Environmetrics最新文献

The present work takes an innovative point of view in the study of a marked point pattern dataset of two ants' species, over an irregular region with a spatial covariate. The approach, based on entropy measures, brings new insights to the interpretation of the behavior of such ants' nesting habits, which can be exploited in the general area of biodiversity evaluation. We make proper use of descriptive entropy measures and inferential approaches, performing a comparative study of their uncertainty and interpretability in the context of biodiversity. For the first time in the study of these ants' nests data, all the available information is fully exploited, and interpretation guidelines are given for assessing both the observed and the latent biodiversity of the system, with a simultaneous consideration of spatial structures, covariate and interpoint interaction effects. Computations are supported by the new release of our R package SpatEntropy.

The hierarchical model-based (HMB) statistical method is currently applied in connection with NASA's Global Ecosystem Dynamics Investigation (GEDI) mission for assessing forest aboveground biomass (AGB) in areas lacking a sufficiently large number of GEDI footprints for employing hybrid inference. This study focuses on variance estimation using a bootstrap procedure that separates the computations into parts, thus considerably reducing the computational time required and making bootstrapping a viable option in this context. The procedure we propose uses a theoretical decomposition of the HMB variance into two parts. Through this decomposition, each variance component can be estimated separately and simultaneously. For demonstrating the proposed procedure, we applied a square-root-transformed ordinary least squares (OLS) model, and parametric bootstrapping, in the first modeling step of HMB. In the second step, we applied a random forest model and pairwise bootstrapping. Monte Carlo simulations showed that the proposed variance estimator is approximately unbiased. The study was performed on an artificial copula-generated population that mimics forest conditions in Oregon, USA, using a dataset comprising AGB, GEDI, and Landsat variables.

Climate models are useful tools for analyzing historical and projecting future climate conditions. However, the model results tend to differ systematically from observations, particularly for parameters with complex spatial and temporal distributions such as precipitation. A combination of quantile mapping and generalized additive models (GAMs) is presented and proposed as a new method (Q-GAM) for the bias correction of daily precipitation. Q-GAM is demonstrated by using data from five European stations with different climate characteristics. For each station, the closest continental grid point of a EURO-CORDEX climate model was selected for bias correction. A bootstrapping experiment is presented with over 1000 repetitions of randomly splitting the historical period 1981 to 2005 into a calibration and evaluation period. The results for all stations reveal that Q-GAM is a straightforward, accurate and computationally efficient method for the bias correction of precipitation. In particular, the method improves the frequency of dry days and the total annual rainfall amount. This outcome is robust across stations with varying climate characteristics and also to the choice of calibration and evaluation periods. Similar results are also obtained for other precipitation characteristics such as the 0.9 and 0.95 quantiles.

With the advent of new alternative methods for rapid toxicity screening of chemicals comes the need for new statistical methodologies which appropriately synthesize the large amount of data collected. For example, transcriptomic assays can be used to assess the impact of a chemical on thousands of genes, but current approaches to analyzing the data treat each gene separately and do not allow sharing of information among genes within pathways. Furthermore, the methods employed are fully parametric and do not account for changes in distribution shape that may occur at high exposure levels. To address the limitations of these methods, we propose Constrained Logistic Density Regression (COLDER) to model expression data from different genes simultaneously. Under COLDER, the dose-response function for each gene is assigned a prior via a discrete logistic stick-breaking process (LSBP) whose weights depend on gene-level characteristics (e.g., pathway membership) and atoms consist of different dose-response functions subject to a shape constraint that ensures biological plausibility. The posterior distribution for the benchmark dose among genes within the same pathways can be estimated directly from the model, which is another advantage over current methods. The ability of COLDER to predict gene-level dose-response is evaluated in a simulation study and the method is illustrated with data from a National Toxicology Program study of Aflatoxin B1.

Colorblindness is a genetic condition that affects a person's ability to accurately perceive colors. Several papers still exist making use of rainbow colors palette to show output. In such cases, for colorblind people such graphs are meaningless. In this paper, we propose good practices and coding solutions developed in the R Free and Open Source Software to (i) simulate colorblindness, (ii) develop colorblind friendly color palettes and (iii) provide the tools for converting a noncolorblind friendly graph into a new image with improved colors.

Spatial models for areal data are often constructed such that all pairs of adjacent regions are assumed to have near-identical spatial autocorrelation. In practice, data can exhibit dependence structures more complicated than can be represented under this assumption. In this article, we develop a new model for spatially correlated data observed on graphs, which can flexibly represented many types of spatial dependence patterns while retaining aspects of the original graph geometry. Our method implies an embedding of the graph into Euclidean space wherein covariance can be modeled using traditional covariance functions, such as those from the Matérn family. We parameterize our model using a class of graph metrics compatible with such covariance functions, and which characterize distance in terms of network flow, a property useful for understanding proximity in many ecological settings. By estimating the parameters underlying these metrics, we recover the “intrinsic distances” between graph nodes, which assist in the interpretation of the estimated covariance and allow us to better understand the relationship between the observed process and spatial domain. We compare our model to existing methods for spatially dependent graph data, primarily conditional autoregressive models and their variants, and illustrate advantages of our method over traditional approaches. We fit our model to bird abundance data for several species in North Carolina, and show how it provides insight into the interactions between species-specific spatial distributions and geography.

We present a novel measure to assess the spatial balance of a sample by utilizing the balancing equation, which captures the balance between the sample units and their neighbours. Spatially balanced samples are desirable as they may reduce the variance of an estimator of a population parameter. If the auxiliary variables we employ to spread the sample possess high explanatory power for the variable(s) of interest, the resulting reduction in variance can be substantial. An advantageous aspect of using auxiliary variables is that their availability is not contingent upon the sampling effort. Therefore, we can assess and compare sampling designs before committing resources to full-scale surveys. By comparing the proposed measure with commonly used measures of spatial balance, we ascertain that our measure consistently yields meaningful insights regarding the spatial balance of samples. Consequently, our measure can effectively differentiate between various designs when planning a survey, evaluate the potential gains from replacing an existing sample, and determine which non-responding units would contribute the most to enhancing the set of responding units.

The growing frequency and size of wildfires across the US necessitates accurate quantitative assessment of evolving wildfire behavior to predict risk from future extreme wildfires. We build a joint model of wildfire counts and burned areas, regressing key model parameters on climate and demographic covariates. We use extended generalized Pareto distributions to model the full distribution of burned areas, capturing both moderate and extreme sizes, while leveraging extreme value theory to focus particularly on the right tail. We model wildfire counts with a zero-inflated negative binomial model, and join the wildfire counts and burned areas sub-models using a temporally-varying shared random effect. Our model successfully captures the trends of wildfire counts and burned areas. By investigating the predictive power of different sets of covariates, we find that fire indices are better predictors of wildfire burned area behavior than individual climate covariates, whereas climate covariates are influential drivers of wildfire occurrence behavior.