Keywords: econometrics, time series, forecasting, monetary economics

Forecasting Exchange Rate Volatility: The Superior Performance of Conditional Combinations of Time Series and Option Implied Forecasts

August, 2008

With Guillermo Benavides

Abstract: This paper shows that combinations of option implied and time series volatility forecasts that are conditional on current information are statistically superior to individual models, (unconditional) combinations, and hybrid forecasts. Hence, it finds empirical evidence that both, combining individual forecasts, and taking into account the conditional expected performance of each model given current information, are important to improve out-of-sample forecasting performance. The method used in this paper extends the application of conditional predictive ability tests to select forecast combinations. We show that this method works well in practice by applying it to volatility forecasts for the Mexican Peso-US Dollar exchange rate, where the actual value is taken to be the realized volatility measured using intra-day observations.

Submitted

Working paper 08/20/08 [pdf]

Las Expectativas Macroeconómicas de los Especialistas: Una Evaluación de Pronósticos de Corto Plazo en México

Agosto, 2008

Con Gabriel López-Moctezuma

Resumen: Se analizan los pronósticos de inflación, tipo de cambio, tasa de interés y crecimiento del PIB contenidos en la Encuesta sobre Expectativas de los Especialistas en Economía del Sector Privado, que recaba mensualmente el Banco de México. El estudio se enfoca en el promedio simple de las respuestas de los especialistas para el periodo que va de enero de 1995 a abril de 2008. Se evalúa la eficiencia en el uso de información y el desempeño relativo utilizando como referencia pronósticos sencillos de series de tiempo, y pronósticos obtenidos utilizando variables macroeconómicas. Se encuentra que las expectativas de inflación, tasa de interés y PIB parecen incorporar información disponible de manera relativamente eficiente, con excepción de los de inflación anual. Por otro lado, los pronósticos de tipo de cambio no parecen incorporar de manera óptima información disponible y no parecen ser mejores que pronósticos obtenidos a partir de un modelo de caminata aleatoria..

Submitted

Documento de Investigación, Banco de México 2008-11 [pdf]

Forecast Combination with Entry and Exit of Experts

August, 2008

With Allan Timmermann

Abstract: Combination of forecasts from survey data is complicated by the frequent entry and exit of individual forecasters which renders conventional least squares regression approaches infeasible. We explore the consequences of this issue for existing combination methods and propose new methods for bias-adjusting the equal-weighted forecast or applying combinations on an extended panel constructed by back-filling missing observations using an EM algorithm. Through simulations and an application to a range of macroeconomic variables we show that the entry and exit of forecasters can have a large effect on the real-time performance of conventional combination methods. The bias-adjusted combination method is found to work well in practice.

Revise and resubmit JBES

Working paper 08/04/08 [pdf]

Banco de México Research Document 2006-08 [pdf]

Optimality Tests for Multi-Horizon Forecasts

December, 2007

Abstract: This paper develops and analyzes a series of tests to evaluate the optimality of forecasts when forecasts for more than one horizon are available. The tests are based on the property that the unconditional expected loss of optimal forecasts should not decrease with the forecast horizon (e.g., under quadratic loss the variance of optimal forecast errors should not decrease with the horizon). The tests complement existing methods of forecast evaluation, such as Mincer-Zarnowitz-type tests, by using an implication of optimality that directly concerns forecasts made at different horizons. The finite sample performance of the tests is analyzed and an illustration using the Survey of Professional Forecasters is provided.

Revise and resubmit OBES

Banco de México Research Document 2007-14 [pdf]

Does Inflation Targeting Affect the Dispersion of Inflation Expectations?

August, 2007

With Manuel Ramos-Francia

Abstract: In this paper we examine the effect of having an inflation targeting framework on the dispersion of inflation forecasts from professional forecasters. We use a panel data set of 26 countries including 14 inflation targeters with monthly information from the last 16 years. We find that the dispersion of long-run inflation expectations is lower in targeting regimes after controlling for country-specific effects, time-specific effects, initial dispersion, the level and the variance of inflation, disinflation periods, and global inflation. When we differentiate between developed and developing countries, we find different dynamics for each group. In particular, the mentioned effect of inflation targeting seems to be present only on the developing countries.

Submitted

Banco de México Research Document 2007-11 [pdf]

Bias in Federal Reserve Inflation Forecasts: Is the Federal Reserve Irrational or Just Cautious?

Forthcoming in: Journal of Monetary Economics.

Working paper version 07/02/2008 [pdf]

Banco de México Research Document 2006-14 [pdf]

UCSD discussion paper 2005-05 [pdf]

Disagreement and Biases in Inflation Expectations

With Allan Timmermann

Forthcoming in: Journal of Money, Credit and Banking.

Working paper version 02/18/08 [pdf]

Banco de México Research Document 2006-07 [pdf]

Inflation Dynamics in Latin America

With Manuel Ramos-Francia

Forthcoming in: Contemporary Economic Policy.

Working paper version 04/21/08 [pdf]

Banco de México Research Document  2006-11 [pdf]

On Comparing Multi-horizon Forecasts

Published in: Economics Letters, 93:176-181, 2006

Link to published version [link]

Working paper version 02/28/06 [pdf]