Residuals and Diagnostics for Binary and Ordinal Regression Models: An Introduction to the sure Package

Greenwell, Brandon; McCarthy, Andrew J.; Boehmke, Bradley C.; Liu, Dungang

doi:10.32614/rj-2018-004

Cited by 146 publications

(153 citation statements)

References 6 publications

Supporting

Mentioning

130

Contrasting

Order By: Relevance

“…Tree ensembles were also developed by gradient boosting machines (gbm, gbm‐package; Greenwell, Boehmke, Cunningham & GBM Developers, ). In gbms numerous classification and regression trees are formulated, and for each tree a random subset of the data is used.…”

Section: Methodsmentioning

confidence: 99%

Factors controlling the variation in organic carbon stocks in agricultural soils of Germany

Vos

Don

Hobley

et al. 2019

European J Soil Science

View full text Add to dashboard Cite

This study gives an overview of soil organic carbon (SOC) stocks in Germany's agricultural soils, and quantifies and explains the influence of explanatory variables such as land use and management, soil type and climate. Over 2500 agricultural sites were sampled and their SOC stocks determined, together with other soil properties. Machine‐learning algorithms were used to identify the most important variables. Land use, land‐use history, clay content and electrical conductivity were the main predictors in the topsoil, whereas bedrock material, relief and electrical conductivity governed the variation in subsoil carbon stocks. We found that 32% of all soil profiles were anthropogenically transformed. The influence of climate variables was surprisingly small, whereas site variables, in particular in the subsoil, explained a large proportion of the variation in soil carbon. The understanding of SOC dynamics at the regional scale requires a thorough description of the spatial variation in soil properties. The effect of agronomic management on SOC stocks was important near the soil surface, but was mainly attributable to land use (grassland or arable and not to other management factors. Highlights Factors affecting spatial variation of soil organic carbon stocks are largely unknown. More than 200 possible predictors for this variation were assessed for over 2500 sites. Land use (history), texture, electrical conductivity, bedrock and relief were main controlling factors of carbon stock variation. Aggregation and carbon storage capacity of soil determine much of the spatial variation in carbon stocks.

show abstract

Section: Methodsmentioning

confidence: 99%

Factors controlling the variation in organic carbon stocks in agricultural soils of Germany

Vos

Don

Hobley

et al. 2019

European J Soil Science

View full text Add to dashboard Cite

show abstract

“…We averaged parameter estimates in all models up to a cumulative weight of 0.95. We explored model fit and diagnostics based on surrogate residuals using the R package “sure” (Greenwell, McCarthy, Boehmke, & Liu, ).…”

Section: Methodsmentioning

confidence: 99%

Perspectives of traditional Himalayan communities on fostering coexistence with Himalayan wolf and snow leopard

Kusi

Sillero‐Zubiri

Macdonald

et al. 2019

Conservat Sci and Prac

View full text Add to dashboard Cite

The Himalayan wolf Canis sp. and snow leopard Panthera uncia are found in the Nepalese Himalayas where conservation efforts target the latter but not the former. We conducted semistructured questionnaire surveys of 71 residents in upper Humla, upper Dolpa, and Kanchenjunga Conservation Area (KCA) during 2014–2016 to understand people's knowledge, perceptions, attitudes and interactions with these two carnivores. We fitted a cumulative link mixed model to predict Likert scale ordinal responses from a series of Generalized Linear Mixed Models. Overall, attitudes were more positive toward snow leopards than wolves. Livestock depredation was the main predictor of the general negative attitude toward wolves (Estimate = −1.30873; p = .029866) but there was no evidence for an effect for snow leopards (Estimate = −0.3640; p = .631446). Agropastoralists had more negative attitudes than respondents with other occupations toward both carnivores and men had more positive attitudes than women. Among our study areas, respondents in the community‐owned KCA had the most positive attitudes. Our findings illustrate the need to reduce human–carnivore conflict through a combined approach of education, mitigation, and economic cost‐sharing with respectful engagement of local communities. Specifically, to encourage more villagers to participate in livestock insurance schemes, they should be improved by including all large carnivores and adjusting compensation to the market value of a young replacement of the depredated livestock type. Carnivore conservation interventions should target the whole predator guild to achieve long‐term success and to protect the Himalayan ecosystem at large.

show abstract

“…Models were built in R, Ver. 3.5.1, using the gbm package and additional code (Elith et al ; Greenwell et al ).…”

Section: Methodsmentioning

confidence: 99%

Detecting Amphibians in Agricultural Landscapes Using Environmental DNA Reveals the Importance of Wetland Condition

Ruso

Morrissey

Hogan

et al. 2019

Enviro Toxic and Chemistry

View full text Add to dashboard Cite

Amphibians are declining worldwide, in part because of large‐scale degradation of habitat from agriculture and pervasive pathogens. Yet a common North American amphibian, the wood frog (Lithobates sylvaticus), ranges widely and persists in agricultural landscapes. Conventional survey techniques rely on visual encounters and dip‐netting efforts, but detectability limits the ability to test for the effects of environmental variables on amphibian habitat suitability. We used environmental DNA to determine the presence of wood frogs and an amphibian pathogen (ranavirus) in Prairie Pothole wetlands and investigated the effects of 32 water quality, wetland habitat, and landscape‐level variables on frog presence at sites representing different degrees of agricultural intensity. Several wetland variables influenced wood frog presence, the most influential being those associated with wetland productivity (i.e., nutrients), vegetation buffer width, and proportion of the surrounding landscape that is comprised of other water bodies. Wood frog presence was positively associated with higher dissolved phosphorus (>0.4 mg/L), moderate dissolved nitrogen (0.1–0.2 mg/L), lower chlorophyll a (≤15 µg/L), wider vegetation buffers (≥10 m), and more water on the landscape (≥0.25). These results highlight the effects of environmental factors at multiple scales on the presence of amphibians in this highly modified landscape—namely the importance of maintaining wetland water quality, vegetation buffers, and surrounding habitat heterogeneity. Environ Toxicol Chem 2019;38:2750–2763. © 2019 SETAC

show abstract

Residuals and Diagnostics for Binary and Ordinal Regression Models: An Introduction to the sure Package

Cited by 146 publications

References 6 publications

Factors controlling the variation in organic carbon stocks in agricultural soils of Germany

Factors controlling the variation in organic carbon stocks in agricultural soils of Germany

Perspectives of traditional Himalayan communities on fostering coexistence with Himalayan wolf and snow leopard

Detecting Amphibians in Agricultural Landscapes Using Environmental DNA Reveals the Importance of Wetland Condition

Contact Info

Product

Resources

About