Using multivariate regression modeling for sampling and predicting chemical characteristics of mixed waste in old landfills

Municipal solid waste landfills pose a threat on environment and human health, especially old landfills which lack facilities for collection and treatment of landfill gas and leachate. Consequently, missing information about emission flows prevent site-specific environmental risk assessments. To overcome this gap, the combination of waste sampling and analysis with statistical modeling is one option for estimating present and future emission potentials. Optimizing the tradeoff between investigation costs and reliable results requires knowledge about both: the number of samples to be taken and variables to be analyzed.This article aims to identify the optimized number of waste samples and variables in order to predict a larger set of variables. Therefore, we introduce a multivariate linear regression model and tested the applicability by usage of two case studies. Landfill A was used to set up and calibrate the model based on 50 waste samples and twelve variables. The calibrated model was applied to Landfill B including 36 waste samples and twelve variables with four predictor variables.The case study results are twofold: first, the reliable and accurate prediction of the twelve variables can be achieved with the knowledge of four predictor variables (Loi, EC, pH and Cl). For the second Landfill B, only ten full measurements would be needed for a reliable prediction of most response variables. The four predictor variables would exhibit comparably low analytical costs in comparison to the full set of measurements. This cost reduction could be used to increase the number of samples yielding an improved understanding of the spatial waste heterogeneity in landfills.Concluding, the future application of the developed model potentially improves the reliability of predicted emission potentials. The model could become a standard screening tool for old landfills if its applicability and reliability would be tested in additional case studies.     

Assessing farming eco-efficiency: a Data Envelopment Analysis approach

This paper assesses farming eco-efficiency using Data Envelopment Analysis (DEA) techniques. Eco-efficiency scores at both farm and environmental pressure-specific levels are computed for a sample of Spanish farmers operating in the rain-fed agricultural system of Campos County. The determinants of eco-efficiency are then studied using truncated regression and bootstrapping techniques. We contribute to previous literature in this field of research by including information on slacks in the assessment of the potential environmental pressure reductions in a DEA framework. Our results reveal that farmers are quite eco-inefficient, with very few differences emerging among specific environmental pressures. Moreover, eco-inefficiency is closely related to technical inefficiencies in the management of inputs. Regarding the determinants of eco-efficiency, farmers benefiting from agri-environmental programs as well as those with university education are found to be more eco-efficient. Concerning the policy implications of these results, public expenditure in agricultural extension and farmer training could be of some help to promote integration between farming and the environment. Furthermore, Common Agricultural Policy agri-environmental programs are an effective policy to improve eco-efficiency, although some doubts arise regarding their cost-benefit balance.     

A review of adaptive cluster sampling: 1990–2003

Adaptive cluster sampling (ACS) is an adaptive sampling scheme which operates under the rule that when the observed value of an initially selected sampling unit satisfies some condition of interest, C, other additional units in some pre-defined accompanying neighborhood are also added to the sample. In turn, if any of these additional units satisfy C, then their corresponding unit neighborhoods are added to the sample as well, and so on. This process stops when no additional units satisfying C are encountered. This paper will provide a review of the major developments and issues in ACS since its introduction by Thompson (1990) [Journal of the American Statistical Association, 85, 1050–1059].