scholarly journals Ambient Sulfate Trends and the Influence of Meteorology

2005 ◽  
Vol 44 (11) ◽  
pp. 1745-1760 ◽  
Author(s):  
Stephen F. Mueller
Keyword(s):  
Statistical Models ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Total Sulfur ◽  
Eastern United States ◽  
Sulfur Species ◽  
Sulfate Sulfur ◽  
Average Change ◽  
Meteorological Influences ◽  
Local Deposition

Abstract Data on atmospheric levels of sulfur dioxide (SO2) and sulfate were examined to quantify changes since 1989. Changes in sulfur species were adjusted to account for meteorological variability. Adjustments were made using meteorological variables expressed in terms of their principal components that were used as predictors in statistical models. Several models were tested. A generalized additive model (GAM)—based in part on nonparametric, locally smoothed predictor functions—computed the greatest association between sulfate and the meteorological predictors. Sulfate trends estimated after a GAM-based adjustment for weather-related influences were found to be primarily downward across the eastern United States by as much as 6.7% per year (average of −2.6% per year), but large spatial variability was noted. The most conspicuous characteristic in the trends was over portions of the Appalachian Mountains where very small (average = −1.6% per year) and often insignificant sulfate changes were found. The Appalachian region also experienced a tendency, after removing meteorological influences, for increases in the ratio RS of sulfate sulfur to total sulfur. Before 1991, this ratio averaged 0.33 across all sites. Appalachian increases in RS were equivalent to 0.07 during 1989–2001 (significant for most sites at the 0.05 level), or nearly 2 times the average change at the other sites. This suggests that conditions over the Appalachians became notably more efficient at oxidizing SO2 into sulfate. Alternatively, subtle changes in local deposition patterns occurred, preferentially in and near mountainous monitoring sites, that changed the SO2–sulfate balance.

scholarly journals Modelling Cyclists’ Multi-Exposure to Air and Noise Pollution with Low-Cost Sensors—The Case of Paris

Atmosphere ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 422
Author(s):  
Jérémy Gelb ◽  
Philippe Apparicio
Keyword(s):  
Statistical Models ◽  
Noise Exposure ◽  
Generalized Additive Model ◽  
Low Cost ◽  
Additive Model ◽  
Noise Pollution ◽  
Ventilation Rate ◽  
Mixed Effects ◽  
Mobile Data ◽  
Mobile Data Collection

Cyclists are particularly exposed to air and noise pollution because of their higher ventilation rate and their proximity to traffic. However, few studies have investigated their multi-exposure and have taken into account its real complexity in building statistical models (nonlinearity, pseudo replication, autocorrelation, etc.). We propose here to model cyclists’ exposure to air and noise pollution simultaneously in Paris (France). Specifically, the purpose of this study is to develop a methodology based on an extensive mobile data collection using low-cost sensors to determine which factors of the urban micro-scale environment contribute to cyclists’ multi-exposure and to what extent. To this end, we developed a conceptual framework to define cyclists’ multi-exposure and applied it to a multivariate generalized additive model with mixed effects and temporal autocorrelation. The results show that it is possible to reduce cyclists’ multi-exposure by adapting the planning and development practices of cycling infrastructure, and that this reduction can be substantial for noise exposure.

GAMLSS for high-variability data: an application to liver fibrosis case

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Andrea Marletta ◽  
Mariangela Sciandra
Keyword(s):  
Risk Factors ◽  
Liver Fibrosis ◽  
Statistical Models ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Finite Mixture Model ◽  
High Variability ◽  
Finite Mixture ◽  
Potential Risk Factors ◽  
Variability Data

AbstractThis article aims to provide rigorous and convenient statistical models for dealing with high-variability phenomena. The presence of discrepance in variance represents a substantial issue when it is not possible to reduce variability before analysing the data, leading to the possibility to estimate an inadequate model. In this paper, the application of Generalized Additive Model for Location, Scale and Shape (GAMLSS) and the use of finite mixture model for GAMLSS will be proposed as a solution to the problem of overdispersion. An application to Liver fibrosis data is illustrated in order to identify potential risk factors for patients, which could determine the presence of the disease but also its levels of severity.

scholarly journals CLIMATE-DRIVEN STATISTICAL MODELS AS EFECTIVE PREDICTIONS OF LOCAL DENGUE INDICENCE IN COSTA RICA: A GENERALIZED ADDITIVE MODEL AND RANDOM FOREST APPROACH

2019 ◽  
Vol 27 (1) ◽  
pp. 1-21
Author(s):  
PAOLA VÁSQUEZ ◽  
ANTONIO LORÍA ◽  
FABIO SÁNCHEZ ◽  
LUIS ALBERTO BARBOZA
Keyword(s):  
Public Health ◽  
Relative Risk ◽  
Costa Rica ◽  
Random Forest ◽  
Prediction Model ◽  
Statistical Models ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Climate Data ◽  
Tropical Country

Climate has been an important factor in shaping the distribution and incidence of dengue cases in tropical and subtropical countries. In Costa Rica, a tropical country with distinctive micro-climates, dengue has been endemic since its introduction in 1993, inflicting substantial economic, social, and public health repercussions. Using the number of dengue reported cases and climate data from 2007-2017, we fitted a prediction model applying a Generalized Additive Model (GAM) and Random Forest (RF) approach, which allowed us to retrospectively predict the relative risk of dengue in five climatological diverse municipalities around the country.

scholarly journals A Simulation Study to Evaluate Survey Designs and Assessment Models for Estimation of Dungeness Crab (Cancer magister) Softshell Periods

2016 ◽  
Vol 9 (1) ◽  
pp. 57-74
Author(s):  
Zane Zhang ◽  
Jason S. Dunham
Keyword(s):  
Data Collection ◽  
Hierarchical Model ◽  
Statistical Models ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Quadratic Function ◽  
Dungeness Crab ◽  
Catch Per Unit Effort ◽  
Unit Effort ◽  
Survey Designs

Softshell Dungeness Crabs have inferior meat quality and are vulnerable to handling by harvesters; therefore, knowing when softshell periods occur is important for managing Dungeness Crab fisheries. A computer simulation was used to study the effectiveness of several survey designs and statistical models for estimating softshell periods which normally would be construed from crab shell condition data obtained from trap surveys. Survey designs varied in the number of years of data collection (1, 3, 5 or 10 years) and by the number and arrangement of sampling events per year. Three statistical models, including standardized catch-per-unit-effort (SCPUE), hierarchical, and generalized additive, were tested using catch-per-unit-effort data (CPUEs) or CPUE- transformed data. CPUEs were standardised by dividing CPUE estimates by the maximum CPUE obtained in the sample year, and then transformed using the complementary log-log function. In the hierarchical model, CPUEs were modelled using a lognormal distribution, assuming the expected logarithms of CPUEs are a quadratic function of days plus a random normal error. CPUE-transformed data were modelled using a normal distribution, assuming expected values are a quadratic function of days in the SCPUE model or a spline smooth function of days in the generalized additive model. Results suggest the best survey design requires a relatively high number (6 or 11) of sampling events during several key consecutive months which contain the softshell period, and fewer sampling events during those months when softshell crab abundance is low. A minimum 3 years of data collection is required to produce reliable outputs. The hierarchical model performs best, slightly better than the SCPUE model. Use of the generalized additive model is not recommended.

scholarly journals Assessing the Performance of Random Forests for Modeling Claim Severity in Collision Car Insurance

Risks ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 53
Author(s):  
Yves Staudt ◽  
Joël Wagner
Keyword(s):  
Random Forests ◽  
Goodness Of Fit ◽  
Generalized Additive Model ◽  
Mean Squared Error ◽  
Additive Model ◽  
Continuous Variables ◽  
Insurance Portfolio ◽  
Normal Transformation ◽  
Car Insurance ◽  
Log Normal

For calculating non-life insurance premiums, actuaries traditionally rely on separate severity and frequency models using covariates to explain the claims loss exposure. In this paper, we focus on the claim severity. First, we build two reference models, a generalized linear model and a generalized additive model, relying on a log-normal distribution of the severity and including the most significant factors. Thereby, we relate the continuous variables to the response in a nonlinear way. In the second step, we tune two random forest models, one for the claim severity and one for the log-transformed claim severity, where the latter requires a transformation of the predicted results. We compare the prediction performance of the different models using the relative error, the root mean squared error and the goodness-of-lift statistics in combination with goodness-of-fit statistics. In our application, we rely on a dataset of a Swiss collision insurance portfolio covering the loss exposure of the period from 2011 to 2015, and including observations from 81 309 settled claims with a total amount of CHF 184 mio. In the analysis, we use the data from 2011 to 2014 for training and from 2015 for testing. Our results indicate that the use of a log-normal transformation of the severity is not leading to performance gains with random forests. However, random forests with a log-normal transformation are the favorite choice for explaining right-skewed claims. Finally, when considering all indicators, we conclude that the generalized additive model has the best overall performance.

scholarly journals Generalized additive model with embedded variable selection for bankruptcy prediction: Prediction versus interpretation

2019 ◽  
Vol 7 (1) ◽  
pp. 1597956
Author(s):  
Carlos Valencia ◽  
Sergio Cabrales ◽  
Laura Garcia ◽  
Juan Ramirez ◽  
Diego Calderona ◽  
...  
Keyword(s):  
Variable Selection ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Bankruptcy Prediction ◽  
Selection For
Sign in / Sign up

Export Citation Format

Share Document