Papers by Carlos Capistrán
This document analyzes inflation, exchange rate, interest rate, and GDP growth forecasts from the... more This document analyzes inflation, exchange rate, interest rate, and GDP growth forecasts from the monthly Survey of Professional Forecasters, maintained by Banco de Mexico. The study concentrates on the mean across forecasters for the period from January 1995 to April 2008. Their efficiency in the use of information is examined, as well as their relative performance using as benchmarks forecasts obtained from time-series, macroeconomic, and financial variables. In general, consensus forecasts do not pass tests of unbiasedness, lack of serial correlation, and efficient use of available information, suggesting opportunities to improve the quality of these forecasts. However, the forecasts seem to be, in general, more accurate than the benchmark forecasts, although this relative forecasting advantage appears to diminish in a sample that starts in January 2002. [ABSTRACT FROM AUTHOR] Abstract (Spanish): Se analiza los pronosticos de inflacion, tipo de cambio, tasa de interes y crecimien...
International Journal of Forecasting, 2014
We analyze forecasts of inflation and GDP growth contained in Banco de México´s Survey of Profess... more We analyze forecasts of inflation and GDP growth contained in Banco de México´s Survey of Professional Forecasters for the period 1995-2009. The forecasts are for the current and the following year, comprising an unbalanced three-dimensional panel with multiple individual forecasters, target years, and forecast horizons. The fixed-event nature of the forecasts enables us to examine efficiency by looking at the revision process. The panel structure allows us to control for aggregate shocks and to construct a measure of the news that impacted expectations in the period under study. The results suggest that respondents seem to rely for longer than appears to be optimal on their previous forecasts, and that they do not seem to use past information in an efficient manner. In turn, this means there are areas of opportunity to improve the accuracy of the forecasts, for instance, by taking into account the positive autocorrelation found in forecast revisions.
It would be natural to expect that shocks to producer prices, as they spill over through the prod... more It would be natural to expect that shocks to producer prices, as they spill over through the production chain, should eventually have some effect on consumer prices. This should hold true for “cost-push ” shocks that are expected to appear initially during the first stages of the production chain. In this case, it would also be natural, from a statistical point of view, for
Combination of forecasts from survey data is complicated by the frequent entry and exit of indivi... more 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 various combination methods in common use and propose a new method that projects actual outcomes on the equal-weighted forecast to adjust for biases and noise in the underlying forecasts. Through simulations and an application to inflation forecasts we show that the entry and exit of individual forecasters can have a large effect on the real time performance of conventional combination methods. The proposed projection works well in practice.
Empirical work documents substantial disagreement in inflation expectations obtained from survey ... more Empirical work documents substantial disagreement in inflation expectations obtained from survey data. Furthermore, the extent of such disagreement varies systematically over time in a way that reflects the level and variance of current inflation. This paper offers a simple explanation for these facts based on asymmetries in the forecasters ’ costs of over- and under-predicting inflation. Our model implies biased forecasts with positive serial correlation in forecast errors and a cross-sectional dispersion that rises with the level and the variance of the inflation rate. It also implies that forecast errors at different horizons can be predicted through the spread between the short- and long-term variance of inflation. We find empirically that these patterns are present in inflation forecasts from the Survey of Professional Forecasters. A constant bias component, not explained by asymmetric loss and rational expectations, is required to explain the shift in the sign of the bias obse...
This paper analyzes the pass-through of exchange rate to different price indexes in Mexico. The a... more This paper analyzes the pass-through of exchange rate to different price indexes in Mexico. The analysis is based on a vector autoregressive model (VAR) using monthly data from January 1997 to December 2010. The pass-through effects are calculated by means of accumulated impulse response functions to a recursively identified exchange rate shock. The results show that the exchange rate pass-through to import prices is complete, but it declines along the distribution chain in such a way that the impact on consumer prices is below 20 percent. Moreover, we find that the exchange rate pass-through seems to have decreased substantially from 2001 onwards, which coincides with the adoption of an inflation targeting regime by Banco de Mexico.
Disagreement in inflation expectations observed from survey data varies systematically over time ... more Disagreement in inflation expectations observed from survey data varies systematically over time in a way that reflects the level and variance of current inflation. This paper offers a simple explanation for these facts based on asymmetries in the forecasters’ costs of overand under-predicting inflation. Our model implies (i) biased forecasts; (ii) positive serial correlation in forecast errors; (iii) a cross-sectional dispersion that rises with the level and the variance of the inflation rate; and (iv) predictability of forecast errors at different horizons by means of the spread between the shortand long-term variance of inflation. We find empirically that these patterns are present in inflation forecasts from the Survey of Professional Forecasters. A constant bias component, not explained by asymmetric loss and rational expectations, is required to explain the shift in the sign of the bias observed for a substantial portion of forecasters around 1982.
To advance our understanding of the mechanisms through which monetary policy affect the economy, ... more To advance our understanding of the mechanisms through which monetary policy affect the economy, in this note we analyze the volatilities of the Mexican short-term interest rate and of the peso-Dollar exchange rate under two monetary policy instruments: a non-borrowed reserves requirement target (the "Corto") and an interest rate target. Using tests for multiple structural changes, we document that both volatilities decreased around the time Banco de Mexico started the transition from the former to the latter. With respect to the volatility transmission from interest rates to exchange rates and vice versa, we find, using a bivariate GARCH model and causality-in-variance tests, bi-causality during the period of the Corto, but no causal relation after the transition started.
In this paper we use data from Mexico to identify Dornbusch's (1976) exchange rate overshooti... more In this paper we use data from Mexico to identify Dornbusch's (1976) exchange rate overshooting hypothesis. We specify and estimate a structural cointegrated VAR that considers explicitly the presence of a set of long-run theoretical relations on macroeconomic variables (a purchasing power parity, an uncovered interest parity, a money demand, and a relation between domestic and U.S. output levels). We then impose a recursiveness assumption to identify the response of domestic variables to a monetary policy shock. The long-run restrictions embedded in the model are themselves identified, estimated, and tested using an ARDL methodology that is robust to the degree of persistence of the time series and, in particular, to whether they are trend- or first-difference stationary. With this approach, we are able to find that the response of the exchange rate to monetary policy shocks is consistent with Dornbusch's model.
We study the dynamics of the term-structure of interest rates in Mexico. Specifically, we investi... more We study the dynamics of the term-structure of interest rates in Mexico. Specifically, we investigate time variation in bond risk premia and the common factors that have influenced the behavior of the yield curve. We find that term-premia in government bonds appear to be time-varying. We then estimate a principal components model. We find that over 95% of the total variation in the yield curve can be explained by two factors. The first factor captures movements in the level of the yield curve, while the second one captures movements in the slope. Moreover, we find that the level factor is positively correlated with measures of long-term inflation expectations and that the slope factor is negatively correlated with the overnight interest rate.
We analyze inflation’s persistence in the 1980-2006 period for the ten largest Latin American eco... more We analyze inflation’s persistence in the 1980-2006 period for the ten largest Latin American economies using univariate time-series techniques. Although the estimated degree of inflation persistence appears to be different across countries, for the region as a whole the persistence seems to be very high. However, the estimated degree of persistence falls in all countries once we permit structural breaks in the mean of inflation. The timing of these breaks coincides with shifts in the monetary policy regimes and is similar across countries. Regardless of the changes in the mean, the degree of persistence appears to be decreasing in the region, even though for some countries persistence does not seem to be changing.
Since the adoption of inflation targeting, the seasonal appears to be the component that explains... more Since the adoption of inflation targeting, the seasonal appears to be the component that explains the major part of inflation's total variation in Mexico. In this context, we study the performance of seasonal time series models to forecast short-run inflation. Using multi-horizon evaluation techniques, we examine the real-time forecasting performance of four well-known seasonal models using data on 16 indices of the Mexican Consumer Price Index (CPI), including headline and core inflation. These models consider both, deterministic and stochastic seasonality. After selecting the best forecasting model for each index, we apply and compare two methods that aggregate hierarchical time series, the bottom-up method and an optimal combination approach. The best forecasts are able to compete with those taken from surveys of experts.
In this paper we use data from Mexico to identify Dornbusch's (1976) exchange rate overshooting h... more In this paper we use data from Mexico to identify Dornbusch's (1976) exchange rate overshooting hypothesis. We specify and estimate a structural cointegrated VAR that considers explicitly the presence of a set of long-run theoretical relations on macroeconomic variables (a purchasing power parity, an uncovered interest parity, a money demand, and a relation between domestic and U.S. output levels). We then impose a recursiveness assumption to identify the response of domestic variables to a monetary policy shock. The long-run restrictions embedded in the model are themselves identified, estimated, and tested using an ARDL methodology that is robust to the degree of persistence of the time series and, in particular, to whether they are trend-or first-difference stationary. With this approach, we are able to find that the response of the exchange rate to monetary policy shocks is consistent with Dornbusch's model.
Oxford Handbooks Online, 2011
… Research Paper No. …, 2010
We consider combinations of subjective survey forecasts and model-based forecasts from linear and... more We consider combinations of subjective survey forecasts and model-based forecasts from linear and non-linear univariate specifications as well as multivariate factoraugmented models. Empirical results suggest that a simple equal-weighted average of survey forecasts outperform the best model-based forecasts for a majority of macroeconomic variables and forecast horizons. Additional improvements can in some cases be gained by using a simple equal-weighted average of survey and model-based forecasts. We also provide an analysis of the importance of model instability for explaining gains from forecast combination. Analytical and simulation results uncover break scenarios where forecast combinations outperform the best individual forecasting model.
... by José Sidaoui, Carlos Capistrán, Daniel Chiquiar, Manuel Ramos ... G García-Castrillo in An... more ... by José Sidaoui, Carlos Capistrán, Daniel Chiquiar, Manuel Ramos ... G García-Castrillo in Anales del instituto de Estudios Marítimos (1980). 1 reader Save reference to library · Related research. Acerca del primer hallazgo de una fauna Ordovícica en el sector norte de la Riojana. ...
Uploads
Papers by Carlos Capistrán