|
on Econometric Time Series |
| By: | Martin Bruns; Helmut Lütkepohl |
| Abstract: | A central assumption for identifying structural shocks in vector autoregressive (VAR) models via heteroskedasticity is the time-invariance of the impact effects of the shocks. It is shown how that assumption can be tested when long-run restrictions are available for identifying structural shocks. The importance of performing such tests is illustrated by investigating the impact of fundamental shocks on stock prices in the U.S.. It is found that fundamental shocks post-1986 have become more important than in the pre-1986 period. |
| Keywords: | Structural vector autoregression, heteroskedasticity, cointegration, structural vector error correction model |
| JEL: | C32 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:diw:diwwpp:dp2103 |
| By: | Wang, Shu |
| Abstract: | This paper presents a high-frequency structural VAR framework for identifying oil price shocks and examining their uncertainty transmission in the U.S. macroeconomy and financial markets. Leveraging the stylized features of financial data - specifically, volatility clustering effectively captured by a GARCH model - this approach achieves global identification of shocks while allowing for volatility spillovers across them. Findings reveal that increased variance in aggregate demand shocks increases the oil-equity price covariance, while precautionary demand shocks, triggering heightened investor risk aversion, significantly diminish this covariance. A real-time forecast error variance decomposition further highlights that oil supply uncertainty was the primary source of oil price forecast uncertainty from late March to early May 2020, yet it contributed minimally during the 2022 Russian invasion of Ukraine. |
| Keywords: | Oil price, uncertainty, impulse response functions, structural VAR, forecast error variance decomposition, GARCH |
| JEL: | Q43 Q47 C32 C58 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:cegedp:307602 |
| By: | Liudas Giraitis (Queen Mary University of London, School of Economics and Finance); George Kapetanios (King's College London); Yufei Li (King's College London); Tien Chuong Nguyen (Vietnam National University) |
| Abstract: | This paper explores a semiparametric version of a time-varying regression, where a subset of the regressors have a fixed coefficient and the rest a time-varying one. We provide an estimation method and establish associated theoretical properties of the estimates and standard errors in extended for heterogeneity regression space. In particular, we show that the estimator of the fixed regression coefficient preserves the parametric rate of convergence, and that, despite of general heterogenous environment, the asymptotic normality property for components of regression parameters can be established and the estimators of standard errors have the same form as those given by White (1980). The theoretical properties of the estimator and good finite sample performance are confirmed by Monte Carlo experiments and illustrated by an empirical example on forecasting. |
| Keywords: | structural change, time-varying parameters, non-parametric estimation |
| JEL: | C13 C14 C50 |
| Date: | 2024–12–18 |
| URL: | https://d.repec.org/n?u=RePEc:qmw:qmwecw:985 |
| By: | Gabriel Rodriguez-Rondon |
| Abstract: | This paper introduces a new approach for estimating core inflation indicators based on common factors across a broad range of price indices. Specifically, by utilizing procedures for detecting multiple regimes in high-dimensional factor models, we propose two types of core inflation indicators: one incorporating multiple structural breaks and another based on Markov switching. The structural breaks approach can eliminate revisions for past regimes, though it functions as an offline indicator, as real-time detection of breaks is not feasible with this method. On the other hand, the Markov switching approach can reduce revisions while being useful in real time, making it a simple and robust core inflation indicator suitable for real-time monitoring and as a short-term guide for monetary policy. Additionally, this approach allows us to estimate the probability of being in different inflationary regimes. To demonstrate the effectiveness of these indicators, we apply them to Canadian price data. To compare the real-time performance of the Markov switching approach to the benchmark model without regime-switching, we assess their abilities to forecast headline inflation and minimize revisions. We find that the Markov switching model delivers superior predictive accuracy and significantly reduces revisions during periods of substantial inflation changes. Hence, our findings suggest that accounting for time-varying factors and parameters enhances inflation signal accuracy and reduces data requirements, especially following sudden economic shifts. |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2411.12845 |
| By: | Pierdomenico Duttilo |
| Abstract: | This PhD Thesis presents an investigation into the analysis of financial returns using mixture models, focusing on mixtures of generalized normal distributions (MGND) and their extensions. The study addresses several critical issues encountered in the estimation process and proposes innovative solutions to enhance accuracy and efficiency. In Chapter 2, the focus lies on the MGND model and its estimation via expectation conditional maximization (ECM) and generalized expectation maximization (GEM) algorithms. A thorough exploration reveals a degeneracy issue when estimating the shape parameter. Several algorithms are proposed to overcome this critical issue. Chapter 3 extends the theoretical perspective by applying the MGND model on several stock market indices. A two-step approach is proposed for identifying turmoil days and estimating returns and volatility. Chapter 4 introduces constrained mixture of generalized normal distributions (CMGND), enhancing interpretability and efficiency by imposing constraints on parameters. Simulation results highlight the benefits of constrained parameter estimation. Finally, Chapter 5 introduces generalized normal distribution-hidden Markov models (GND-HMMs) able to capture the dynamic nature of financial returns. This manuscript contributes to the statistical modelling of financial returns by offering flexible, parsimonious, and interpretable frameworks. The proposed mixture models capture complex patterns in financial data, thereby facilitating more informed decision-making in financial analysis and risk management. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2411.11847 |
| By: | Lorenzo Mori; Gert Peersman (-) |
| Abstract: | A common approach for estimating the macroeconomic effects of oil supply news employs SVAR-IV models identified using changes in oil futures prices around OPEC quota announcements as an instrument. However, we show that the reduced-form oil price innovations, structural shocks, and the instrumental variable in these estimations are all Granger-caused by financial variables, indicating informational deficiencies in the VAR model and contamination of the instrument. To resolve these issues, we incorporate financial indicators into the econometrician’s information set, yielding significantly different results. These include a sharper short-term output decline, lower and less persistent inflationary effects, and a reversal of the monetary policy response. Our results also show greater stability over time and the disappearance of puzzling responses. Finally, we identify similar issues in other prominent oil-market SVAR models, suggesting that informational deficiencies are a pervasive issue in oil-market research. |
| JEL: | C32 C36 E31 E32 F31 Q43 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:rug:rugwps:24/1099 |
| By: | Jeffrey Mollins; Rachit Lumb |
| Abstract: | This paper summarizes and assesses several of the most popular methods to seasonally adjust weekly data. The industry standard approach, known as X-13ARIMA-SEATS, is suitable only for monthly or quarterly data. Given the increased availability and promise of non-traditional data at higher frequencies, alternative approaches are required to extract relevant signals for monitoring and analysis. This paper reviews four such methods for high-frequency seasonal adjustment. We find that tuning the parameters of each method helps deliver a properly adjusted series. We optimize using a grid search and test for residual seasonality in each series. While no method works perfectly for every series, some methods are generally effective at removing seasonality in weekly data, despite the increased difficulty of accounting for the shock of the COVID-19 pandemic. Because seasonally adjusting high-frequency data is typically a difficult task, we recommend closely inspecting each series and comparing results from multiple methods whenever possible. |
| Keywords: | Econometric and statistical methods |
| JEL: | C1 C4 C52 C8 E01 E21 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocadp:24-17 |
| By: | ShengQuan Zhou |
| Abstract: | We introduce a Markov-functional approach to construct local volatility models that are calibrated to a discrete set of marginal distributions. The method is inspired by and extends the volatility interpolation of Bass (1983) and Conze and Henry-Labord\`ere (2022). The method is illustrated with efficient numerical algorithms in the cases where the constructed local volatility functions are: (1) time-homogeneous between or (2) continuous across, the successive maturities. The step-wise time-homogeneous construction produces a parsimonious representation of the local volatility term structure. |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2411.15053 |