The Predictive Power of the Business and Bank Sentiment of Firms: A High-Dimensional Granger Causality Approach

Abstract

Abstract. We study the predictive power of industry-specific economic sentiment indicators for future macro-economic developments. In addition to the sentiment of firms towards their own business situation, we study their sentiment with respect to the banking sector -their main credit providers. The use of industry-specific sentiment indicators results in a high-dimensional forecasting problem. To identify the most predictive industries, we present a bootstrap Granger Causality test based on the Adaptive Lasso. This test is more powerful than the standard Wald test in such high-dimensional settings. Forecast accuracy is improved by using only the most predictive industries rather than all industries.

Forecasting economic indicators using a consumer sentiment index: Survey‐based versus text‐based data

“…The extent to which the economic sentiment index offers relevant, timely insights regarding economic conditions can be translated into a Granger causality framework. A (set of) time series is said to Granger‐cause another time series if the former has incremental predictive power for predicting the latter (Wilms, Gelper, & Croux, ). In this section, we discuss the Granger causality test results to confirm that our newly created index has causality and predictive power for key economic indicators.…”

Empirical modelling of survey-based expectations for the design of economic indicators in five European regions

“…Bruestle and Crain (2015) have showed that controlling for significant versus insignificant changes in consumer confidence improved the accuracy of household expenditure forecasting models. Wilms et al (2016) have suggested selecting survey indicators from the most predictive industries in order to improve the predictive capacity of survey data. Similarly, Dreger and Kholodilin (2013) have noted that better performing survey-based indicators should be built upon pre-selection methods and data-driven approaches to determine the weights.…”

“…Accordingly, survey results provide important information about agents' economic expectations, allowing comparisons among different countries' business cycles. On the one hand, sectoral results of the surveys have been often used as partial indicators for the construction of more general aggregate economic indicators and for the estimation of macro magnitudes through their introduction in econometric models (Abberger, 2007;Bruestle and Crain, 2015;Graff, 2010;Hanson et al, 2005;Lehmann and Wohlrabe, 2017;Wilms et al, 2016). On the other hand, survey-based expectations have also been introduced into behavioural equations postulated by economic theory such as the Phillips curve and to evaluate the formation of expectations, as they provide a direct measure of expectations to test the rationality of agents (Altug and Çakmakli, 2016;Bovi, 2013;Jean-Baptiste, 2012;Lee, 1994;Miah et al, 2016;Paloviita, 2006).…”

A novel robust structural quadratic forecasting model and applications

“…To overcome COD, variable selection, which distinguishes important variables from noisy ones, is a popular and powerful technique in the realm of forecasting (Alberto et al, 2010; Hrdle et al, 2009; Refenes & Zapranis, 1999; Zeng, 2017). It can be regarded as a simplification procedure that extracts valuable data information from data by selecting important variable with predictive power (Ballings & Van den Poel, 2015; Bertsimas & Copenhaver, 2014; Ma et al, 2016; Wilms et al, 2016). In recent decades, variable selection focuses on penalizing methods that consider a minimization problem consisting of loss function and regularization terms (Guyon & Elisseeff, 2003; Nataraja & Johnson, 2011).…”