Category: IJEDF

IJEDF-5-Causal Inference with Time-Varying Instrument Strength: A Framework for Dynamic Local Average Treatment Effects

International Journal of Economic Dynamics and Finance

An Open Access Peer Reviewed International Journal.
Publication Frequency: Bimonthly
ISSN Online: XXXX-XXXX
Country of Origin: Nigeria
Language: English
Publisher Name: Academians Publishers

Causal Inference with Time-Varying Instrument Strength: A Framework for Dynamic Local Average Treatment Effects

Keywords:

Instrumental variables, local average treatment effect, time-varying instrument strength, weak identification, π-LATE, dynamic causal inference, monetary policy,

Abstract

Traditional instrumental variable approaches assume uniform instrument relevance across all observations, an assumption frequently violated in time series applications due to structural breaks, regime changes, and evolving economic relationships. This paper develops a comprehensive framework for identifying, estimating, and conducting inference on local average treatment effects when the strength of the instrument varies over time. We introduce the concept of π-LATE, which represents treatment effects for the subset of observations where instruments remain relevant, and demonstrate methods for individually identifying compliers in time series data. Through extensive simulation studies and an empirical application to monetary policy transmission, we demonstrate that focusing on strongly identified subsamples can substantially improve estimation precision while maintaining a valid causal interpretation. Our survey of recent publications in leading economics journals reveals that weak identification affects 75% of time series specifications, yet strong identification often exists in large subsamples, suggesting the widespread applicability of our methods.

Editorial Team
Join as Editor

IJEDF

IJEDF-4-Advancements in Causal Inference for High- Frequency Financial Data: A Novel Identification and Estimation Framework

International Journal of Economic Dynamics and Finance

Advancements in Causal Inference for High- Frequency Financial Data: A Novel Identification and Estimation Framework

Keywords:

Causal inference, High-frequency financial data, Instrumental variables, Time-varying identification, Local average treatment effect, Market microstructure, Monetary policy, Treasury futures, Empirical finance, Econometric methods

Abstract

The rapid expansion of high-frequency financial data has profoundly transformed the landscape of empirical research in monetary policy, asset pricing, and market microstructure. While these granular datasets offer unprecedented opportunities to uncover causal relationships and evaluate the impact of policy interventions at an intraday level, they also introduce significant methodological challenges. Notably, standard instrumental variable (IV) approaches often struggle in this context, as instrument strength can fluctuate dramatically within trading days, leading to unreliable estimates and inference when applied naively. In response, this study proposes a novel and broadly applicable identification and estimation framework designed specifically for high-frequency settings characterized by time-varying instrument validity. Our approach features a time-contingent compliance method that dynamically partitions the trading day into intervals of strong and weak instrument strength, thereby facilitating accurate and robust estimation of local average treatment effects (LATE) in real time. By leveraging smoothness constraints on asset return processes and systematically exploiting volatility spikes around scheduled economic announcements—such as Federal Open Market Committee (FOMC) meetings—our method isolates quasi-experimental shocks that underpin causal identification. We illustrate the utility of this framework through an in-depth empirical analysis of intraday Treasury futures surrounding FOMC announcements, demonstrating that our method consistently outperforms conventional IV and two-stage least squares (2SLS) techniques in both precision and reliability. Extensive simulation experiments further validate the approach, showing that it preserves correct inference under weak identification and delivers substantial power gains in strongly identified segments. These contributions offer a comprehensive toolkit for economists and financial researchers seeking to harness high-frequency data for robust causal inference across a wide array of financial market questions.

Editorial Team
Join as Editor

IJEDF

IJEDF-3-Integrating Deep Learning and Econometric Models for Predictive Analysis of Macroeconomic Indicators

International Journal of Economic Dynamics and Finance

Integrating Deep Learning and Econometric Models for Predictive Analysis of Macroeconomic Indicators

Keywords:

Deep learning, Econometric models, Hybrid forecasting, Macroeconomic indicators, RNN, SVAR, GDP, Inflation, High-frequency data, Economic policy analysis

Abstract

Abstract: The proliferation of large-scale economic datasets and advances in deep learning have created new avenues for forecasting critical macroeconomic indicators. Traditional econometric models, while interpretable, often struggle to capture nonlinear, high-dimensional relationships. This paper proposes a novel hybrid framework that integrates recurrent neural networks (RNNs) with structural vector autoregressions (SVARs) to leverage the strengths of both approaches. The RNN component extracts complex temporal patterns from high-frequency financial and sentiment data, while the SVAR imposes economic theory–guided structural identification. We apply this framework to forecast U.S. quarterly GDP growth and inflation rates using a richly textured dataset including daily market returns, text-based sentiment indices, and monthly labor statistics from 2000 to 2024. The hybrid model exhibits a 15% reduction in root mean squared forecast error (RMSFE) for GDP and a 12% reduction for inflation relative to benchmark VAR and pure deep learning models. Structural impulse‐response functions derived from the SVAR component retain economic interpretability, demonstrating realistic propagation of shocks through key economic channels.

In addition to strong predictive performance, the proposed framework is designed to facilitate economic policy analysis by ensuring the hybrid model’s outputs remain aligned with established macroeconomic theory. The integration of high-frequency sentiment and financial data enables the model to capture rapid shifts in market expectations and labor conditions, offering timely insights during periods of economic uncertainty such as the global financial crisis and the COVID-19 pandemic. Robustness checks confirm that the hybrid model’s gains persist across alternative sentiment proxies and varying model specifications, underscoring its versatility. Our results highlight not only the value of combining machine learning with econometric structures for robust and interpretable macroeconomic forecasting, but also the potential of such frameworks to inform economic decision-making in a fast-evolving data landscape.

Editorial Team
Join as Editor

IJEDF

IJEDF-2-Digital Content Quality and Market Dynamics in the Era of Artificial Intelligence: An Economic Framework for Understanding Information Ecosystems

International Journal of Economic Dynamics and Finance

Digital Content Quality and Market Dynamics in the Era of Artificial Intelligence: An Economic Framework for Understanding Information Ecosystems

Keywords:

Information Economics, Digital Content Quality, Market Failures, Algorithmic Governance, Information Pollution

Abstract

The rapid advancement of artificial intelligence—particularly large language models—has fundamentally transformed the economics of digital content creation. This transformation introduces profound challenges for preserving information quality, sustaining market efficiency, and safeguarding social welfare. Unlike traditional economic theories that focus on information asymmetries, today’s digital landscape is characterized by the mass production of apparently credible yet low-quality content at minimal cost, while generating high-quality, verified content remains resource-intensive. This paper presents a comprehensive economic framework to analyze how AI-induced cost differentials reshape digital information markets, create novel market failures, and demand innovative governance responses. Using both theoretical models and empirical evidence, we demonstrate that current market dynamics contribute to a systemic erosion of content quality. We introduce a multidimensional index to assess ecosystem health and propose adaptable policy frameworks suited to rapid technological change. Our findings deepen the understanding of technological disruption in information markets and inform the design of evidence-based policy solutions for the digital economy.

Editorial Team
Join as Editor

IJEDF

IJEDF-1-Behavioral Integration in Personal Finance Large Language Models: A Data-Centric Framework for Efficient and Trustworthy Financial Advisory Systems

International Journal of Economic Dynamics and Finance

Behavioral Integration in Personal Finance Large Language Models: A Data-Centric Framework for Efficient and Trustworthy Financial Advisory Systems

Keywords:

Large Language Models, Personal Finance, Behavioral Finance, Chain-of-Thought Reasoning, Financial Advisory, Data-Centric

Abstract

The rapid advancement of large language models (LLMs) is transforming the landscape of automated financial advisory, offering the potential for scalable, personalized, and data-driven guidance. However, current solutions are constrained by significant computational demands, insufficient adaptation to individual user behavior, and the persistence of systematic biases. In this paper, we propose a comprehensive data-centric framework that fundamentally rethinks the training and deployment of personal finance LLMs. Central to our approach is the integration of behavioral finance principles at every stage of the model development pipeline, including an innovative four-phase chain-of-thought generation process that explicitly incorporates users’ psychological states and emotional cues into financial reasoning. We constructed an extensive dataset of 19,000 real-world personal finance queries across eight diverse domains—ranging from debt management to retirement planning—and used it to fine-tune a Qwen-3-8B model. Our multi-faceted evaluation, combining held-out testing, blind LLM-jury studies, and cost-benefit analysis, demonstrates that the resulting 8B-parameter model matches or surpasses the performance of models 2–4 times larger (14–32B parameters) in factual accuracy, response fluency, and degree of personalization, while reducing operational costs by 80%. This framework directly tackles the pitfalls of current agentic and general-purpose approaches, notably their architectural complexity, high maintenance burden, and poor real-world efficiency. By showing that principled behavioral integration and robust data design can substitute for brute-force computational scaling, our work paves the way for practical, accessible, and genuinely trustworthy financial AI systems applicable to a broad range of users and scenarios.

Editorial Team
Join as Editor