Mixed Frequency Approach Research Articles

A nowcasting model for Ecuador: Implementing a time-varying mean output growth

We propose a model to nowcast the annual growth rate of real GDP for Ecuador, whose economy lacks timely macroeconomic information for some key variables and has gone through unstable periods due to its dependence on oil exports. Our specification combines monthly information for 30 macroeconomic and financial variables with quarterly information for real GDP in a mixed-frequency approach. Our setup includes a time-varying coefficient on the mean annual growth rate of output to allow the model to incorporate prolonged periods of low or high growth. The model produces more accurate nowcasts of real output growth in pseudo out-of-sample exercises than a nowcasting model that assumes a constant mean real GDP growth rate. We also conduct sensitivity analyses on our nowcasting model within the time-varying mean setup and find that including financial variables can be detrimental to the performance of the proposed model.

A Mixed Frequency Approach for Stock Returns and Valuation Ratios

We employ a Mixed-Frequency VAR to study the effect of four valuation ratios (the price-dividend ratio, the price-earnings ratio, the Cyclically Adjusted Price Earnings Ratio and the Total Return Cyclically Adjusted Price Earnings Ratio) on the US stock market. We quantify the interaction between high and low frequency data. We show that all valuation ratios (observed at a monthly frequency) significantly affect stock market returns (observed at a daily frequency) at both long and short horizons.

A Nowcasting Model for the Growth Rate of Real GDP of Ecuador: Implementing a Time-Varying Intercept

This paper proposes a model to nowcast the annual growth rate of real GDP for Ecuador. The specification combines monthly information of 28 macroeconomic variables with quarterly information of real GDP in a mixed-frequency approach. Additionally, our setup includes a time-varying mean coefficient on the annual growth rate of real GDP to allow the model to incorporate prolonged periods of low growth, such as those experienced during secular stagnation episodes. The model produces reasonably good nowcasts of real GDP growth in pseudo out-of-sample exercises and is marginally more precise than a simple ARMA model.

Identifying Long-Run Risks: A Bayesian Mixed-Frequency Approach

Identifying Long-Run Risks: A Bayesian Mixed-Frequency Approach

Mixed-Frequency Macro-Financial Spillovers

We develop a new methodology to analyse spillovers between the real and financial sides of the economy that employs a mixed-frequency modelling approach. This enables high-frequency financial and low-frequency macroeconomic data series to be employed directly, avoiding the data aggregation and information loss incurred when using common-frequency methods. In a detailed analysis of macro-financial spillovers for the US economy, we find that the additional high-frequency information preserved by our mixed-frequency approach results in estimated spillovers that are typically substantially higher than those from an analogous common-frequency approach and are more consistent with known in-sample events. We also show that financial markets are typically net transmitters of shocks to the real side of the economy, particularly during turbulent market conditions, but that the bond and equity markets act heterogeneously in both transmitting and receiving shocks to the non-financial sector. We observe substantial short and medium-run variation in macro-financial spillovers that is statistically associated with key variables related to financial and macroeconomic fundamentals; the values of the term spread, VIX and unemployment rate in particular appear to be important determinants of macro- financial spillovers.

A mixed frequency approach to the forecasting of private consumption with ATM/POS data

The recent worldwide development and widespread use of electronic payment systems has provided an opportunity to explore new sources of data for the monitoring of macroeconomic activity. In this paper, we analyse the usefulness of data collected from automated teller machines (ATM) and points-of-sale (POS) for nowcasting and forecasting quarterly private consumption. We take advantage of the availability of such high frequency data by using mixed data sampling (MIDAS) regressions. A comparison of several MIDAS variants proposed in the literature is conducted, and both single- and multi-variable models are considered, together with different information sets within the quarter. Given the substantial use of ATM/POS technology in Portugal, it is important to assess the information content of this data for tracking private consumption. We find that ATM/POS data display a better forecast performance than typical indicators, which reinforces the potential usefulness of this novel type of data among policymakers and practitioners.

Testing for Granger causality with mixed frequency data

We develop Granger causality tests that apply directly to data sampled at different frequencies. We show that taking advantage of mixed frequency data allows us to better recover causal relationships when compared to the conventional common low frequency approach. We also show that the new causality tests have higher local asymptotic power as well as more power in finite samples compared to conventional tests. In an empirical application involving U.S. macroeconomic indicators, we show that the mixed frequency approach and the low frequency approach produce very different causal implications, with the former yielding more intuitively appealing result.

Testing for Granger Causality with Mixed Frequency Data

We develop Granger causality tests that apply directly to data sampled at different frequencies. We show that taking advantage of mixed frequency data allows us to better recover causal relationships when compared to the conventional common low frequency approach. We also show that the new causality tests have higher local asymptotic power as well as more power in finite samples compared to conventional tests. In an empirical application involving U.S. macroeconomic indicators, we show that the mixed frequency approach and the low frequency approach produce very different causal implications, with the former yielding more intuitively appealing result.

Sluggish Private Investment in Japan's Lost Decade: Mixed Frequency Vector Autoregression Approach

It is well known that sluggish private investment plagued the Japanese macroeconomy in the Lost Decade. Past empirical papers have not reached a clear consensus on what caused the investment slowdown. This paper sheds new light on this issue by applying mixed frequency vector autoregressive techniques to monthly stock prices, quarterly bank loans, firm profit, and private investment. First, we reveal a spiral of declining stock prices, profit, and investment. Second, monthly stock prices explain as much as 50.3% of the long-run forecast error variance of investment. Third, the stagnation of bank loans is a consequence (and not a cause) of declining stock prices and investment. Aggregating monthly stock prices into a quarterly level underestimates the influence of stock prices. It also weakens the statistical significance of the spiral of stock prices, profit, and investment. The mixed frequency approach therefore yields richer economic insights into Japan's sluggish investment than the classical single-frequency approach.

Nowcasting and Short-term Forecasting of Chinese Quarterly GDP: Mixed Frequency Approach

Conventional macroeconomic forecasting model must change the mixed frequency data into the same frequency data by means of aggregation and interpolation, which ignores the information of high frequency data and decreases the timeliness and accuracy of nowcasting and short-term forecasting. Using monthly and quarterly macroeconomic data, this paper apply mixed data sampling (MIDAS) model and mixed-frequency VAR model (MF-VAR) to nowcast and forecast Chinese quarterly GDP growth rate. The results show that MIDAS model considering an autoregressive item tends to perform better in shorter horizons, whereas MF-VAR model in longer horizons. Additionally, the pooled forecast of MIDAS model and MF-VAR model outperform the individual models. Finally, forecasting results reveal that China's quarterly GDP growth will rebound steadily from the beginning of the third quarter of 2012

Identifying Long-Run Risks: A Bayesian Mixed-Frequency Approach

We develop a nonlinear state-space model that captures the joint dynamics of consumption, dividend growth, and asset returns. Building on Bansal and Yaron (2004), our model consists of an economy containing a common predictable component for consumption and dividend growth and multiple stochastic volatility processes. The estimation is based on annual consumption data from 1929 to 1959, monthly consumption data after 1959, and monthly asset return data throughout. We maximize the span of the sample to recover the predictable component and use high-frequency data, whenever available, to efficiently identify the volatility processes. Our Bayesian estimation provides strong evidence for a small predictable component in consumption growth (even if asset return data are omitted from the estimation). Three independent volatility processes capture different frequency dynamics; our measurement error specification implies that consumption is measured much more precisely at an annual than monthly frequency; and the estimated model is able to capture key asset-pricing facts of the data.

Forecasting Covariance Matrices: A Mixed Frequency Approach

This paper proposes a new method for forecasting covariance matrices of financial returns. the model mixes volatility forecasts from a dynamic model of daily realized volatilities estimated with high-frequency data with correlation forecasts based on daily data. This new approach allows for flexible dependence patterns for volatilities and correlations, and can be applied to covariance matrices of large dimensions. The seperate modeling of volatility and correlation forecasts considerably reduces the estimation and measurement error implied by the joint estimation and modeling of covariance matrix dynamics. Our empirical results show that the new mixing approach provides superior forecasts compared to multivariate volatility specifications using single sources of information.

Forecasting data revisions of GDP: a mixed frequency approach

Releases of GDP data undergo a series of revisions over time. These revisions have an impact on the results of macroeconometric models documented by the growing literature on real-time data applications. Revisions of U.S. GDP data can be explained and are partly predictable according to Faust et al. (J. Money Credit Bank. 37(3):403–419, 2005) or Fixler and Grimm (J. Product. Anal. 25:213–229, 2006). This analysis proposes the inclusion of mixed frequency data for forecasting GDP revisions. Thereby, the information set available around the first data vintage can be better exploited than the pure quarterly data. In-sample and out-of-sample results suggest that forecasts of GDP revisions can be improved by using mixed frequency data.

Hedonic Prices and Implicit Markets: Product Differentiation in Pure Competition

A class of differentiated products is completely described by a vector of objectively measured characteristics. Observed product prices and the specific amounts of characteristics associated with each good define a set of implicit or "hedonic" prices. A theory of hedonic prices is formulated as a problem in the economics of spatial equilibrium in which the entire set of implicit prices guides both consumer and producer locational decisions in characteristics space. Buyer and seller choices, as well as the meaning and nature of market equilibrium, are analyzed. Empirical implications for hedonic price regressions and index number construction are pointed out.