of the Hawkes processes are also given by using the expectations of intensity functions directly via some matrix manipulations. Two kinds of Hawkes processes are considered, the standard linear Hawkes process with non-Markovian memory function expressed as a finite sum of exponentials, and the nonlinear Hawkes process with an intensity function that is quadratic as a function of an internal variable (“tension”) itself expressed as the sum over all past events with memory function given as a finite sum of exponentials and with zero mean random marks. All results obtained for the quadratic Hawkes processes are new contributions to the literature. The results obtained for linear Hawkes processes recover already known conclusions, while providing a novel alternative approach to existing methods. The matrix method presented in this paper gives a new way for finding the necessary and sufficient conditions for the stability of Hawkes processes.

We present an innovative approach leveraging Physics-Guided Neural Networks (PGNNs) for enhancing agricultural quality assessments. Central to our methodology is the application of physics-guided inverse regression, a technique that significantly improves the model’s ability to precisely predict quality metrics of crops. This approach directly addresses the challenges of scalability, speed, and practicality that traditional assessment methods face. By integrating physical principles, notably Fick’s second law of diffusion, into neural network architectures, our developed PGNN model achieves a notable advancement in enhancing both the interpretability and accuracy of assessments. Empirical validation conducted on cucumbers and mushrooms demonstrates the superior capability of our model in outperforming conventional computer vision techniques in postharvest quality evaluation. This underscores our contribution as a scalable and efficient solution to the pressing demands of global food supply challenges.

Augmented block designs for unreplicated test treatments are investigated under the A- and MV-criteria with respect to test versus test, control versus test and control versus control comparisons. We derive design-independent lower bounds on these criteria over a wide class of competing designs. These bounds are useful benchmarks and the resulting expressions for efficiencies enable objective assessment of any given design under theA- and MV-criteria. It is seen that the use of BIB designs and duals thereof as well as existing block design catalogs often leads to very high efficiencies for all three types of comparisons. Illustrative examples, including a large-scale one, are presented.

The microbiome constitutes a complex microbial ecology of interacting components that regulates important pathways in the host. Most microbial communities at various body sites tend to share common substructures of interactions, while also showing diversity related to the needs of the local environment. The aim of this paper is to develop a method for inferring both the common core and the differences in such microbiota systems. The approach combines two elements: (i) a random graph model generating networks across environments, and capturing potential relatedness at the structural level, with (ii) a Gaussian copula graphical model for the inference of environment-specific networks from multivariate microbial data. We propose a Bayesian approach for the joint inference of microbiota systems from metagenomic data for a number of body sites. The analysis of human microbiome data shows how the proposed random graphical model is able to capture varying levels of structural similarity across the different body sites and how this is supported by their taxonomical classification. Beyond a stable core, the inferred microbiome systems show interesting differences between the body sites, as well as interpretable relationships between various classes of microbes.