			Home About us Contact

Ordinal Response Variable (ordinal + response_variable)

Distribution by Scientific Domains

Mathematics and Statistics	50%

Selected Abstracts

Impact of twenty-first century climate change on diadromous fish spread over Europe, North Africa and the Middle East

GLOBAL CHANGE BIOLOGY, Issue 5 2009
G. LASSALLE
Abstract Climate change is expected to drive species ranges towards the poles and to have a strong influence on species distributions. In this study, we focused on diadromous species that are of economical and ecological importance in the whole of Europe. We investigated the potential distribution of all diadromous fish regularly encountered in Europe, North Africa and the Middle East (28 species) under conditions predicted for twenty-first century climate change. To do so, we investigated the 1900 distribution of each species in 196 basins spread across all of Europe, North Africa and the Middle East. Four levels were used to semiquantitatively describe the abundance of species, that is missing, rare, common and abundant. We then selected five variables describing the prevailing climate in the basins, the physical nature of the basins and reflecting historical events known to have affected freshwater fish distribution. Logistic regressions with a four-level ordinal response variable were used to develop species-specific models. These predictive models related the observed distribution of these species in 1900 to the most explanatory combination of variables. Finally, we selected the A2 SRES scenario and the HadCM3 (Hadley Centre Coupled Model version 3) global climate model (GCM) to obtain climate variables (temperature and precipitation) at the end of this century. We used these 2100 variables in our models and obtained maps of climatically suitable and unsuitable basins, percentages of contraction or expansion for each species. Twenty-two models were successfully built, that is there were five species for which no model could be established because their distribution range was too narrow and the Acipenser sturio model failed during calibration. All the models selected temperature or/and precipitation as explanatory variables. Responses to climate change were species-specific but could be classified into three categories: little or no change in the distribution (five species), expansion of the distribution range (three species gaining suitable basins mainly northward) and contraction of the distribution (14 species losing suitable basins). Shifting ranges were in accordance with those found in other studies and underlined the high sensitivity of diadromous fish to modifications in their environment. [source]

Applying the Liu-Agresti Estimator of the Cumulative Common Odds Ratio to DIF Detection in Polytomous Items

JOURNAL OF EDUCATIONAL MEASUREMENT, Issue 4 2003
Randall D. Penfield
Liu and Agresti (1996) proposed a Mantel and Haenszel-type (1959) estimator of a common odds ratio for several 2 × J tables, where the J columns are ordinal levels of a response variable. This article applies the Liu-Agresti estimator to the case of assessing differential item functioning (DIF) in items having an ordinal response variable. A simulation study was conducted to investigate the accuracy of the Liu-Agresti estimator in relation to other statistical DIF detection procedures. The results of the simulation study indicate that the Liu-Agresti estimator is a viable alternative to other DIF detection statistics. [source]

A spatial model for the needle losses of pine-trees in the forests of Baden-Württemberg: an application of Bayesian structured additive regression

JOURNAL OF THE ROYAL STATISTICAL SOCIETY: SERIES C (APPLIED STATISTICS), Issue 1 2007
Nicole H. Augustin
Summary., The data that are analysed are from a monitoring survey which was carried out in 1994 in the forests of Baden-Württemberg, a federal state in the south-western region of Germany. The survey is part of a large monitoring scheme that has been carried out since the 1980s at different spatial and temporal resolutions to observe the increase in forest damage. One indicator for tree vitality is tree defoliation, which is mainly caused by intrinsic factors, age and stand conditions, but also by biotic (e.g. insects) and abiotic stresses (e.g. industrial emissions). In the survey, needle loss of pine-trees and many potential covariates are recorded at about 580 grid points of a 4 km × 4 km grid. The aim is to identify a set of predictors for needle loss and to investigate the relationships between the needle loss and the predictors. The response variable needle loss is recorded as a percentage in 5% steps estimated by eye using binoculars and categorized into healthy trees (10% or less), intermediate trees (10,25%) and damaged trees (25% or more). We use a Bayesian cumulative threshold model with non-linear functions of continuous variables and a random effect for spatial heterogeneity. For both the non-linear functions and the spatial random effect we use Bayesian versions of P -splines as priors. Our method is novel in that it deals with several non-standard data requirements: the ordinal response variable (the categorized version of needle loss), non-linear effects of covariates, spatial heterogeneity and prediction with missing covariates. The model is a special case of models with a geoadditive or more generally structured additive predictor. Inference can be based on Markov chain Monte Carlo techniques or mixed model technology. [source]

Penalized Regression with Ordinal Predictors

INTERNATIONAL STATISTICAL REVIEW, Issue 3 2009
Jan Gertheiss
Summary Ordered categorial predictors are a common case in regression modelling. In contrast to the case of ordinal response variables, ordinal predictors have been largely neglected in the literature. In this paper, existing methods are reviewed and the use of penalized regression techniques is proposed. Based on dummy coding two types of penalization are explicitly developed; the first imposes a difference penalty, the second is a ridge type refitting procedure. Also a Bayesian motivation is provided. The concept is generalized to the case of non-normal outcomes within the framework of generalized linear models by applying penalized likelihood estimation. Simulation studies and real world data serve for illustration and to compare the approaches to methods often seen in practice, namely simple linear regression on the group labels and pure dummy coding. Especially the proposed difference penalty turns out to be highly competitive. Résumé Les variables indépendantes catégoriques ordinales sont un cas courant dans les modèles de régression. Contrairement au cas des variables dépendantes ordinales, les variables indépendantes ordinales ont été largement négligées par la recherche. Le présent article présente les méthodes existantes et propose l'utilisation de techniques de régression pénalisée. Deux types de pénalisation basés sur des variables dummy sont exposés; le premier impose une pénalité de différence, le second est une procédure basée sur une forme de régression ridge. D'autre part, une motivation baysienne est présentée. La méthode est également appliquée au cas de variables dépendantes non gaussiennes. Des études de simulation et des données réelles servent à illustrer et à comparer les nouvelles méthodes aux méthodes que l'on rencontre souvent dans la pratique - à savoir les régressions linéaires sur les nombres entiers et sur des variables dummy sans penalité. Une pénalité de différence notamment a montré de bons résultats. [source]