Estimation of shape constrained additive models with missing response at random

Environmental conditions can have spatially complex effects on the dynamics of marine fish stocks that change across life-history stages. Yet the potential for non-stationary environmental effects across multiple dimensions, e.g. space and ontogeny, are rarely considered. In this study, we examined the evidence for spatial and ontogenetic non-stationary temperature effects on Pacific hake Merluccius productus biomass along the west coast of North America. Specifically, we used Bayesian additive models to estimate the effects of temperature on Pacific hake biomass distribution and whether the effects change across space or life-history stage. We found latitudinal differences in the effects of temperature on mature Pacific hake distribution (i.e. age 3 and older); warmer than average subsurface temperatures were associated with higher biomass north of Vancouver Island, but lower biomass offshore of Washington and southern Vancouver Island. In contrast, immature Pacific hake distribution (i.e. age 2) was better explained by a nonlinear temperature effect; cooler than average temperatures were associated with higher biomass coastwide. Together, our results suggest that Pacific hake distribution is driven by interactions between age composition and environmental conditions and highlight the importance of accounting for varying environmental effects across multiple dimensions.

Download Full-text

Association of the CD14 C159T and the Toll-like receptor 4 Asp299Gly polymorphisms with various phenotypes of asthma in adults from Crimea

Allergy and Asthma Proceedings ◽

10.2500/aap.2019.40.190007 ◽

2020 ◽

Vol 41 (2) ◽

pp. 134-140

Author(s):

Yuriy Bisyuk ◽

Andrew Dubovyi ◽

Ilona DuBuske ◽

Viktor Litus ◽

Lawrence M. DuBuske

Keyword(s):

Late Onset ◽

Adult Population ◽

Additive Models ◽

Atopic Asthma ◽

Control Group ◽

Nucleotide Polymorphisms ◽

Toll Like Receptor ◽

Toll Like Receptor 4 ◽

Single Nucleotide ◽

Gender And Age

Background: This study assessed gene polymorphisms of the CD14 receptor (C-159T) and Toll-like receptor 4 (Asp299Gly) in a patient population in Crimea, Ukraine, stratified by clinical (early versus late onset; frequent versus occasional relapses; fixed versus reversible obstruction) and immunologic (atopic versus nonatopic; eosinophilic; neutrophilic or paucigranulocytic inflammation) subtype. Methods: Two polymorphisms, CD14 C-159T and TLR4 Asp299Gly, were assessed in 331 patients with asthma. The control group included 285 volunteers who were nonatopic. The single nucleotide polymorphisms were studied by using polymerase chain reaction with electrophoretic detection. Results: There were increased odds of asthma development in patients with the Asp299Gly TLR4 mutation compared with the general population underdominant odds ratio (OR) 1.52 [95% confidence interval (CI), 1.00‐2.32] and overdominant (OR 1.55 [95% CI, 1.01‐2.38]) models after adjustment for gender and age. In addition, mutations in this gene decreased the odds of nonatopic asthma in underdominant (OR 0.26 [95% CI, 0.07‐0.93]; p = 0.027), overdominant (OR 0.27 [95% CI, 0.07‐0.96]; p = 0.033), and log-additive models (OR 0.26 [95% CI, 0.07‐0.93]; p = 0.026) compared with the atopic subgroup after adjustment for gender, age, number of exacerbations, and type of airway inflammation. Allele frequencies for CD14 and TLR4 polymorphisms did not show statistical differences between the patients with asthma and the control subjects. Conclusion: CD14 C-159T polymorphisms were not associated with asthma in the adult population in Crimea. TLR4 Asp299Gly polymorphisms were associated with asthma and with decreased odds of nonatopic asthma compared with atopic asthma in the adult population in Crimea.

Download Full-text

Joint Semantic Synthesis and Morphological Analysis of the Derived Word

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00003 ◽

2018 ◽

Vol 6 ◽

pp. 33-48 ◽

Cited By ~ 4

Author(s):

Ryan Cotterell ◽

Hinrich Schütze

Keyword(s):

Neural Networks ◽

Recurrent Neural Networks ◽

Probabilistic Model ◽

Morphological Analysis ◽

Semantic Representation ◽

English Word ◽

Word Formation ◽

Additive Models ◽

Segmentation Accuracy ◽

Morphological Productivity

Much like sentences are composed of words, words themselves are composed of smaller units. For example, the English word questionably can be analyzed as question+ able+ ly. However, this structural decomposition of the word does not directly give us a semantic representation of the word’s meaning. Since morphology obeys the principle of compositionality, the semantics of the word can be systematically derived from the meaning of its parts. In this work, we propose a novel probabilistic model of word formation that captures both the analysis of a word w into its constituent segments and the synthesis of the meaning of w from the meanings of those segments. Our model jointly learns to segment words into morphemes and compose distributional semantic vectors of those morphemes. We experiment with the model on English CELEX data and German DErivBase (Zeller et al., 2013) data. We show that jointly modeling semantics increases both segmentation accuracy and morpheme F1 by between 3% and 5%. Additionally, we investigate different models of vector composition, showing that recurrent neural networks yield an improvement over simple additive models. Finally, we study the degree to which the representations correspond to a linguist’s notion of morphological productivity.

Download Full-text

Predicting Malaria Transmission Dynamics in Dangassa, Mali: A Novel Approach Using Functional Generalized Additive Models

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17176339 ◽

2020 ◽

Vol 17 (17) ◽

pp. 6339

Author(s):

François Freddy Ateba ◽

Manuel Febrero-Bande ◽

Issaka Sagara ◽

Nafomon Sogoba ◽

Mahamoudou Touré ◽

...

Keyword(s):

Wind Speed ◽

Malaria Incidence ◽

Generalized Additive Models ◽

Community Health Center ◽

Additive Model ◽

Additive Models ◽

Functional Regression ◽

Novel Approach ◽

Malaria Incidence Rate ◽

Mean Wind Speed

Mali aims to reach the pre-elimination stage of malaria by the next decade. This study used functional regression models to predict the incidence of malaria as a function of past meteorological patterns to better prevent and to act proactively against impending malaria outbreaks. All data were collected over a five-year period (2012–2017) from 1400 persons who sought treatment at Dangassa’s community health center. Rainfall, temperature, humidity, and wind speed variables were collected. Functional Generalized Spectral Additive Model (FGSAM), Functional Generalized Linear Model (FGLM), and Functional Generalized Kernel Additive Model (FGKAM) were used to predict malaria incidence as a function of the pattern of meteorological indicators over a continuum of the 18 weeks preceding the week of interest. Their respective outcomes were compared in terms of predictive abilities. The results showed that (1) the highest malaria incidence rate occurred in the village 10 to 12 weeks after we observed a pattern of air humidity levels >65%, combined with two or more consecutive rain episodes and a mean wind speed <1.8 m/s; (2) among the three models, the FGLM obtained the best results in terms of prediction; and (3) FGSAM was shown to be a good compromise between FGLM and FGKAM in terms of flexibility and simplicity. The models showed that some meteorological conditions may provide a basis for detection of future outbreaks of malaria. The models developed in this paper are useful for implementing preventive strategies using past meteorological and past malaria incidence.

Download Full-text

Gradient boosting in Markov-switching generalized additive models for location, scale, and shape

Econometrics and Statistics ◽

10.1016/j.ecosta.2021.04.002 ◽

2021 ◽

Author(s):

Timo Adam ◽

Andreas Mayr ◽

Thomas Kneib

Keyword(s):

Generalized Additive Models ◽

Markov Switching ◽

Additive Models ◽

Gradient Boosting

Download Full-text