Research

Journal Articles

(Part of PhD Dissertation)

WP Version: International Network for Economic Research - INFER, Working Papers 2021.02

Abstract: The Great Moderation was a global phenomenon marked by stable economic growth and inflation. However, how much monetary policy contributed to its success remained a popular debate in the literature. Answering this question became imperative after the global financial crisis since global conditions became relatively more important than past. I examined the recent macroeconomic history of New Zealand through the lens of a regime-switching structural vector-autoregression model to understand the contributions of domestic monetary policy and global conditions to its macroeconomic stabilization. A small open economy structure is essential to facilitate the identification of structural shocks that spillover from the globe.

Working Papers

Abstract: This paper is concerned with nowcasting in a setting involving a large dataset with mixed frequencies, missing data problems, and regime-switching over time. I show that the Expectation-Maximization (EM) algorithm provides satisfactory performance relative to other estimation methods and delivers a good trade-off between accuracy and speed, which makes it especially useful for real-time applications involving large dimensional data. The methodology solves for the closed form solutions to the parameter estimators instead of relying numerical maximization routines. In an application to vintage US data, I show that the regime-switching modification promises improved forecasting performance. The regime-switching model demonstrates superior nowcasting performance, particularly when key economic indicators are released. In addition, the regime-switching nowcasting model is able to closely match the recession dating of the NBER despite having less information than actual committee meetings. This allows policymakers to act beforehand. In a backcasting exercise, I show that the fit between actual NBER recession dates and model recession estimates becomes more apparent with the additional available information.

Abstract: Quarterly GDP statistics facilitate timely economic assessment, but the availability of such data are limited for more than 60 developing economies, including about 20 countries in sub-Saharan Africa as well as more than two-thirds of fragile and conflict-affected states. To address this limited data availability, this paper proposes a panel approach that utilizes a statistical relationship estimated from countries where data are available, to estimate quarterly GDP statistics for countries that do not publish such statistics by leveraging the indicators readily available for many countries. This framework demonstrates potential, especially when applied for similar country groups, and could provide valuable real-time insights into economic conditions supported by empirical evidence.