Evaluating sampling strategies and logistic regression methods for modelling complex land cover changes

The role of land cover change as a significant component of global change has become increasingly recognized in recent decades. Large databases measuring land cover change, and the data which can potentially be used to explain the observed changes, are also becoming more commonly available. When developing statistical models to investigate observed changes, it is important to be aware that the chosen sampling strategy and modelling techniques can influence results. We present a comparison of three sampling strategies and two forms of grouped logistic regression models (multinomial and ordinal) in the investigation of patterns of successional change after agricultural land abandonment in Switzerland. Results indicated that both ordinal and nominal transitional change occurs in the landscape and that the use of different sampling regimes and modelling techniques as investigative tools yield different results. Synthesis and applications. Our multimodel inference identified successfully a set of consistently selected indicators of land cover change, which can be used to predict further change, including annual average temperature, the number of already overgrown neighbouring areas of land and distance to historically destructive avalanche sites. This allows for more reliable decision making and planning with respect to landscape management. Although both model approaches gave similar results, ordinal regression yielded more parsimonious models that identified the important predictors of land cover change more efficiently. Thus, this approach is favourable where land cover change pattern can be interpreted as an ordinal process. Otherwise, multinomial logistic regression is a viable alternative.

Binary classification of dyslipidemia from the waist-to-hip ratio and body mass index: a comparison of linear, logistic, and CART models.

BACKGROUND: We sought to improve upon previously published statistical modeling strategies for binary classification of dyslipidemia for general population screening purposes based on the waist-to-hip circumference ratio and body mass index anthropometric measurements. METHODS: Study subjects were participants in WHO-MONICA population-based surveys conducted in two Swiss regions. Outcome variables were based on the total serum cholesterol to high density lipoprotein cholesterol ratio. The other potential predictor variables were gender, age, current cigarette smoking, and hypertension. The models investigated were: (i) linear regression; (ii) logistic classification; (iii) regression trees; (iv) classification trees (iii and iv are collectively known as "CART"). Binary classification performance of the region-specific models was externally validated by classifying the subjects from the other region. RESULTS: Waist-to-hip circumference ratio and body mass index remained modest predictors of dyslipidemia. Correct classification rates for all models were 60-80%, with marked gender differences. Gender-specific models provided only small gains in classification. The external validations provided assurance about the stability of the models. CONCLUSIONS: There were no striking differences between either the algebraic (i, ii) vs. non-algebraic (iii, iv), or the regression (i, iii) vs. classification (ii, iv) modeling approaches. Anticipated advantages of the CART vs. simple additive linear and logistic models were less than expected in this particular application with a relatively small set of predictor variables. CART models may be more useful when considering main effects and interactions between larger sets of predictor variables.

Validation of Logistic Regression Models for Landslide Susceptibility Maps

A wide range of numerical models and tools have been developed over the last decades to support the decision making process in environmental applications, ranging from physical models to a variety of statistically-based methods. In this study, a landslide susceptibility map of a part of Three Gorges Reservoir region of China was produced, employing binary logistic regression analyses. The available information includes the digital elevation model of the region, geological map and different GIS layers including land cover data obtained from satellite imagery. The landslides were observed and documented during the field studies. The validation analysis is exploited to investigate the quality of mapping.

Explaining Fiscal Balances with a Simultaneous Equation Model of Revenue and Expenditure : A Case Study of Swiss Cantons Using Panel Data

Empirical literature on the analysis of the efficiency of measures for reducing persistent government deficits has mainly focused on the direct explanation of deficit. By contrast, this paper aims at modeling government revenue and expenditure within a simultaneous framework and deriving the fiscal balance (surplus or deficit) equation as the difference between the two variables. This setting enables one to not only judge how relevant the explanatory variables are in explaining the fiscal balance but also understand their impact on revenue and/or expenditure. Our empirical results, obtained by using a panel data set on Swiss Cantons for the period 1980-2002, confirm the relevance of the approach followed here, by providing unambiguous evidence of a simultaneous relationship between revenue and expenditure. They also reveal strong dynamic components in revenue, expenditure, and fiscal balance. Among the significant determinants of public fiscal balance we not only find the usual business cycle elements, but also and more importantly institutional factors such as the number of administrative units, and the ease with which people can resort to political (direct democracy) instruments, such as public initiatives and referendum.

Estimation de la fonction rénale par l'equation MDRD: intérêt et limites pour l'adaptation des doses de médicaments [Renal function estimation by MDRD equation: interest and limitations for drug dosing].

The MDRD (Modification of diet in renal disease) equation enables glomerular filtration rate (GFR) estimation from serum creatinine only. Thus, the laboratory can report an estimated GFR (eGFR) with each serum creatinine assessment, increasing therefore the recognition of renal failure. Predictive performance of MDRD equation is better for GFR < 60 ml/min/1,73 m2. A normal or near-normal renal function is often underestimated by this equation. Overall, MDRD provides more reliable estimations of renal function than the Cockcroft-Gault (C-G) formula, but both lack precision. MDRD is not superior to C-G for drug dosing. Being adjusted to 1,73 m2, MDRD eGFR has to be back adjusted to the patient's body surface area for drug dosing. Besides, C-G has the advantage of a greater simplicity and a longer use.

Predisposing and precipitating factors of delirium after cardiac surgery: a prospective observational cohort study.

OBJECTIVE: To comprehensively assess pre-, intra-, and postoperative delirium risk factors as potential targets for intervention. BACKGROUND: Delirium after cardiac surgery is associated with longer intensive care unit (ICU) stay, and poorer functional and cognitive outcomes. Reports on delirium risk factors so far did not cover the full range of patients' presurgical conditions, intraoperative factors, and postoperative course. METHODS: After written informed consent, 221 consecutive patients ≥ 50 years scheduled for cardiac surgery were assessed for preoperative cognitive performance, and functional and physical status. Clinical and biochemical data were systematically recorded perioperatively. RESULTS: Of the 215 patients remaining for analysis, 31% developed delirium in the intensive care unit. Using logistic regression models, older age [73.3 (71.2-75.4) vs 68.5 (67.0-70.0); P = 0.016], higher Charlson's comorbidity index [3.0 (1.5-4.0) vs 2.0 (1.0-3.0) points; P = 0.009], lower Mini-Mental State Examination (MMSE) score (MMSE, [27 (23-29) vs 28 (27-30) points; P = 0.021], length of cardiopulmonary bypass (CPB) [CPB; 133 (112-163) vs 119 (99-143) min; P = 0.004], and systemic inflammatory response syndrome in the intensive care unit [25 (36.2%) vs 13 (8.9%); P = 0.001] were independently associated with delirium. Combining age, MMSE score, Charlson's comorbidity index, and length of CPB in a regression equation allowed for a prediction of postoperative delirium with a sensitivity of 71.19% and a specificity of 76.26% (receiver operating analysis, area under the curve: 0.791; 95% confidence interval: 0.727-0.845). CONCLUSIONS: Further research will evaluate if modification of these risk factors prevents delirium and improves outcomes.

Shrews in suburbia: an application of Goodman's extinction model

An equation is applied for calculating the expected persistence time of an unstructured population of the white-toothed shrew Crocidura russula from Preverenges, a suburban area in western Switzerland. Population abundance data from March and November between 1977 and 1988 were fit to the logistic density dependence model to estimate mean population growth rate as a function of population density. The variance in mean growth rate was approximated with two different models. The largest estimated persistence time was less than a few decades, the smallest less than 10 years. The results are sensitive to the magnitude of variance in population growth rate. Deviations from the logistic density dependence model in November are quite well explained by weather variables but those in March are uncorrelated with weather variables. Variability in population growth rates measured in winter months may be better explained by behavioural mechanisms. Environmental variability, dispersal of juveniles and refugia within the range of the population may contribute to its long-term survival.

Further insights on the French WISC-IV factor structure through Bayesian structural equation modeling

The interpretation of the Wechsler Intelligence Scale for Children-Fourth Edition (WISC-IV) is based on a 4-factor model, which is only partially compatible with the mainstream Cattell-Horn-Carroll (CHC) model of intelligence measurement. The structure of cognitive batteries is frequently analyzed via exploratory factor analysis and/or confirmatory factor analysis. With classical confirmatory factor analysis, almost all crossloadings between latent variables and measures are fixed to zero in order to allow the model to be identified. However, inappropriate zero cross-loadings can contribute to poor model fit, distorted factors, and biased factor correlations; most important, they do not necessarily faithfully reflect theory. To deal with these methodological and theoretical limitations, we used a new statistical approach, Bayesian structural equation modeling (BSEM), among a sample of 249 French-speaking Swiss children (8-12 years). With BSEM, zero-fixed cross-loadings between latent variables and measures are replaced by approximate zeros, based on informative, small-variance priors. Results indicated that a direct hierarchical CHC-based model with 5 factors plus a general intelligence factor better represented the structure of the WISC-IV than did the 4-factor structure and the higher order models. Because a direct hierarchical CHC model was more adequate, it was concluded that the general factor should be considered as a breadth rather than a superordinate factor. Because it was possible for us to estimate the influence of each of the latent variables on the 15 subtest scores, BSEM allowed improvement of the understanding of the structure of intelligence tests and the clinical interpretation of the subtest scores.

Population density and optimal body size.

The population density of an organism is one of the main aspects of its environment, and shoud therefore strongly influence its adaptive strategy. The r/K theory, based on the logistic model, was developed to formalize this influence. K-selectioon is classically thought to favour large body sizes. This prediction, however, cannot be directly derived from the logistic model: some auxiliary hypotheses are therefor implicit. These are to be made explicit if the theory is to be tested. An alternative approach, based on the Euler-Lotka equation, shows that density itself is irrelevant, but that the relative effect of density on adult and juvenile features is crucial. For instance, increasing population will select for a smaller body size if the density affects mainly juvenile growth and/or survival. In this case, density shoud indeed favour large body sizes. The theory appears nevertheless inconsistent, since a probable consequence of increasing body size will be a decrease in the carrying capacity