Search

This paper develops Monte Carlo likelihood-ratio tests for determining the number of regimes in Markov switching models. Unlike most existing procedures, which focus on testing one versus two regimes, the proposed methods allow testing an arbitrary number of regimes. They are valid in finite samples, robust to identification problems, and applicable to nonstationary, multivariate, and Markov switching GARCH models.

We construct a macroeconomic estimate of total AI production in the United States, combining inference and R&D/training activities with quality adjustments to account for algorithmic progress. We then develop a nascent framework for "AI GDP" that tracks the AI economy as a coherent whole, complementing traditional national accounts.

Amid heightened Canada–US trade tensions in 2025, financial markets showed signs that investors had greater difficulty anticipating near-term Bank of Canada interest rate decisions. We look at the Overnight Index Swap prices and intraday Government of Canada yields to identify the main driver of uncertainty around interest rate decisions.

How do central bank crisis interventions calm market fears? Using options data, we measure the perceived risk of large asset price drops across horizons from two weeks to ten years. Studying the Fed's response to the 2020 turmoil, we find asset purchases reduce short-term fears while interest rate actions shape long-term expectations.

This paper examines how climate change affects income inequality across US states. Using a new climate-inequality VAR and a century of daily temperature data, it shows that shifts across the full temperature distribution—not just average warming—have diverse effects on within-state inequality.

This paper reviews how central banks are integrating non traditional data and artificial intelligence (AI) into policy analysis and operations. Using the Bank of Canada’s experience, it examines emerging applications, governance challenges, and strategic choices for responsibly scaling AI to enhance insight, efficiency, and institutional resilience.

How can Surveys of Professional Forecasters (SPF) be used to improve inflation forecasts? By using US historical quarterly data on SPF forecasts, we provide better understanding of how we can use forecast disagreement to improve our own forecasts.

Statistical inference--both estimation and testing--for stochastic volatility (SV) models is known to be challenging and computationally demanding. We propose simple and efficient estimators for SV models with conditionally heavy-tailed error distributions, particularly the Student’s t and Generalized Exponential Distributions (GED). The estimators rely on a small set of moment conditions derived from ARMA-type representations of SV models, with an option to apply “winsorization” to improve stability and finite-sample performance. Except for the degrees of-freedom parameter, closed-form expressions are available for all other parameters, extending Ahsan and Dufour (2019, 2021), thus eliminating the need for numerical optimization or initial values. We derive the estimators’ asymptotic distribution and show that, due to their analytical tractability, they support reliable, and even exact, simulation-based inference via Monte Carlo or bootstrap methods. We assess their performance through extensive simulations and demonstrate their practical relevance in financial return data, which strongly reject the normality assumption in favor of heavy-tailed models.

We present the R package MSTest, which implements hypothesis testing procedures to determine the number of regimes in Markov switching models. The package provides several testing frameworks, including Monte Carlo likelihood ratio tests, moment-based tests, parameter stability tests, and classical likelihood ratio procedures.

Can monetary policy influence the neutral real interest rate (r-star)? Using a new statistical model, we show that interest rate hikes tend to lower r-star and long-run growth, but that monetary policy explains only a small share of the long-run decline in r-star.