Role of range and precision of the independent variable in regression of data

Brauner, Neima; Shacham, Mordechai

doi:10.1002/aic.690440311

Cited by 50 publications

(33 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Collinearity in the predictors is another crucial problem associated with stepwise model selection (Brauner and Shacham, 1998). A common observation is that two highly correlated predictors can both appear non-significant even though each would explain a significant proportion of the deviance if considered individually.…”

Section: Variable Selection Methods and Diagnosticsmentioning

confidence: 99%

“…A common observation is that two highly correlated predictors can both appear non-significant even though each would explain a significant proportion of the deviance if considered individually. Various approaches can be used to detect harmful collinearity, such as condition number and variance inflation factor (VIF; Brauner and Shacham, 1998), although with careful model selection or regularization through application of ridge or lasso techniques collinearity becomes less of an issue.…”

Section: Variable Selection Methods and Diagnosticsmentioning

confidence: 99%

See 1 more Smart Citation

Generalized linear and generalized additive models in studies of species distributions: setting the scene

Guisan

Edwards

Hastie

2002

Ecological Modelling

1,887

1,188

View full text Add to dashboard Cite

Section: Variable Selection Methods and Diagnosticsmentioning

confidence: 99%

Section: Variable Selection Methods and Diagnosticsmentioning

confidence: 99%

Generalized linear and generalized additive models in studies of species distributions: setting the scene

Guisan

Edwards

Hastie

2002

Ecological Modelling

1,887

1,188

View full text Add to dashboard Cite

“…Since standard deviations and square of the standard deviations of the explanatory variables strongly depend on the segment and pixel size (varying crown diameter) their usage might be critical and not directly transferable to datasets from other sensors. Furthermore, according to [83] problems may also be related to redundant predictors (which is possible) and the one-at-a-time nature of adding/dropping variables.…”

Section: Extraction Of Explanatory Variablesmentioning

confidence: 99%

Evaluating the Potential of WorldView-2 Data to Classify Tree Species and Different Levels of Ash Mortality

et al. 2014

View full text Add to dashboard Cite

Forest disturbances in central Europe caused by fungal pests may result in widespread tree mortality. To assess the state of health and to detect disturbances of entire forest ecosystems, up-to-date knowledge of the tree species diversity is essential. The German state Mecklenburg-Vorpommern is severely affected by ash (Fraxinus excelsior) dieback caused by the fungal pathogen Hymenoscyphus pseudoalbidus. In this study, species diversity and the magnitude of ash mortality was assessed by classifying seven different tree species and multiple levels of damaged ash. The study is based on a multispectral WorldView-2 (WV-2) scene and uses object-based supervised classification methods based on multinomial logistic regressions. Besides the original multispectral image, a set of remote sensing indices (RSI) was derived, which significantly improved the accuracies of classifying different levels of damaged ash but only slightly improved tree species classification. The large number of features was reduced by three approaches, of which the linear discriminant analysis (LDA) clearly outperformed the more commonly used principal component analysis (PCA) and a stepwise selection method. Promising overall accuracies (83%) for classifying seven tree species and (73%) for classifying four different levels of damaged ash were obtained. Detailed tree damage and tree species maps were visually inspected using aerial images. The results are of high relevance for forest OPEN ACCESSRemote Sens. 2014, 6 4516 managers to plan appropriate cutting and reforestation measures to decrease ash dieback over entire regions.

show abstract

“…The model building process consists of the following steps: 1) selection of the underlying distribution of the response (see Section 2.2.2 for more details); 2) selection of predictors building independent models for each covariant deleting insignificant effects in the final model; 3) selection between correlated predictors through the Pearson correlation coefficient (threshold value: ρ=|0.6|) to avoid problems of collinearity (Brauner and Shacham 1998) using the covariant with the most explanatory potential; and 4) analysis of residuals diagnostics. All analyses were performed in R3.0.1 (mgcvRpackage: Wood 2006).…”

Section: Model Constructionmentioning

confidence: 99%

Analysis and standardization of landings per unit effort of red shrimp <em>Aristeus antennatus</em> from the trawl fleet of Barcelona (NW Mediterranean)

Mamouridis¹,

Maynou²,

Aneiros³

2014

Sci. Mar.

View full text Add to dashboard Cite

Summary:Monthly landings and effort data from the Barcelona trawl fleet (NW Mediterranean) were selected to analyse and standardize the landings per unit effort (LPUE) of the red shrimp (Aristeus antennatus) using generalized additive models. The dataset covers a span of 15 years (1994)(1995)(1996)(1997)(1998)(1999)(2000)(2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008) and consists of a broad spectrum of predictors: fleet-dependent (e.g. number of trips performed by vessels and their technical characteristics, such as the gross registered tonnage), temporal (inter-and intra-annual variability), environmental (North Atlantic Oscillation [NAO] index) and economic (red shrimp and fuel prices) variables. All predictors individually have an impact on LPUE, though some of them lose their predictive power when considered jointly. That is the case of the NAO index. Our results show that six variables from the whole set can be incorporated into a global model with a total explained deviance (ED) of 43%. We found that the most important variables were effort-related predictors (trips, tonnage, and groups) with a total ED of 20.58%, followed by temporal variables, with an ED of 13.12%, and finally the red shrimp price as an economic predictor with an ED of 9.30%. Taken individually, the main contributing variable was the inter-annual variability (ED=12.40%). This high ED value suggests that many factors correlated with inter-annual variability, such as environmental factors (the NAO in specific years) and fuel price, could in turn affect LPUE variability. The standardized LPUE index with the effort variability removed was found to be similar to the fishery-independent abundance index derived from the MEDITS programme.Keywords: LPUE; standardized LPUE; Aristeus antennatus; generalized additive models; NW Mediterranean; deep-water fisheries.Análisis y estandarización de los desembarcos por unidad de esfuerzo de la gamba roja Aristeus antennatus por la flota de arrastre de Barcelona (Mediterráneo noroccidental)Resumen: Se llevó a cabo un análisis del volumen de desembarcos por unidad de esfuerzo (LPUE) de la gamba roja (Aristeus antennatus) de la flota de arrastre en el puerto de Barcelona (Mediterráneo noroccidental) mediante modelos aditivos generalizados (GAM). El conjunto de datos cubre un periodo de 15 años (1994)(1995)(1996)(1997)(1998)(1999)(2000)(2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008) y consiste en un amplio espectro de predictores: variables dependientes de la flota (el número de mareas efectuadas por cada embarcación y las características técnicas de estas, como el tonelaje bruto), temporales (variabilidad inter-e intra-anual), ambientales (índice de Ocilación del Atlántico Norte [NAO]) y económicas (precio de la gamba roja y precio del combustible). Todos los predictores a nivel individual tienen impacto sobre LPUE, pero algunos de ellos pierden su poder explicativo cuando se considéran conjuntamente con otros, como en el caso del índice NAO. Nuestros resultados muestran que seis variables del conjunto pue...

show abstract

Role of range and precision of the independent variable in regression of data

Abstract: Regression of the experimental data of one independent variable, y us. a linear combination of functions of an independent variable of the form y

Cited by 50 publications

References 11 publications

Generalized linear and generalized additive models in studies of species distributions: setting the scene

Generalized linear and generalized additive models in studies of species distributions: setting the scene

Evaluating the Potential of WorldView-2 Data to Classify Tree Species and Different Levels of Ash Mortality

Analysis and standardization of landings per unit effort of red shrimp <em>Aristeus antennatus</em> from the trawl fleet of Barcelona (NW Mediterranean)

Contact Info

Product

Resources

About