Comparative species abundance modeling of Capitellidae (Annelida) in Tampa Bay, Florida, USA

2020 ◽  
Vol 653 ◽  
pp. 105-119
Author(s):  
J Hilliard ◽  
D Karlen ◽  
T Dix ◽  
S Markham ◽  
A Schulze
Keyword(s):  
Negative Binomial ◽  
Generalized Additive Models ◽  
Species Abundance ◽  
Single Species ◽  
Tampa Bay ◽  
Additive Models ◽  
Boosted Regression Trees ◽  
Environmental Drivers ◽  
Hurdle Models ◽  
Abundance Modeling

Capitellid polychaetes are ubiquitous throughout the world’s oceans and are often encountered in high abundance. We used an extensive dataset of species abundance and distribution records of the Capitella capitata complex, C. aciculata, C. jonesi, Heteromastus filiformis, Mediomastus ambiseta, and M. californiensis from Tampa Bay, Florida, USA, as a model system of closely related species filling a similar ecological niche. We sought to (1) characterize the spatial distribution of each species, (2) determine if a single species abundance modeling strategy could be applied to them all, and (3) assess environmental drivers of species distribution and abundance. We found that all species had a zero-inflated abundance distribution and there was spatial autocorrelation by bay regions. Lorenz curves were an effective tool to assess spatial patterns of species abundance across large areas. Bay segment, depth, and dissolved oxygen were the most important environmental drivers. Modeling was accomplished by comparing 6 different approaches: 4 generalized additive models (GAMs: Poisson, negative binomial, Tweedie, and zero-inflated Poisson distributions), hurdle models, and boosted regression trees. There was no single model with top performance for every species. However, GAM-Tweedie and hurdle models performed well overall and may be useful for studies of other benthic marine invertebrates.

scholarly journals Spatial variability of Chondrichthyes in the northern Mediterranean

2020 ◽  
Vol 83 (S1) ◽  
pp. 81 ◽  
Author(s):  
Maria C. Follesa ◽  
Martina F. Marongiu ◽  
Walter Zupa ◽  
Andrea Bellodi ◽  
Alessandro Cau ◽  
...  
Keyword(s):  
Continental Shelf ◽  
Generalized Additive Models ◽  
Regional Scale ◽  
Additive Models ◽  
Environmental Drivers ◽  
Shark Species ◽  
Fishing Pressure ◽  
The Mediterranean ◽  
High Level ◽  
Management And Conservation

Thanks to the availability of the MEDITS survey data, a standardized picture of the occurrence and abundance of demersal Chondrichthyes in the northern Mediterranean has been obtained. During the spring-summer period between 2012 and 2015, 41 Chondrichthyes, including 18 sharks (5 orders and 11 families), 22 batoids (3 orders and 4 families) and 1 chimaera, were detected from several geographical sub-areas (GSAs) established by the General Fisheries Commission for the Mediterranean. Batoids had a preferential distribution on the continental shelf (10-200 m depth), while shark species were more frequent on the slope (200-800 m depth). Only three species, the Carcharhiniformes Galeus melastomus and Scyliorhinus canicula and the Torpediniformes Torpedo marmorata were caught in all GSAs studied. On the continental shelf, the Rajidae family was the most abundant, being represented in primis by Raja clavata and then by R. miraletus, R. polystigma and R. asterias. The slope was characterized by the prevalence of G. melastomus in all GSAs, followed by S. canicula, E. spinax and Squalus blainville. Areas under higher fishing pressure, such as the Adriatic Sea and the Spanish coast (with the exception of the Balearic Islands), show a low abundance of chondrichthyans, but other areas with a high level of fishing pressure, such as southwestern Sicily, show a high abundance, suggesting that other environmental drivers work together with fishing pressure to shape their distribution. Results of generalized additive models highlighted that depth is one of the most important environmental drivers influencing the distribution of both batoid and shark species, although temperature also showed a significant influence on their distribution. The approach explored in this work shows the possibility of producing maps modelling the distribution of demersal chondrichthyans in the Mediterranean that are useful for the management and conservation of these species at a regional scale. However, because of the vulnerability of these species to fishing exploitation, fishing pressure should be further incorporated in these models in addition to these environmental drivers.

scholarly journals Distinctive trajectories of COVID-19 epidemic by age and gender: a retrospective modeling of the epidemic in South Korea

2020 ◽  
Author(s):  
Xinhua Yu ◽  
Jiasong Duan ◽  
Yu Jiang ◽  
Hongmei Zhang
Keyword(s):  
South Korea ◽  
Elderly People ◽  
Negative Binomial ◽  
Generalized Additive Models ◽  
Age Groups ◽  
Additive Models ◽  
Age And Gender ◽  
Epidemic Dynamics ◽  
And Gender ◽  
Gender Groups

AbstractObjectivesElderly people had suffered disproportional burden of COVID-19. We hypothesized that males and females in different age groups might have different epidemic trajectories.MethodsUsing publicly available data from South Korea, daily new COVID-19 cases were fitted with generalized additive models, assuming Poisson and negative binomial distributions. Epidemic dynamics by age and gender groups were explored with interactions between smoothed time terms and age and gender.ResultsA negative binomial distribution fitted the daily case counts best. Interaction between the dynamic patterns of daily new cases and age groups was statistically significant (p<0.001), but not with gender group. People aged 20-39 years led the epidemic processes in the society with two peaks: one major peak around March 1 and a smaller peak around April 7, 2020. The epidemic process among people aged 60 or above was trailing behind that of younger people with smaller magnitude. After March 15, there was a consistent decline of daily new cases among elderly people, despite large fluctuations of case counts among young adults.ConclusionsAlthough young people drove the COVID-19 epidemic in the whole society with multiple rebounds, elderly people could still be protected from virus infection after the peak of epidemic.

Estimation of seal pup production from aerial surveys using generalized additive models

2009 ◽  
Vol 66 (5) ◽  
pp. 847-858 ◽  
Author(s):  
Arnt-Børre Salberg ◽  
Tor Arne Øigård ◽  
Garry B. Stenson ◽  
Tore Haug ◽  
Kjell T. Nilssen
Keyword(s):  
Standard Error ◽  
Negative Binomial ◽  
Generalized Additive Models ◽  
Additive Models ◽  
Aerial Photographs ◽  
Closed Form Expression ◽  
Error Estimator ◽  
Fine Grid ◽  
Aerial Surveys ◽  
Error Bias

In this paper, we estimate the pup production of harp seals ( Pagophilus groenlandicus ) using generalized additive models (GAMs) based on thin-plate regression splines. The spatial distribution of seal pups in a patch is modelled using GAMs, and the pup production is estimated by numerically integrating the model over a fine grid area of the patch. Closed form expression for estimation of the the standard error of the pup production estimate is derived. The estimators are applied to simulated seal populations to investigate their properties. The results show that the proposed pup production estimator is comparable with the conventional pup production estimator. However, the bias of the standard error estimator of the proposed method is much lower than the bias of the conventional standard error estimator. The decrease of standard error bias results in a considerable reduction of the coefficient of variation estimate using the proposed GAM-based method. The proposed method is also applied to real survey data of harp seals obtained from aerial surveys in the Greenland Sea pack ice in 2002. We show that the number of pups counted from aerial photographs possess a good fit to the negative binomial distribution when a logarithmic link function is applied. The approach described here is applicable to many situations where georeferenced counts or measurements are available.

scholarly journals Testing the ability of species distribution models to infer variable importance

2019 ◽  
Author(s):  
Adam B. Smith ◽  
Maria J. Santos
Keyword(s):  
Predictive Accuracy ◽  
Permutation Test ◽  
Generalized Additive Models ◽  
Simulated Data ◽  
Variable Importance ◽  
Additive Models ◽  
Environmental Data ◽  
Boosted Regression Trees ◽  
Distribution Models ◽  
Model Algorithm

AbstractModels of species’ distributions and niches are frequently used to infer the importance of range- and niche-defining variables. However, the degree to which these models can reliably identify important variables and quantify their influence remains unknown. Here we use a series of simulations to explore how well models can 1) discriminate between variables with different influence and 2) calibrate the magnitude of influence relative to an “omniscient” model. To quantify variable importance, we trained generalized additive models (GAMs), Maxent, and boosted regression trees (BRTs) on simulated data and tested their sensitivity to permutations in each predictor. Importance was inferred by calculating the correlation between permuted and unpermuted predictions, and by comparing predictive accuracy of permuted and unpermuted predictions using AUC and the Continuous Boyce Index. In scenarios with one influential and one uninfluential variable, models were unable to discriminate reliably between variables in conditions that are normally challenging for generating accurate predictions: training occurrences <8-64; prevalence >0.5; small spatial extent; environmental data with coarse resolution when spatial autocorrelation is low; and correlation between environmental variables where |r| >0.7. When two variables influenced the distribution equally, importance was underestimated when species had narrow or intermediate niche breadth. Interactions between variables in how they shaped the niche did not affect inferences about their importance. When variables acted unequally, the effect of the stronger variable was overestimated. GAMs and Maxent discriminated between variables more reliably than BRTs, but no algorithm was consistently well-calibrated vis-à-vis the omniscient model. Algorithm-specific measures of importance like Maxent’s change-in-gain metric were less robust than the permutation test. Overall, high predictive accuracy did not connote robust inferential capacity. As a result, requirements for reliably measuring variable importance are likely more stringent than for creating models with high predictive accuracy.

scholarly journals Blowing in the wind? The effect of weather on the intensity and spatial distribution of crime

2019 ◽  
Author(s):  
Rannveig Hart ◽  
Willy Pedersen ◽  
Torbjørn Skardhamar
Keyword(s):  
Spatial Distribution ◽  
Minimum Temperature ◽  
Negative Binomial ◽  
Generalized Additive Models ◽  
Spatial Models ◽  
Weather Conditions ◽  
Additive Models ◽  
Extensive Literature ◽  
Weather Effects ◽  
Count Models

Despite an extensive literature on weather and crime, the magnitude of weather effects on crime and their implications for practical policing remain unclear. Similarly, the effects of weather on the location of crime have barely been explored empirically. We investigated how weather influences the intensity and spatial distribution of crime in Oslo, the capital of Norway. Geocoded locations of criminal offences were combined with data on temperature, wind, and rain. We used negative binomial count models to assess the effect of weather on the intensity of crime and generalized additive models (GAMs) to test for spatial variations. The intensity and spatial distribution of crime were not very sensitive to weather in Oslo. The largest effect was for drug crimes, for which maximum relative to minimum temperature was related to a single incident increase every six days. No effects were found for dislocation in the spatial models. In Oslo, Norway, weather conditions are of little importance for practical policing. The effects of weather on the intensity of crime are miniscule, and effects on the location of crime even smaller.

scholarly journals Association between COVID-19, mobility and environment in Brazilian capitals

2021 ◽  
Author(s):  
Sergio Ibarra ◽  
Edmilson Dias de Freitas
Keyword(s):  
Air Pollution ◽  
Negative Binomial ◽  
Generalized Additive Models ◽  
Additive Models ◽  
Metropolitan Region ◽  
High Dispersion ◽  
Stat Assoc ◽  
Mobility Index ◽  
Belo Horizonte ◽  
Meteorology And Air Pollution

&lt;p&gt;Brazilis is the country with highest number of COVID-19 cases and deaths in the sotuhern hsmisphere, third behind India and&amp;#160; U.S globally. Some studies have analized the relationship between mobility, meteorology and air pollution, finding that staying out-of-home increases cases about 5 days and deaths about two weeks after the exposure. (Ibarra-Espinosa, et al., 2021). In this work we will extend the analyses presented by Ibarra-Espinosa et al., (2021), by including more Brazilian cities. Specifically, the metropolitan region of Rio de Janeiro si cosndierer a MEgacity and monitors meteorology and air pollution, necessary to the analyses. The metropolitan regions of Porto Alegre, Belo horizonte and Curutiba as well. The method consists in applying a semiparametric model (Dominici et al, 2004), but in this case, controllying all the environmental factors and their interactions and the parameter consists in the mobility alone. We will compare local mobility index, as Google Residential Mobility Index (RMI), as done by Ibarra-Espinosa et al., (2021). Due to the high dispersion of the data, OVID-19 will be modeled by quasi-poisson and negative binomial distribution, with generalzied additive models (Wood., 2017; Zeileis et al., 2008; R Core Team, 2021).&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;Ibarra-Espinosa, S., de Freitas, E.D., Ropkins, K., Dominici, F., Rehbein, A., 2021. Association between COVID-19, mobility and environment in S&amp;#227;o Paulo, Brazil. medRxiv. https://doi.org/10.1101/2021.02.08.21250113&lt;/p&gt;&lt;p&gt;Dominici F, McDermott A, Hastie TJ. 2004. Improved semiparametric time series models of air pollution and mortality. J Am Stat Assoc 99: 938&amp;#8211;948.&lt;/p&gt;&lt;p&gt;&lt;span&gt;R Core Team. 2021. R: A Language and Environment for Statistical Computing.&lt;/span&gt;&lt;/p&gt;&lt;p&gt;Wood S. 2017. &lt;em&gt;Generalized Additive Models: An Introduction with R&lt;/em&gt;. Chapman and Hall/CRC.&lt;/p&gt;&lt;p&gt;&lt;span&gt;Zeileis A, Kleiber C, Jackman S. 2008. &lt;/span&gt;Regression Models for Count Data in R. J Stat Software, Artic 27:1&amp;#8211;25; doi:10.18637/jss.v027.i08.&lt;/p&gt;

scholarly journals A CASE STUDY ON ANIMAL BEHAVIOR ANALYSIS USING GAMLSS

2021 ◽  
Vol 39 (3) ◽  
Author(s):  
Lineu Alberto Cavazani de FREITAS ◽  
Cesar Augusto TACONELI ◽  
José Luiz Padilha da SILVA ◽  
Priscilla Regina TAMIOSO ◽  
Carla Forte Maiolino MOLENTO
Keyword(s):  
Animal Behavior ◽  
Beta Distribution ◽  
Count Data ◽  
Negative Binomial ◽  
Generalized Additive Models ◽  
Random Variable ◽  
Additive Models ◽  
Genetic Lineages ◽  
Flexible Framework ◽  
Social Separation

Animal behavior studies usually produce large amounts of data and a wide variety of data structures, including nonlinear relationships, interaction effects, nonconstant variance, correlated measures, overdispersion, and zero inflation, among others. We aimed to explore here the potential of generalized additive models for location, scale and shape (GAMLSS) in analyzing data from animal behavior studies. Data from 20 Romane ewes from two genetic lineages submitted to brushing by a familiar observer were analyzed. Behavioral responses through ear posture changes, a count random variable, and the proportion of time to perform the horizontal ear posture, a continuous random variable on the interval (0,1), with non-null probabilities in zero and one, were analyzed. The Poisson, negative binomial, and their zero-inflated and zero-adjusted extensions models were considered for the count data, whereas the beta distribution and its inflated versions were evaluated for the proportions. Random effects were also included to consider the multilevel structure of the experiment. The zero adjusted negative binomial model has better fitted the count data, whereas the inflated beta distribution performed the best for the proportions. Both models allowed us to properly assess the effects of social separation, brushing, and genetic lineages on sheep behavioral. We may conclude that GAMLSS is a flexible framework to analyze animal behavior data.

Sign in / Sign up

Export Citation Format

Share Document