Forecasting with nonstationary dynamic factor models

Peña, Daniel; Poncela, Pilar

doi:10.1016/s0304-4076(03)00198-2

Cited by 60 publications

(39 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These have recently shown promise in theory (Stock & Watson, 2002;Forni et al, 2005) and application (e.g. Peña & Poncela, 2004), and we suspect they will become much more widely used in the years ahead.…”

Section: A Look To the Futurementioning

confidence: 99%

25 years of time series forecasting

Gooijer

Hyndman

2006

International Journal of Forecasting

1,291

632

View full text Add to dashboard Cite

During this period, over one third of all papers published in these journals concerned time series forecasting. We also review highly influential works on time series forecasting that have been published elsewhere during this period. Enormous progress has been made in many areas, but we find that there are a large number of topics in need of further development. We conclude with comments on possible future research directions in this field.

show abstract

Section: A Look To the Futurementioning

confidence: 99%

25 years of time series forecasting

Gooijer

Hyndman

2006

International Journal of Forecasting

1,291

632

View full text Add to dashboard Cite

show abstract

“…In addition to the non-stationarity included in Poncela (2004 and2006), in this work we include the possibility of common factors following a multiplicative seasonal model 7 with constant. Seasonality introduces some additional non-linear constraints between parameters in matrix Ψ, and modifying the estimation procedure as we will show.…”

Section: Seadfa Estimation Using the Em Algorithmmentioning

confidence: 99%

Seasonal Dynamic Factor Analysis and Bootstrap Inference: Application to Electricity Market Forecasting

et al. 2011

View full text Add to dashboard Cite

Year-ahead forecasting of electricity prices is an important issue in the current context of electricity markets. Nevertheless, only one-day-ahead forecasting is commonly tackled up in previous published works. Moreover, methodology developed for the short-term does not work properly for long-term forecasting.In this paper we provide a seasonal extension of the Non-Stationary Dynamic Factor Analysis, to deal with the interesting problem (both from the economic and engineering point of view) of long term forecasting of electricity prices. Seasonal Dynamic Factor Analysis (SeaDFA) allows to deal with dimensionality reduction in vectors of time series, in such a way that extracts common and specific components. Furthermore, common factors are able to capture not only regular dynamics (stationary or not) but also seasonal one, by means of common factors following a multiplicative seasonal VARIMA(p,d,q)×(P,D,Q) s model. Besides, a bootstrap procedure is proposed to be able to make inference on all the parameters involved in the model. A bootstrap scheme developed for forecasting includes uncertainty due to parameter estimation, allowing to enhance the coverage of forecast confidence intervals. Concerning the innovative and challenging application provided, bootstrap procedure developed allows to calculate not only point forecasts but also forecasting intervals for electricity prices.

show abstract

“…Alternatively, the nonstationary common trends can be modelled. In the latter case, Peña and Poncela (2004) show that the gain in precision, in terms of the prediction MSE, of small nonstationary factor models with respect to univariate ARIMA and pooled forecasts depends on the common information and increases with the number of time series and the sum of the relative sizes of the factor loadings. Fuleky and Bonham (2013) analyze empirically the forecasting performance of small mixed frequency factor models when the observed variables share stochastic trends.…”

Section: Forecasting Using Targeted Predictorsmentioning

confidence: 97%

Short-Term Forecasting for Empirical Economists. A Survey of the Recently Proposed Algorithms

2013

Self Cite

View full text Add to dashboard Cite

Practitioners do not always use research …ndings, sometimes because the research is not always conducted in a manner relevant to real-world practice. This survey seeks to close the gap between research and practice on short-term forecasting in real time.Towards this end, we review the most relevant recent contributions to the literature, examine their pros and cons, and we take the liberty of proposing some lines of future research. We include bridge equations, MIDAS, VARs, factor models and Markovswitching factor models, all allowing for mixed-frequency and ragged ends. Using the four constituent monthly series of the Stock-Watson coincident index, industrial production, employment, income and sales, we evaluate their empirical performance to forecast quarterly US GDP growth rates in real time. Finally, we review the main results regarding the number of predictors in factor based forecasts and how the selection of the more informative or representative variables can be made.Keywords: Business Cycles, Output Growth, Time Series. JEL Classi…cation: E32, C22, E27C o rre sp o n d in g A u th o r: G a b rie l P e re z Q u iro s, B a n c o d e E sp a ñ a , R e se a rch D iv isio n , M o n e ta ry a n d F in a n c ia l S tu d ie s D e p a rtm e nt, D G E c o n o m ic s, S ta tistic s, a n d R e se a rch . A lc a lá 4 8 , 2 8 0 1 4 M a d rid , S p a in . E -m a il: g a b rie l.p e re z @ b d e .e s. M . C a m a ch o a n d P. P o n c e la a ck n ow le d g e s su p p o rt fro m p ro je c ts E C O 2 0 1 0 -1 9 8 3 0 , E C O 2 0 0 9 -1 0 2 8 7 a n d E C O 2 0 1 2 -3 2 8 5 4 , re sp e c tive ly.

show abstract

Forecasting with nonstationary dynamic factor models

Cited by 60 publications

References 27 publications

25 years of time series forecasting

25 years of time series forecasting

Seasonal Dynamic Factor Analysis and Bootstrap Inference: Application to Electricity Market Forecasting

Short-Term Forecasting for Empirical Economists. A Survey of the Recently Proposed Algorithms

Contact Info

Product

Resources

About