We study treatment-effect estimation using panel data. The treatment may be non-binary, non-absorbing, and the outcome may be affected by treatment lags. We make a parallel-trends assumption, and propose event-study estimators of the effect of being exposed to a weakly higher treatment dose for ℓ periods. We also propose normalized estimators, that estimate a weighted average of the effects of the current treatment and its lags. We also analyze commonly-used two-way fixed-effects regressions. Unlike our estimators, they can be biased in the presence of heterogeneous treatment effects. A local-projection version of those regressions is biased even with homogeneous effects.
The FAO Irrigation and Drainage Paper 56, which was first published in 1998, has been widely recognized as a comprehensive guidebook for estimating crop evapotranspiration and calculating crop water requirements under various conditions, supporting the efficient management of water resources in agriculture. Over the past twenty-eight years, science and technology have significantly evolved in agricultural productivity and water resource mobilization, use, and management, as well as in research advances, data availability and management, and modeling capabilities and uses. However, these improvements have come against a backdrop of increasingly pressing challenges, especially those posed by climate change and water scarcity. Thus, considering all recent advances in knowledge, an updated version (FAO56 Rev.1) of that guidebook was recently released. The current article summarizes and highlights the main features and innovations that the revision has incorporated.
The study of human behavior has shifted in the last fifteen years, with increasing reliance on opt-in non-probability online data sources. We offer an analysis of nine such data sources (total N = 13,053), aiming to inform researchers conducting experiments or correlational studies. We assess response validity (attentiveness, effort, honesty, speeding, and attrition), the extent to which samples represent the underlying population (observable demographics, measured attitude representativeness, and responding to experimental treatments), and professionalism (number of studies taken, frequency of taking studies, and modality of device on which the study is taken). We document substantial variation across these samples on each dimension. Samples that employ demographic quotas display relatively higher amounts of representativeness across multiple indicators (beyond demographics) but often exhibit less response validity. However, the inclusion of two attention checks early in a study enhances response validity without negatively impacting representativeness. We offer guidance for choosing opt-in samples, depending on the purpose of the research and resource constraints.
The Normalized Difference Vegetation Index (NDVI) serves as a fundamental parameter for monitoring vegetation dynamics and ecosystem health, yet existing moderate-resolution NDVI products lack the spatial detail required for fine-scale environmental applications. While Landsat satellites provide long-term observations at 30meter resolution suitable for detailed vegetation monitoring, frequent cloud contamination and the 16-day revisit cycle create substantial data gaps that compromise temporal continuity. Traditional gap-filling approaches face limitations including reliance on auxiliary sensors, assumptions of temporal stability, and inability to handle persistent cloud cover in tropical and mountainous regions. We developed an innovative Multiple Imputation with Recursive Feature Elimination and Bidirectional Long Short-Term Memory (MI-RFE-BiLSTM) framework to generate spatiotemporally seamless Landsat NDVI time series. The methodology employs a fourstep approach: GLASS NDVI-based pre-filling leveraging correlation-weighted similarity analysis for initial gap estimates, BiLSTM networks to model bidirectional temporal dependencies in vegetation phenology, iterative multiple imputation for progressive refinement of missing values and model parameters through convergencecontrolled optimization, and recursive feature elimination using gradient-based sensitivity analysis to optimize temporal feature selection. Comprehensive validation across 97 globally distributed study regions spanning diverse biomes demonstrated superior reconstruction performance, with MI-RFE-BiLSTM achieving R2 values of 0.84-0.93 and RMSE values of 0.02-0.06 across diverse vegetation types and environmental conditions. Robustness analysis revealed the framework maintained stable accuracy even under severely limited clear-sky observations, showing graceful degradation when data availability decreased to 5-10% of original coverage. Large-scale applications in persistently cloudy mountainous regions confirmed operational viability, successfully reconstructing complete NDVI coverage while preserving fine-scale spatial patterns at native Landsat resolution. The method exhibits strong generalizability across varied landscapes and climate zones. By addressing the critical bottleneck of fixed high-dimensional inputs in existing deep learning methods, the proposed adaptive feature selection reduces input dimensionality by 30-50% while achieving approximately twofold improvement in computational efficiency, making large-scale operational deployment practically feasible. This framework provides a reliable solution for generating high-quality, temporally continuous Landsat NDVI products essential for precision agriculture, ecosystem monitoring, and climate change research applications.
In this work, we propose a Stackelberg-like model for a resource allocation problem over an urban region. The model incorporates transportation costs, distribution costs, and utility functions. A social planner aims to minimize the total cost while maximizing the welfare of the population that receives the resource. The resulting formulation is a bilevel optimization problem—also known as a Stackelberg game in game theory. The existence of the best-response function is established by means of results from optimal transport theory.
