This paper employs multilevel factor modelling techniques to unravel systematic unobserved determinants of the intraday and interzonal price curve dynamics for the Pennsylvania-New Jersey-Maryland (PJM) interconnection. These techniques make an explicit separation of global drivers from region-specific common factors, thereby facilitating the identification of the actual sources of co-variability. Our empirical findings confirm the hypothesis that the common unobserved determinants of power prices in the PJM interconnection obey a block structure, some of which affect different segments of our panel. We argue that a multilevel factor approach offers a more systematic and transparent representation of intertemporal and cross-sectional patterns in PJM electricity prices compared to alternative brute-force VARMAX parametrizations and the single-level factor models, which are often put forward in the literature as viable modelling alternatives.
AlessiL.BarigozziM.CapassoM. (2007). “Improved penalization for determining the number of factors in approximate factor models.” Statistics and Probability Letters80: 1806-1813. https://doi.org/10.1016/j.spl.2010.08.005.
2.
AlonsoA.Garca-MartosC.RodrguezR.SánchezM.-J. (2011). “Seasonal dynamic factor analysis and bootstrap inference: application to electricity market forecasting.” Technometrics53(2): 137-151. https://doi.org/10.1198/TECH.2011.09050.
3.
BaiJ.NgS. (2002). “Determining the number of factors in approximate factor models.” Econometrica70(1): 191-221. https://doi.org/10.1111/1468-0262.00273.
4.
BanburaM.GiannoneD.ReichlinL. (2011). “Nowcasting.” Oxford handbook of economic forecasting, edited by M. P. Clements and D. F. Hendry, Oxford University Press. https://doi.org/10.1093/oxfordhb/9780195398649.013.0008.
5.
BreitungJ.EickmeierS. (2016). “Analyzing international business and financial cycles using multi-level factor models: a comparison of alternative approaches.” Dynamic Factor Models edited by E. Hillebrand and S.J. Koopman, Emerald Group Publishing Ltd, 177-214.
6.
ErgemenY.E. (2016). “Generalized efficient inference on factor models with long-range dependence.” CREATES Research Papers 2016-05, Department of Economics and Business Economics, Aarhus University.
7.
ErgemenY.E.Rodríguez-CaballeroC.V. (2016). “A dynamic multi-level factor model with long-range dependence.” CREATES Research Papers 2016-23, Department of Economics and Business Economics, Aarhus University.
8.
ErgemenY.E.Rodríguez-CaballeroC.V. (2017). “Estimation of a dynamic multilevel factor model with possible long-range dependence.” DES - Working papers, Statistics and Econometrics (WS 24614), Universidad Carlos III de Madrid. Departamento de Estadística.
9.
ErgemenY.VelascoC. (2017). “Estimation of fractionally integrated panels with fixed effects and cross-section dependence.” Journal of Econometrics196(2): 248-258. https://doi.org/10.1016/j.jeconom.2016.05.020.
10.
HallinM.LiškaR. (2007). “The generalized dynamic factor model: determining the number of factors.” Journal of the American Statistical Association102: 603-617. https://doi.org/10.1198/016214506000001275.
11.
HanX. (2016). “Shrinkage estimation of factor models with global and group-specific factors.” Tsinghua International Conference in Econometrics, China, 28/06/16-29/06/16. https://doi.org/10.2139/ssrn.2843129.
12.
HanX.CanerM. (2017). “Determining the number of factors with potentially strong within-block correlations in error terms.” Econometric Reviews36(6-9): 946-969. https://doi.org/10.1080/07474938.2017.1307599.
13.
HuismanR.HuurmanC.MahieuR. (2007). “Hourly electricity prices in day-ahead markets.” Energy Economics29(2): 240-248. https://doi.org/10.1016/j.eneco.2006.08.005.
14.
LieblD. (2013). “Modeling and forecasting electricity spot prices: a functional data perspective.” The Annals of Applied Statistics7(3): 1562-1592. https://doi.org/10.1214/13-AOAS652.
15.
LuX.SuL. (2016). “Shrinkage estimation of dynamic panel data models with interactive fixed effects.” Journal of Econometrics190: 148-175. https://doi.org/10.1016/j.jeconom.2015.09.005.
16.
MaciejowskaK.WeronR. (2015). “Forecasting of daily electricity prices with factor models: utilizing intra-day and inter-zone relationships.” Computational Statistics30(3): 805-819. https://doi.org/10.1007/s00180-014-0531-0.
17.
MoenchE.NgS.PotterS. (1990). “Dynamic hierarchical factor models.” Review of Economics and Statistics95(5): 1811-1817. https://doi.org/10.1162/REST_a_00359.
18.
MuñozM.P.CorcheroC.HerediaF.-J. (2013). “Improving electricity market price forecasting with factor models for the optimal generation bid.” International Statistical Review81(2): 289-306. https://doi.org/10.1111/insr.12014.
19.
PolitisD.N.RomanoJ.P. (1994). “The stationary bootstrap.” Journal of the American Statistical Association89(428): 1303-1313. https://doi.org/10.1080/01621459.1994.10476870.
VehviläinenI.PyykkönenT (2005). “Stochastic factor model for electricity spot price: the case of the Nordic market.” Energy Economics27(2): 351-367. https://doi.org/10.1016/j.eneco.2005.01.002.
22.
WangP. (2008). “Large dimensional factor models with a multi-level factor structure: identification, estimation and inference.” New York University, Department of Economics, Working Paper.
23.
WolakF.A. (2000). “Market Design and price behavior in restructured electricity markets: an international comparison.” Pricing in Competitive Electricity Markets, edited by Faruqui, A. and Eakin, K., Springer US, Boston, MA, 127-152. https://doi.org/10.1007/978-1-4615-4529-3_8.
24.
ZhouZ.ChanW.K.ChowJ.H. (2007). “Agent-based simulation of electricity markets: a survey of tools.” Artificial Intelligence Review28(4): 305-342. https://doi.org/10.1007/1_suppl0462-009-9105-x.
