Search results

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.

The production planning problem with fine-grained information has hardly been considered in practice. The purpose of this study is to investigate the data-driven production planning problem when a manufacturer can observe historical demand data with high-dimensional mixed-frequency features, which provides fine-grained information.

In this study, a two-step data-driven optimization model is proposed to examine production planning with the exploitation of mixed-frequency demand data is proposed. First, an Unrestricted MIxed DAta Sampling approach is proposed, which imposes Group LASSO Penalty (GP-U-MIDAS). The use of high frequency of massive demand information is analytically justified to significantly improve the predictive ability without sacrificing goodness-of-fit. Then, integrated with the GP-U-MIDAS approach, the authors develop a multiperiod production planning model with a rolling cycle. The performance is evaluated by forecasting outcomes, production planning decisions, service levels and total cost.

Numerical results show that the key variables influencing market demand can be completely recognized through the GP-U-MIDAS approach; in particular, the selected accuracy of crucial features exceeds 92%. Furthermore, the proposed approach performs well regarding both in-sample fitting and out-of-sample forecasting throughout most of the horizons. Taking the total cost and service level obtained under the actual demand as the benchmark, the mean values of both the service level and total cost differences are reduced. The mean deviations of the service level and total cost are reduced to less than 2.4%. This indicates that when faced with fluctuating demand, the manufacturer can adopt the proposed model to effectively manage total costs and experience an enhanced service level.

Compared with previous studies, the authors develop a two-step data-driven optimization model by directly incorporating a potentially large number of features; the model can help manufacturers effectively identify the key features of market demand, improve the accuracy of demand estimations and make informed production decisions. Moreover, demand forecasting and optimal production decisions behave robustly with shifting demand and different cost structures, which can provide manufacturers an excellent method for solving production planning problems under demand uncertainty.

The purpose of this study is to forecast the development performance of important economies in a smart city using mixed-frequency data.

This study introduces reverse unrestricted mixed-data sampling (RUMIDAS) to support vector regression (SVR) to develop a novel RUMIDAS-SVR model. The RUMIDAS-SVR model was estimated using a quadratic programming problem. The authors then use the novel RUMIDAS-SVR model to forecast the development performance of all high-tech listed companies, an important sector of the economy reflecting the potential and dynamism of urban economic development in Shanghai using the mixed-frequency consumer price index (CPI) producer price index (PPI), and consumer confidence index (CCI) as predictors.

The empirical results show that the established RUMIDAS-SVR is superior to the competing models with regard to mean absolute error (MAE) and root-mean-squared error (RMSE) and multi-source macroeconomic predictors contribute to the development performance forecast of important economies.

Smart city policy makers should create a favourable macroeconomic environment, such as controlling inflation or stabilising prices for companies within the city, and companies within the important city economic sectors should take initiative to shoulder their responsibility to support the construction of the smart city.

This study contributes to smart city monitoring by proposing and developing a new model, RUMIDAS-SVR, to help the construction of smart cities. It also empirically provides strategic insights for smart city stakeholders.

The focus of the current research is to examine whether mixed-frequency investor sentiment affects stock volatility in the China A-shares stock market.

Mixed-frequency sampling models are employed to find the relationship between stock market volatility and mixed-frequency investor sentiment. Principal analysis and MIDAS-GARCH model are used to calibrate the impact of investor sentiment on the large-horizon components of volatility of Shanghai composite stocks.

The results show that the volatility in Chinese stock market is positively influenced by B–W investor sentiment index, when the sentiment index encompasses weighted mixed frequencies with different horizons. In particular, the impact of mixed-frequency investor sentiment is most significantly on the large-horizon components of volatility. Moreover, it is demonstrated that mixed-frequency sampling model has better explanatory powers than exogenous regression models when accounting for the relationship between investor sentiment and stock volatility.

Given the various unique features of Chinese stock market and its importance as the major representative of world emerging markets, the findings of the current paper are of particularly scholarly and practical significance by shedding lights to the applicableness GARCH-MIDAS in the focused frontiers.

A more accurate and insightful understanding of volatility has always been one of the core scholarly pursuits since the influential structural time series modeling of Engle (1982) and the seminal work of Engle and Rangel (2008) attempting to accommodate macroeconomic factors into volatility models. However, the studies in this regard are so far relatively scarce with mixed conclusions. The current study fills such gaps with improved MIDAS-GARCH approach and new evidence from Shanghai A-share market.

This article proposes a new approach to detecting the presence of common cyclical features when several time series are sampled at different frequencies. We generalize the common-frequency approach introduced by Engle and Kozicki (1993) and Vahid and Engle (1993). We start with the mixed-frequency VAR representation investigated in Ghysels (2012) for stationary time series. For non-stationary time series in levels, we show that one has to account for the presence of two sets of long-run relationships. The first set is implied by identities stemming from the fact that the differences of the high-frequency I (1) regressors are stationary. The second set comes from possible additional long-run relationships between one of the high-frequency series and the low-frequency variables. Our transformed vector error-correction model (VECM) representations extend the results of Ghysels (2012) and are important for determining the correct set of variables to be used in a subsequent common cycle investigation. This fact has implications for the distribution of test statistics and for forecasting. Empirical analyses with quarterly real gross national product (GNP) and monthly industrial production indices for, respectively, the United States and Germany illustrate our new approach. We also conduct a Monte Carlo study which compares our proposed mixed-frequency models with models stemming from classical temporal aggregation methods.

This paper is concerned with estimation of the parameters of a high-frequency VAR model using mixed-frequency data, both for the stock and for the flow case. Extended Yule–Walker estimators and (Gaussian) maximum likelihood type estimators based on the EM algorithm are considered. Properties of these estimators are derived, partly analytically and by simulations. Finally, the loss of information due to mixed-frequency data when compared to the high-frequency situation as well as the gain of information when using mixed-frequency data relative to low-frequency data is discussed.

This study is the first to investigate the causal relationship between Bitcoin and equity price returns by sectors. Previous studies have focused on aggregated indices such as S&P500, Nasdaq and Dow Jones, but this study uses mixed frequency and disaggregated data at the sectoral level. This allows the authors to examine the nature, direction and strength of causality between Bitcoin and equity prices in different sectors in more detail.

This paper utilizes an Unrestricted Asymmetric Mixed Data Sampling (U-AMIDAS) model to investigate the effect of high-frequency Bitcoin returns on a low-frequency series equity returns. This study also examines causality running from equity to Bitcoin returns by sector. The sample period covers United States (US) data from 3 Jan 2011 to 14 April 2023 across nine sectors: materials, energy, financial, industrial, technology, consumer staples, utilities, health and consumer discretionary.

The study found that there is no causality running from Bitcoin to equity returns in any sector except for the technology sector. In the tech sector, lagged Bitcoin returns Granger cause changes in future equity prices asymmetrically. This means that falling Bitcoin prices significantly influence the tech sector during market pullbacks, but the opposite cannot be said during market rallies. The findings are consistent with those of other studies that have established that during market pullbacks, individual asset prices have a tendency to decline together, whereas during market rallies, they have a tendency to rise independently. In contrast, this study finds evidence of causality running from all sectors of the equity market to Bitcoin.

The findings have significant implications for investors and fund managers, emphasizing the need to consider the asymmetric causality between Bitcoin and the tech sector. Investors should avoid excessive exposure to both Bitcoin and tech stocks in their portfolio, as this may lead to significant drawdowns during market corrections. Diversification across different asset classes and sectors may be a more prudent strategy to mitigate such risks.

The study's findings underscore the need for investors to pay close attention to the frequency and disaggregation of data by sector in order to fully understand the true extent of the relationship between Bitcoin and the equity market.

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.