arXiv subjects

Filippo Pellegrino

Publications and source records attributed to Filippo Pellegrino.

5 recordsLinked to original sources

arXiv2025

Selecting time-series hyperparameters with the artificial jackknife

This article proposes a generalisation of the delete-$d$ jackknife to solve hyperparameter selection problems for time series. I call it artificial delete-$d$ jackknife to stress that this approach substitutes the classic removal step with a fictitious deletion, wherein observed datapoints are replaced with artificial missing values. This procedure keeps the data order intact and allows plain compatibility with time series. This manuscript justifies the use of this approach asymptotically and shows its finite-sample advantages through simulation studies. Besides, this article describes its real-world advantages by regulating forecasting models for foreign exchange rates.

stat.ME↗

arXiv2023

Factor-augmented tree ensembles

This manuscript proposes to extend the information set of time-series regression trees with latent stationary factors extracted via state-space methods. In doing so, this approach generalises time-series regression trees on two dimensions. First, it allows to handle predictors that exhibit measurement error, non-stationary trends, seasonality and/or irregularities such as missing observations. Second, it gives a transparent way for using domain-specific theory to inform time-series regression trees. Empirically, ensembles of these factor-augmented trees provide a reliable approach for macro-finance problems. This article highlights it focussing on the lead-lag effect between equity volatility and the business cycle in the United States.

stat.ML↗

arXiv2023

Monitoring the Economy in Real Time: Trends and Gaps in Real Activity and Prices

We propose two specifications of a real-time mixed-frequency semi-structural time series model for evaluating the output potential, output gap, Phillips curve, and Okun's law for the US. The baseline model uses minimal theory-based multivariate identification restrictions to inform trend-cycle decomposition, while the alternative model adds the CBO's output gap measure as an observed variable. The latter model results in a smoother output potential and lower cyclical correlation between inflation and real variables but performs worse in forecasting beyond the short term. This methodology allows for the assessment and real-time monitoring of official trend and gap estimates.

econ.EM↗

arXiv2023

Multidimensional dynamic factor models

This paper generalises dynamic factor models for multidimensional dependent data. In doing so, it develops an interpretable technique to study complex information sources ranging from repeated surveys with a varying number of respondents to panels of satellite images. We specialise our results to model microeconomic data on US households jointly with macroeconomic aggregates. This results in a powerful tool able to generate localised predictions, counterfactuals and impulse response functions for individual households, accounting for traditional time-series complexities depicted in the state-space literature. The model is also compatible with the growing focus of policymakers for real-time economic analysis as it is able to process observations online, while handling missing values and asynchronous data releases.

econ.EM↗

arXiv2020

A Model of the Fed's View on Inflation

We develop a medium-size semi-structural time series model of inflation dynamics that is consistent with the view - often expressed by central banks - that three components are important: a trend anchored by long-run expectations, a Phillips curve and temporary fluctuations in energy prices. We find that a stable long-term inflation trend and a well identified steep Phillips curve are consistent with the data, but they imply potential output declining since the new millennium and energy prices affecting headline inflation not only via the Phillips curve but also via an independent expectational channel. A high-frequency energy price cycle can be related to global factors affecting the commodity market, and often overpowers the Phillips curve thereby explaining the inflation puzzles of the last ten years.

econ.EM↗