|
on Econometric Time Series |
| By: | Seisho Sato (Graduate School of Economics, University of Tokyo); Naoto Kunitomo (Gendai-Finance-Center, Tokyo Keizai University) |
| Abstract: | In this study, we investigate a new smoothing approach to estimate the hidden states of random variables and to handle multiple noisy non-stationary time series data. Kunitomo and Sato (2021) have developed a new method to solve the smoothing problem of hidden random variables, and the resulting separating information maximum likelihood (SIML) method enables the handling of multivariate non-stationary time series. We continue to investigate the filtering problem. In particular, we propose the backward SIML smoothing method and the multi-step smoothing method to address the initial value issue. The resulting filtering methods can be interpreted in the time and frequency domains. |
| Date: | 2021–07 |
| URL: | http://d.repec.org/n?u=RePEc:cfi:fseres:cf517&r= |
| By: | Mikkel Bennedsen (Department of Economics and Business Economics, Aarhus University and CREATES); Asger Lunde (Copenhagen Economics and CREATES); Neil Shephard (Department of Economics and Department of Statistics, Harvard University); Almut E.D. Veraart (Imperial College London and CREATES) |
| Abstract: | This paper develops likelihood-based methods for estimation, inference, model selection, and forecasting of continuous-time integer-valued trawl processes. The full likelihood of integer-valued trawl processes is, in general, highly intractable, motivating the use of composite likelihood methods, where we consider the pairwise likelihood in lieu of the full likelihood. Maximizing the pairwise likelihood of the data yields an estimator of the parameter vector of the model, and we prove consistency and asymptotic normality of this estimator. The same methods allow us to develop probabilistic forecasting methods, which can be used to construct the predictive distribution of integer-valued time series. In a simulation study, we document good finite sample performance of the likelihood-based estimator and the associated model selection procedure. Lastly, the methods are illustrated in an application to modelling and forecasting financial bid-ask spread data, where we find that it is beneficial to carefully model both the marginal distribution and the autocorrelation structure of the data. We argue that integer-valued trawl processes are especially well-suited in such situations. |
| Keywords: | Integer valued trawl process, Lévy basis, composite likelihood, pairwise likelihood, estimation, model selection, forecasting |
| JEL: | C01 C13 C22 C51 C53 G17 |
| Date: | 2021–07–27 |
| URL: | http://d.repec.org/n?u=RePEc:aah:create:2021-12&r= |
| By: | Josep Lluís Carrion-i-Silvestre (AQR-IREA, University of Barcelona); María Dolores Gadea (University of Zaragoza) |
| Abstract: | The paper proposes a sequential statistical procedure to test for the presence of level shifts affecting bounded time series, regardless of their order of integration. The paper shows that bounds are relevant for the statistic that assume that the time series are integrated of order one, whereas they do not affect the limiting distribution of the statistic that is defined for time series that are integrated of order zero. The paper proposes a union rejection statistic for bounded processes that does not require information about the order of integration of the stochastic processes. The model specification is general enough to consider the existence of structural breaks that can affect either the level of the time series and/or the bounds that limit its evolution. Monte Carlo simulations indicate that the procedure works well in finite samples. An empirical application that focuses on the Swiss franc against the euro exchange rate evolution illustrates the usefulness of the proposal. |
| Keywords: | Structural breaks, bounded processes, changing bounds JEL classification: C12, C22 |
| Date: | 2021–07 |
| URL: | http://d.repec.org/n?u=RePEc:aqr:wpaper:202106&r= |
| By: | Christiane Baumeister; Danilo Leiva-León; Eric Sims |
| Abstract: | In this paper, we develop a novel dataset of weekly economic conditions indices for the 50 U.S. states going back to 1987 based on mixed-frequency dynamic factor models with weekly, monthly, and quarterly variables that cover multiple dimensions of state economies. We show that there is considerable heterogeneity in the length, depth, and timing of business cycles across individual states. We assess the role of states in national recessions and propose an aggregate indicator that allows us to gauge the overall weakness of the U.S. economy. We also illustrate the usefulness of these state-level indices for quantifying the main forces contributing to the economic collapse caused by the COVID-19 pandemic and for evaluating the e effectiveness of federal economic policies like the Paycheck Protection Program. |
| Keywords: | local economic conditions, government policies, weekly indicators, state economies, cross-state heterogeneity, mixed-frequency dynamic factor model, economic weakness index, Markov-switching, recession probabilities |
| JEL: | C32 C55 E32 E66 |
| Date: | 2021–07 |
| URL: | http://d.repec.org/n?u=RePEc:een:camaaa:2021-55&r= |
| By: | Martin Bruns (University of East Anglia); Michele Piffer (King's College London) |
| Abstract: | We extend the Smooth Transition Vector Autoregressive model to allow for identification via a combination of external instruments and sign restrictions, while estimating rather than calibrating the parameters ruling the nonlinearity of the model. We hence o er an alternative to using the recursive identification with selected calibrated parameters, which is the main approach currently available. We use the model to study how the effects of monetary policy shocks change over the business cycle. We show that financial variables, inflation and output respond to a monetary shock more in a recession than in an expansion, in line with the predictions from the financial accelerator literature. |
| Keywords: | Nonlinear models, proxy SVARs, monetary policy shocks, sign restrictions. |
| JEL: | C32 E52 |
| Date: | 2021–08–05 |
| URL: | http://d.repec.org/n?u=RePEc:uea:ueaeco:2021-07&r= |
| By: | Jesús Otero (Facultad de Economía, Universidad del Rosario, Colombia); Theodore Panagiotidis (Department of Economics, University of Macedonia, Greece; Rimini Centre for Economic Analysis); Georgios Papapanagiotou (Department of Economics, University of Macedonia, Greece) |
| Abstract: | We undertake Monte Carlo simulation experiments to examine the effect of changing the frequency of observations and the data span on the Phillips, Shi, and Yu (2015) Generalised Supremum ADF (GSADF) test for explosive behaviour via Monte Carlo simulations. We find that when a series is characterised by multiple bubbles (periodically collapsing), decreasing the frequency of observations is associated with profound power losses for the test. We illustrate the effects of temporal aggregation by examining two real house price data bases, namely the S&P Case-Shiller real house prices and the international real house price indices available at the Federal Reserve Bank of Dallas. |
| Keywords: | Exuberant/explosive behaviour, bubbles, Monte Carlo, house prices |
| JEL: | C15 C22 |
| Date: | 2021–07 |
| URL: | http://d.repec.org/n?u=RePEc:rim:rimwps:21-13&r= |
| By: | Milda Norkute (Bank of Lithuania, Vilnius University); Joakim Westerlund (Lund University, Deakin University); Ovidijus Stauskas (Lunk University) |
| Abstract: | In this study, we re-visit the factor analytical (FA) approach for (near unit root) dynamic panel data models, whose asymptotic distribution has been shown to be normal and well centered at zero without the need for valid instruments or correction for bias. It is therefore very appealing. The question is: Does the appeal of FA, which so far has only been documented for fixed effects panels, extends to panels with incidental trends? This is an important question, because many persistent variables are trending. The answer turns out to be negative. In particular, while consistent, the asymptotic normality of FA breaks down when there is an exact unit root present, which limits its applicability. |
| Keywords: | Dynamic panel data models, Unit root, Factor analytical method. |
| JEL: | C12 C13 C33 |
| Date: | 2021–07–29 |
| URL: | http://d.repec.org/n?u=RePEc:lie:wpaper:91&r= |
| By: | João A. Bastos; Jorge Caiado |
| Abstract: | We compare a data-driven domain agnostic set of canonical features with a smaller collection of features that capture well-known stylized facts about financial asset returns. We show that these facts discriminate better different asset types than general-purpose features. Therefore, financial time series analysis is a domain where well-informed expert knowledge may not be disregarded in favor of agnosticrepresentations of the data. |
| Keywords: | Financial economics, Time series, Clustering, Classification, Machine learning |
| Date: | 2021–07 |
| URL: | http://d.repec.org/n?u=RePEc:ise:remwps:wp01852021&r= |