nep-for New Economics Papers
on Forecasting
Issue of 2025–01–06
two papers chosen by
Rob J Hyndman, Monash University


  1. Combining Forecasts under Structural Breaks Using Graphical LASSO By Tae-Hwy Lee; Ekaterina Seregina
  2. Consumer Prices Trends in Colombia: Detecting Breaks and Forecasting Infation By Héctor M. Zárate-Solano; Norberto Rodríguez-Niño

  1. By: Tae-Hwy Lee (Department of Economics, University of California Riverside); Ekaterina Seregina (Colby College)
    Abstract: In this paper we develop a novel method of combining many forecasts based on Graphical LASSO. We represent forecast errors from different forecasters as a network of interacting entities and generalize network inference in the presence of common factor structure and structural breaks. First, we note that forecasters often use common information and hence make common errors, which makes the forecast errors exhibit common factor structures. We separate common forecast errors from the idiosyncratic errors and exploit sparsity of the precision matrix of the latter. Second, since the network of experts changes over time as a response to unstable environments, we propose Regime-Dependent Factor Graphical LASSO (RD-FGL) that allows factor loadings and idiosyncratic precision matrix to be regime-dependent. The empirical applications to forecasting macroeconomic series using the data of the European Central Bank’s Survey of Professional Forecasters and Federal Reserve Economic Data monthly database demonstrate superior performance of a combined forecast using RD-FGL.Â
    Keywords: Common Forecast Errors; Regime Dependent Forecast Combination; Sparse Precision Matrix of Idiosyncratic Errors; Structural Breaks
    JEL: C13 C38 C55
    Date: 2024–12
    URL: https://d.repec.org/n?u=RePEc:ucr:wpaper:202413
  2. By: Héctor M. Zárate-Solano; Norberto Rodríguez-Niño
    Abstract: Colombia’s annual infation reached 13.3% in March of 2023, the highest rate since the start of the infation-targeting regime for monetary policy in 2000. However, some groups in the basket show signs of lower infation, while others show higher infation. The persistence of this trend is a matter of active debate that involves analyzing the trend component of both year-to-year and month-to-month changes in the price indices. This paper employs time series models to identify infation shift levels based on the 188 price indices in the basket. We categorize trend breaks as positive or negative and further classify them into tradable versus non-tradable, core versus regulated, and other CPI categories. Using trend models that incorporate these breaks, we forecast total and group infation. Our results show that including trend breaks enhances prediction accuracy for monthly annual infation across all time horizons. **** RESUMEN: En marzo de 2023, la inflación anual en Colombia alcanzó el 13, 3%, la tasa más alta desde que se implementó el régimen de inflación objetivo en el año 2000. Sin embargo, mientras algunos grupos de la canasta básica muestran signos de menor inflación, otros experimentan un aumento. La persistencia de esta tendencia es objeto de un debate activo, que ha utilizado las variaciones anuales y mensuales en los índices de precios para detectar posibles cambios en la tendencia. En este documento, empleamos modelos de series de tiempo para identificar cambios en los niveles de inflación, basándonos en los 188 índices de precios que conforman la canasta. Clasificamos las rupturas de tendencia como positivas o negativas y las agrupamos según diversas categorías, tales como transables y no transables, básicos y regulados, entre otros grupos del IPC. Adicionalmente, utilizamos estos modelos de tendencia, con posibles quiebres, para pronosticar la inflación total y la inflación por grupos. Nuestros resultados indican que incorporar los quiebres en las tendencias mejora la precisión de los pronósticos de acuerdo con las medidas de evaluación tradicionales.
    Keywords: Consumer Price Indexes, Linear Trend Models, Structural Breaks, Forecasting, Forecasting Evaluation, Índices de Precios al Consumidor, Modelos de Tendencia Lineal, Quiebres Estructurales, Pronósticos, Evaluación de pronósticos
    JEL: C22 C43 E31 E37
    Date: 2024–12
    URL: https://d.repec.org/n?u=RePEc:bdr:borrec:1289

This nep-for issue is ©2025 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at https://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.