2018/09/24 by Stephan Smeekes, Smeekes, Stephan, Etiënne Wijler +1 · 1 citation
Economics, Econometrics and Finance · Mathematics · #Econometrics (econ.EM) #FOS: Computer and information sciences #FOS: Economics and business #Methodology (stat.ME) #Monetary Policy and Economic Impact #Statistical Methods and Inference
paper · pdf · doi:10.48550/arxiv.1809.08889
openalex publication_date 2018/09/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper we propose the Single-equation Penalized Error Correction\nSelector (SPECS) as an automated estimation procedure for dynamic\nsingle-equation models with a large number of potentially (co)integrated\nvariables. By extending the classical single-equation error correction model,\nSPECS enables the researcher to model large cointegrated datasets without\nnecessitating any form of pre-testing for the order of integration or\ncointegrating rank. Under an asymptotic regime in which both the number of\nparameters and time series observations jointly diverge to infinity, we show\nthat SPECS is able to consistently estimate an appropriate linear combination\nof the cointegrating vectors that may occur in the underlying DGP. In addition,\nSPECS is shown to enable the correct recovery of sparsity patterns in the\nparameter space and to posses the same limiting distribution as the OLS oracle\nprocedure. A simulation study shows strong selective capabilities, as well as\nsuperior predictive performance in the context of nowcasting compared to\nhigh-dimensional models that ignore cointegration. An empirical application to\nnowcasting Dutch unemployment rates using Google Trends confirms the strong\npractical performance of our procedure.\n