Search results

Many recent chapters have investigated whether data from internet search engines such as Google can help improve nowcasts or short-term forecasts of macroeconomic variables. These chapters construct variables based on Google searches and use them as explanatory variables in regression models. We add to this literature by nowcasting using dynamic model selection (DMS) methods which allow for model switching between time-varying parameter regression models. This is potentially useful in an environment of coefficient instability and over-parameterization which can arise when forecasting with Google variables. We extend the DMS methodology by allowing for the model switching to be controlled by the Google variables through what we call “Google probabilities”: instead of using Google variables as regressors, we allow them to determine which nowcasting model should be used at each point in time. In an empirical exercise involving nine major monthly US macroeconomic variables, we find DMS methods to provide large improvements in nowcasting. Our use of Google model probabilities within DMS often performs better than conventional DMS methods.

This chapter uses an application to explore the utility of Bayesian quantile regression (BQR) methods in producing density nowcasts. Our quantile regression modeling strategy is designed to reflect important nowcasting features, namely the use of mixed-frequency data, the ragged-edge, and large numbers of indicators (big data). An unrestricted mixed data sampling strategy within a BQR is used to accommodate a large mixed-frequency data set when nowcasting; the authors consider various shrinkage priors to avoid parameter proliferation. In an application to euro area GDP growth, using over 100 mixed-frequency indicators, the authors find that the quantile regression approach produces accurate density nowcasts including over recessionary periods when global-local shrinkage priors are used.

This study aims to examine whether and when real-time updated online search engine data such as the daily Baidu Index can be useful for improving the accuracy of tourism demand nowcasting once monthly official statistical data, including historical visitor arrival data and macroeconomic variables, become available.

This study is the first attempt to use the LASSO-MIDAS model proposed by Marsilli (2014) to field of the tourism demand forecasting to deal with the inconsistency in the frequency of data and the curse problem caused by the high dimensionality of search engine data.

The empirical results in the context of visitor arrivals in Hong Kong show that the application of a combination of daily Baidu Index data and monthly official statistical data produces more accurate nowcasting results when MIDAS-type models are used. The effectiveness of the LASSO-MIDAS model for tourism demand nowcasting indicates that such penalty-based MIDAS model is a useful option when using high-dimensional mixed-frequency data.

This study represents the first attempt to progressively compare whether there are any differences between using daily search engine data, monthly official statistical data and a combination of the aforementioned two types of data with different frequencies to nowcast tourism demand. This study also contributes to the tourism forecasting literature by presenting the first attempt to evaluate the applicability and effectiveness of the LASSO-MIDAS model in tourism demand nowcasting.

We develop a framework for measuring and monitoring business cycles in real time. Following a long tradition in macroeconometrics, inference is based on a variety of indicators of economic activity, treated as imperfect measures of an underlying index of business cycle conditions. We extend existing approaches by permitting for heterogenous lead–lag patterns of the various indicators along the business cycles. The framework is well suited for high-frequency monitoring of current economic conditions in real time – nowcasting – since inference can be conducted in the presence of mixed frequency data and irregular patterns of data availability. Our assessment of the underlying index of business cycle conditions is accurate and more timely than popular alternatives, including the Chicago Fed National Activity Index (CFNAI). A formal real-time forecasting evaluation shows that the framework produces well-calibrated probability nowcasts that resemble the consensus assessment of the Survey of Professional Forecasters.

The development of models for variables sampled at different frequencies has attracted substantial interest in the recent literature. In this article, we discuss classical and Bayesian methods of estimating mixed-frequency VARs, and use them for forecasting and structural analysis. We also compare mixed-frequency VARs with other approaches to handling mixed-frequency data.

Entering and exiting the Pandemic Recession, the author study the high-frequency real-activity signals provided by a leading nowcast, the ADS Index of Business Conditions produced and released in real time by the Federal Reserve Bank of Philadelphia. The author tracks the evolution of real-time vintage beliefs and compares them to a later-vintage chronology. Real-time ADS plunges and then swings as its underlying economic indicators swing, but the ADS paths quickly converge to indicate a return to brisk positive growth by mid-May. The author shows, moreover, that the daily real-activity path was highly correlated with the daily COVID-19 cases. Finally, the author provides a comparative assessment of the real-time ADS signals provided when exiting the Great Recession.

Forecasts from dynamic factor models potentially benefit from refining the data set by eliminating uninformative series. This paper proposes to use prediction weights as provided by the factor model itself for this purpose. Monte Carlo simulations and an empirical application to short-term forecasts of euro area, German, and French GDP growth from unbalanced monthly data suggest that both prediction weights and least angle regressions result in improved nowcasts. Overall, prediction weights provide yet more robust results.

This chapter analyses potentials of including online search volume data in modeling the demand series of consumer products. Forecasting future demand for products of a company represents one of the important parts of planning and conducting business in general. Thus, the purpose of this chapter is twofold. The first purpose is to give a critical overview of the existing research on the topic of forecasting and nowcasting demand and consumption. The other purpose is to fill the gap in the literature by empirically comparing several approaches of modeling and forecasting demand and consumption on real data. Results of the empirical analysis show that including online search volume data can enhance modeling and forecasting of demand series, especially in times of economic downturns. Thus, it is advised to use such an approach in modeling of consumer demand in a business so that better business performance in terms of profits could be obtained.

This chapter investigates the impact of different state correlation assumptions for out-of-sample performance of unobserved components (UC) models with stochastic volatility. Using several measures of US inflation the author finds that allowing for correlation between inflation’s trend and cyclical (or gap) components is a useful feature to predict inflation in the short run. In contrast, orthogonality between such components improves the out-of-sample performance as the forecasting horizon widens. Accordingly, trend inflation from orthogonal trend-gap UC models closely tracks survey-based measures of long-run inflation expectations. Trend dynamics in the correlated-component case behave similarly to survey-based nowcasts. To carry out estimation, an efficient algorithm which builds upon properties of Toeplitz matrices and recent advances in precision-based samplers is provided.