Weather adjustment using seemingly unrelated regression
- Idaho Power Company, Boise, ID (United States)
Seemingly unrelated regression (SUR) is a system estimation technique that accounts for time-contemporaneous correlation between individual equations within a system of equations. SUR is suited to weather adjustment estimations when the estimation is: (1) composed of a system of equations and (2) the system of equations represents either different weather stations, different sales sectors or a combination of different weather stations and different sales sectors. SUR utilizes the cross-equation error values to develop more accurate estimates of the system coefficients than are obtained using ordinary least-squares (OLS) estimation. SUR estimates can be generated using a variety of statistical software packages including MicroTSP and SAS.
- Research Organization:
- Electric Power Research Inst. (EPRI), Palo Alto, CA (United States); Pacific Consulting Services, Albany, CA (United States)
- OSTI ID:
- 103285
- Report Number(s):
- EPRI-TR-105012; CONF-930969-; TRN: 95:006490-0039
- Resource Relation:
- Conference: 9. electric utility forecasting symposium: forecasting and DSM - organizing for success, San Diego, CA (United States), 8-10 Sep 1993; Other Information: PBD: May 1995; Related Information: Is Part Of Ninth electric utility forecasting symposium: Proceedings. Forecasting and DSM -- Organizing for success; PB: 705 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Simultaneous density-integral system for estimating stem profile and biomass: Slash pine and willow oak
Bivariate non-parametric regression and varying parameter regression as applied to weather normalization