Ecological economics focuses on provisioning for a good life for all within planetary boundaries. Feminist ecological economists have long highlighted the relevance of unpaid care work, times beyond linear clock time, and social-ecological provisioning towards this same end. In this article, we explore why and how intersectional justice should be a guiding principle for (feminist) ecological economics. Intersectional justice involves recognizing and redressing the discrimination that individuals or groups face due to overlapping social identities, which give rise to structural injustices that undermine the provisioning for a good life for all within planetary boundaries. Through three examples (global care chains, hidden ableist assumptions about ‘work’, and inequitable water access in India) we show that while many areas of feminist ecological economics lend themselves to intersectional analysis, operationalizing intersectional justice as a guiding principle is far from easy in practice. Learning from Black feminisms, disability studies, and feminist standpoint theory, we show how intersectional feminist perspectives can help challenge power structures and institutions that sustain injustices on both epistemic and material levels. This enables the kinds of collaborative action that can bring (feminist) ecological economics into broader acceptance, uniting struggles against various forms of oppression while building economic systems that prioritize the sustainability of life.
This paper examines the role of finance and asset prices in enhancing the real-time reliability of output gap estimates. In a structural unobserved components model, financial indicators are embedded in the cyclical component alongside unemployment and inflation. The results show that incorporating finance and asset prices not only explains a large share of cyclical fluctuations in economic output but also improves real-time reliability by producing estimates that are less prone to ex-post revisions.
Neural networks have become a popular tool in predictive modelling, more commonly associated with machine learning and artificial intelligence than with statistics. Generalised Additive Models (GAMs) are flexible non-linear statistical models that retain interpretability. Both are state-of-the-art in their own right, with their respective advantages and disadvantages. This paper analyses how these two model classes have performed on real-world tabular data. Following PRISMA guidelines, we conducted a systematic review of papers that performed empirical comparisons of GAMs and neural networks. Eligible papers were identified, yielding 143 papers, with 430 datasets. Key attributes at both paper and dataset levels were extracted and reported. Beyond summarising comparisons, we analyse reported performance metrics using mixed-effects modelling to investigate potential characteristics that can explain and quantify observed differences, including application area, study year, sample size, number of predictors, and neural network complexity. Across datasets, no consistent evidence of superiority was found for either GAMs or neural networks when considering the most frequently reported metrics (RMSE, R^2, and AUC). Neural networks tended to outperform in larger datasets and in those with more predictors, but this advantage narrowed over time. Conversely, GAMs remained competitive, particularly in smaller data settings, while retaining interpretability. Reporting of dataset characteristics and neural network complexity was incomplete in much of the literature, limiting transparency and reproducibility. This review highlights that GAMs and neural networks should be viewed as complementary approaches rather than competitors. For many tabular applications, the performance trade-off is modest, and interpretability may favour GAMs.
Large Language Models (LLMs) such as ChatGPT are transforming how scientists conduct and validate research, offering promise as tools to improve scientific reproducibility. However, computational reproducibility and error detection remain expensive and labor-intensive. We experimentally test how collaboration between researchers and LLM assistants influences the reproduction of quantitative social science findings across different levels of AI autonomy. We randomly assigned 288 researchers to 103 teams working under three conditions: human-only, AI-assisted (using ChatGPT as a collaborative tool), or AI-led (ChatGPT operating with minimal human oversight). Teams reproduced published results from leading social science journals, detected coding errors, and proposed robustness checks. Human-only and AI-assisted teams achieved comparable reproduction rates (94% vs. 91%) and performed similarly on most outcomes, except human-only teams identified significantly more major coding errors. Both substantially outperformed AI-led teams, which achieved only a 37% reproduction rate, detected fewer errors across all categories, proposed weaker robustness checks, and required more time. This autonomous approach, however, likely represents only a lower bound of AI capabilities. Despite rapid model advances, expert human judgment currently remains indispensable for reliable empirical verification. While AI assistance did not degrade most outcomes, it provided no measurable advantages and was associated with reduced detection of major errors. However, the 37% autonomous reproduction rate indicates that AI could provide value in settings where scale or cost constraints preclude human review of papers, even though general-purpose LLMs offer no immediate advantages for human-supervised verification.
