|
on Econometric Time Series |
| By: | Ruiz Ortega, Esther; Poncela, Pilar; Miranda Gualdrón, Karen Alejandra |
| Abstract: | Dynamic Factor Models (DFMs), which assume the existence of a small number of unobserved underlying factors capturing the comovements in large systems of variables, are very popular among empirical macroeconomists to reduce dimension and to extract factors with an economic interpretation. Factors can be extracted using either non-parametric Principal Components (PC) or parametric Kalman filter and smoothing (KFS) procedures, with the former being computationally simpler and robust against misspecification and the latter being efficient if the specification is correct and coping in a natural way with missing and mixed-frequency data, time-varying parameters, non-linearities and non-stationarity among many other stylized facts often observed in real systems of economic variables. This paper analyses the empirical consequences on factor estimation and forecasting of using alternative extraction procedures and estimators of the DFM parameters under various sources of potential misspecification. In particular, we consider factor extraction when assuming different number of factors and different factor dynamics. The factors are extracted from a popular data base of US macroeconomic variables that has been widely analyzed in the literature without consensus about the most appropriate model speciffication. We show that this lack of consensus is ony marginally cruzial when it comes to factor extraction but it matters when the objective is forecasting. |
| Keywords: | State-Space Model; Principal Components; Kalman Filter; Em Algorithm |
| Date: | 2021–03–23 |
| URL: | http://d.repec.org/n?u=RePEc:cte:wsrepe:32210&r=all |
| By: | ; Todd E. Clark; Florian Huber; Gary Koop; Massimiliano Marcellino |
| Abstract: | We develop novel multivariate time series models using Bayesian additive regression trees that posit nonlinear relationships among macroeconomic variables, their lags, and possibly the lags of the errors. The variance of the errors can be stable, driven by stochastic volatility (SV), or follow a novel nonparametric specification. Estimation is carried out using scalable Markov chain Monte Carlo estimation algorithms for each specification. We evaluate the real-time density and tail forecasting performance of the various models for a set of US macroeconomic and financial indicators. Our results suggest that using nonparametric models generally leads to improved forecast accuracy. In particular, when interest centers on the tails of the posterior predictive, flexible models improve upon standard VAR models with SV. Another key finding is that if we allow for nonlinearities in the conditional mean, allowing for heteroskedasticity becomes less important. A scenario analysis reveals highly nonlinear relations between the predictive distribution and financial conditions. |
| Keywords: | nonparametric VAR; regression trees; macroeconomic forecasting |
| JEL: | C11 C32 C53 |
| Date: | 2021–03–22 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedcwq:90366&r=all |
| By: | Javier Oliver Muncharaz (Universidad Politécnica de Valencia) |
| Abstract: | In the financial literature, there is great interest in the prediction of stock prices. Stock prediction is necessary for the creation of different investment strategies, both speculative and hedging ones. The application of neural networks has involved a change in the creation of predictive models. In this paper, we analyze the capacity of recurrent neural networks, in particular the long short-term recurrent neural network (LSTM) as opposed to classic time series models such as the Exponential Smooth Time Series (ETS) and the Arima model (ARIMA). These models have been estimated for 284 stocks from the S&P 500 stock market index, comparing the MAE obtained from their predictions. The results obtained confirm a significant reduction in prediction errors when LSTM is applied. These results are consistent with other similar studies applied to stocks included in other stock market indices, as well as other financial assets such as exchange rates. |
| Abstract: | En la literatura financiera existe un gran interés por la predicción de precios bursátiles que es necesario para la creación de diferentes estrategias de inversion, tanto especulativas como de cobertura. La aplicación de las redes neuronales ha supuesto un cambio en la creación de modelos de predicción. En este trabajo se analiza la capacidad que tienen las redes neuronales recurrentes, en concreto la long shortterm recurrent neural network (LSTM) frente a modelos de series temporales clásicos como el Exponential Smooth Time Series (ETS) y el modelo Arima (ARIMA). Para ello se ha estimado dichos modelos para 284 acciones pertenecientes al índice bursátil S&P 500, comparando el MAE obtenido de sus predicciones, con el modelo LSTM. Los resultados obtenidos confirman una reducción importante de los errores de predicción. Estos resultados son coincidentes con otros estudios similares aplicados a acciones de otros índices bursátiles así como a otros activos financieros como los tipos de cambio. |
| Keywords: | S&P 500,Long short-term neural network,Recurrent Neural Network,Arima,Redes neuronales recurrentes |
| Date: | 2020 |
| URL: | http://d.repec.org/n?u=RePEc:hal:journl:hal-03149342&r=all |
| By: | David O. Lucca; Jonathan H. Wright |
| Abstract: | Seasonal adjustment is a key statistical procedure underlying the creation of many economic series. Large economic shocks, such as the 2007-09 downturn, can generate lasting seasonal echoes in subsequent data. In this Liberty Street Economics post, we discuss the prospects for these echo effects after last year’s sharp economic contraction by focusing on the payroll employment series published by the U.S. Bureau of Labor Statistics (BLS). We note that seasonal echoes may lead the official numbers to overstate actual changes in payroll employment modestly between March and July of this year after which distortions flip the other way. |
| Keywords: | seasonal adjustment; COVID-19; Bureau of Labor Statistics (BLS) |
| JEL: | E2 |
| Date: | 2021–03–25 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fednls:90401&r=all |