BackgroundConfounding bias is a common concern in epidemiological research. Its presence is often determined by comparing exposure effects between univariable- and multivariable regression models, using an arbitrary threshold of a 10% difference to indicate confounding bias. However, many clinical researchers are not aware that the use of this change-in-estimate criterion may lead to wrong conclusions when applied to logistic regression coefficients. This is due to a statistical phenomenon called noncollapsibility, which manifests itself in logistic regression models. This paper aims to clarify the role of noncollapsibility in logistic regression and to provide guidance in determining the presence of confounding bias.MethodsA Monte Carlo simulation study was designed to uncover patterns of confounding bias and noncollapsibility effects in logistic regression. An empirical data example was used to illustrate the inability of the change-in-estimate criterion to distinguish confounding bias from noncollapsibility effects.ResultsThe simulation study showed that, depending on the sign and magnitude of the confounding bias and the noncollapsibility effect, the difference between the effect estimates from univariable- and multivariable regression models may underestimate or overestimate the magnitude of the confounding bias. Because of the noncollapsibility effect, multivariable regression analysis and inverse probability weighting provided different but valid estimates of the confounder-adjusted exposure effect. In our data example, confounding bias was underestimated by the change in estimate due to the presence of a noncollapsibility effect.ConclusionIn logistic regression, the difference between the univariable- and multivariable effect estimate might not only reflect confounding bias but also a noncollapsibility effect. Ideally, the set of confounders is determined at the study design phase and based on subject matter knowledge. To quantify confounding bias, one could compare the unadjusted exposure effect estimate and the estimate from an inverse probability weighted model.
MULTIFILE
The Tuntang Watershed is an important watershed in Central Java. Management of watersheds in the Tuntang stream is a priority for various parties to carry out. One of the things that threatens the sustainability of the Tuntang watershed is erosion. The erosion rate can lead to sediment accumulation and siltation in the Tuntang River reservoir, which can cause catastrophic flooding. Flood disaster mitigation caused by erosion needs to be done, one of which is by calculating the erosion rate per year that occurs in the Tuntang watershed. This study calcultated the predicted erosion rate (per year in the Tuntang watershed) using the Revised Universal Soil Loss Equation (RUSLE) method, processed using the Google Earth Engine (GEE). Google offers a cloud-storage technology called GEE. Programming in JavaScript is required to operate GEE. GEE is a petabyte-scale data-based tool that can be used to analyze and archive geospatial data that is open source. The computing environment is designed for the processing of geospatial data, including the depiction of spatial analysis of satellite imagery. Data for RUSLE is obtained from the database in GEE, and the results can be imaged on a map. According to the study's findings, the degree of soil erosion throughout the Tuntang Watershed was essentially constant, with Moderate erosion predominating in the majority of locations. Senjoyo Sub Watershed, Rowopening Sub Watershed, and Tuntang Hilir Sub Watershed are the primary locations with severe erosion. Rowopening Sub Watershed is the region that is the worst.
LINK
Mexican oregano is a non-timber forest product harvested in natural vegetation and represents an important source of income for rural families. Recent reports have highlighted decreases in natural populations caused by increased harvest intensity. Oregano leaf harvesting is a complex problem, involving different components and views, and has a clear spatial dimension. We proposed an analytical framework based on multi-criteria-multi-objective analyses. GIS tools were used as the platform for managing, displaying and analyzing ecological and socioeconomic information from different sources in order to evaluate land suitability of three different management strategies for two competing land objectives: oregano Harvest and oregano Regeneration. The incorporation of environmental evaluation criteria in the analysis allowed the identification of new potential oregano harvesting areas which were neither reported by harvesters, nor registered during harvesting trips. Socio-economic criteria, such as land tenure, highlighted the fact that a substantial proportion of current oregano harvesting areas are located outside ejido limits resulting in potential conflicts for resource access. The proposed Balanced oregano management strategy, in which the same proportion of suitable area (50%) was assigned to both objectives, represents the most favorable management strategy. This option allows harvesters to continue earning an income from oregano leaf harvest; and at the same time helps in the selection of the best areas for oregano regeneration. It also represents a management strategy with a smaller impact on oregano populations and on the harvesters ́ income, as well as lower monitoring costs. The proposed analytical frame-work may contribute to advance the application of systematic approaches for solving decision-making problems in areas where oregano leaves and other NTFP are harvested.
MULTIFILE
