A dynamic factor model for the Mexican economy: are common trends useful when predicting economic activity?

Abstract

In this paper we propose to use the common trends of the Mexican economy in order to predict economic activity one and two steps ahead. We exploit the cointegration properties of the macroeconomic time series, such that, when the series are I(1) and cointegrated, there is a factor representation, where the common factors are the common trends of the macroeconomic variables. Thus, we estimate a large non-stationary dynamic factor model using principal components (PC) as suggested by Bai (J Econom 122(1): 2004), where the estimated common factors are used in a factor-augmented vector autoregressive model to forecast the Global Index of Economic Activity. Additionally, we estimate the common trends through partial least squares. The results indicate that the common trends are useful to predict Mexican economic activity, and reduce the forecast error with respect to benchmark models, mainly when estimated using PC.

A nowcasting approach to generate timely estimates of Mexican economic activity: An application to the period of COVID-19

“…The variables to estimate the DFM are selected by using the criteria of timely and contemporaneous correlation with respect to y * . In this sense, the model differs from the traditional literature on large DFMs, which uses a large amount of economic and financial variables; see, for example, Corona et al (2017a) who use 211 time series to estimate the DFM for the Mexican case with the goal of generating forecasts for the levels of IGAE. On the other hand, Gálvez-Soriano (2020) uses approximately 30 selected time series to generate nowcasts of Mexican quarterly GDP.…”

“…In addition, we compare our results to Corona et al (2017a), which forecasts IGAE levels two steps ahead. To have comparable results between such study and this one, we take the median of the root squared errors obtained by the former just for the first step forward, which is between 0.4 and 0.5, while the current work generates a median AEs of 0.397 for the last In order to contrast the results of our approach with those obtained by other procedures, we consider the following two alternative models:…”

“…• DFM without nontraditional information: We estimate a traditional DFM similar to Corona et al (2017a) or Gálvez-Soriano (2020), but using only economic and financial time series, i.e. without considering the social mobility index and the relevant topics extracted from Google Trends.…”

“…DFM methodology has already been used to nowcast or predict the Mexican economy. Corona et al (2017a), one of the first works in this line, estimated common trends in a large and nonstationary DFM to predict the Global Economic Activity Indicator (IGAE in Spanish) two steps ahead and concluded that the error prediction was reduced with respect to some benchmarking univariate and multivariate time-series models. Caruso (2018) focuses on international indicators, mainly for the US economy, to show that its nowcasts of quarterly GDP outperform the predictions obtained by professional forecasters.…”

Timely Estimates of the Monthly Mexican Economic Activity

“…To generate timely estimates, Delajara et al (2016) use small-scale mixedfrequency DFM to nowcast, backcast and forecast GDP figures. Also, in one of the first works along this line Corona et al (2017a), estimated common trends in a large and nonstationary DFM to predict the IGAE levels two steps ahead and concluded that error prediction was reduced with respect to some benchmarking univariate and multivariate time-series models. Caruso (2018) focuses on international indicators, mainly for the US economy, to show that its nowcasts of quarterly GDP outperform the predictions obtained by professional forecasters.…”