Short-term forecasting with mixed-frequency data: a MIDASSO approach

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may AbstractIn this paper we extend the targeted-regressor approach suggested in Bai and Ng (2008) for variables sampled at the same frequency to mixed-frequency data. Our MIDASSO approach is a combination of the unrestricted MIxed-frequency DAta-Sampling approach (U-MIDAS) (see Foroni et al., 2015;Castle et al., 2009;Bec and Mogliani, 2013), and the LASSO-type penalised regression used in Bai and Ng (2008), called the elastic net (Zou and Hastie, 2005). We illustrate our approach by forecasting the quarterly real GDP growth rate in Switzerland.

Nowcasting from cross‐sectionally dependent panels

“…Although some methods have proposed panel forecast lag selection methods in the presence of fixed effects nuisance parameters (Lee & Phillips, 2015) and cross-sectional dependence (Greenaway-McGrevy, 2019), these are not applicable in the current context with potential parameter heterogeneity and factors. In previous versions of the paper, we also experimented with the use of machine learning methods like LASSO and the elastic net in order to perform shrinkage and lag selection, motivated by other studies using this in the MIDAS context (Babii et al, 2020;Siliverstovs, 2017;Xu et al, 2018). 0.0000 0.0000 0.7990 0.0000 0.0000 1.0470 0.0000 0.0000 0.8324 151 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000…”

Estimation and HAC-based Inference for Machine Learning Time Series Regressions

“…We noted in the main body of the paper that the specification in (2) deviates from the standard MIDAS polynomial specification as it results in a linear regression model -a subtle but key innovation as it maps MIDAS regressions in the standard regression framework. Moreover, casting the MIDAS regressions in a linear regression framework renders the optimization problem convex, something only achieved by Siliverstovs (2017) using the U-MIDAS of Foroni, Marcellino, and Schumacher (2015) which does not recognize the mixed frequency data structure, unlike our sg-LASSO.…”

Does gold–platinum price ratio predict stock returns? International evidence

“…A highly limited set of studies, however, have assessed the ability of gold price to predict stock returns and reflect changes in international stock markets (Schwartz, 1997; Chen et al. , 2005; Chkili, 2016; Siliverstovs, 2017; Huang and Kilic, 2019).…”

“…Investment in gold can mitigate financial risks, and the information contained in gold price could be used to predict stock returns. A highly limited set of studies, however, have assessed the ability of gold price to predict stock returns and reflect changes in international stock markets (Schwartz, 1997;Chen et al, 2005;Chkili, 2016;Siliverstovs, 2017;Huang and Kilic, 2019).…”