Abstract
A theoretical model and a two-stage econometric estimation procedure are proposed for determining the parameters of industry-region-specific cost, input-demand, or other functions using grouped data. The model and estimation procedure are appropriate when only marginal totals or averages are available, or when data are classified by both region and industry but many cells are empty or sparsely represented. An application is reported in which load functions for the hourly input of electricity are estimated for each day of the week and each month of the year in each cell of a 31 × 7 industry-region matrix. The use of the model to simulate the sensitivity of electricity demand to regional location and weather variability is illustrated.
Similar content being viewed by others
References
Bewley R (1989) Weighted least squares estimation from grouped observations. Rev Econ Statis 71:187–188
Buja A, Hastie T, Tibshirani R (1989) Linear smoothers and additive models (accompanied by eight invited comments and a rejoinder). Ann Statist 17:453–555
Denton FT, Robb AL, Spencer BG, Bessell T, Jefferies KL, Mountain DC, Trimnell F (1985) Report on the development of HELPS — a model designed for forecasting and simulation of load patterns. Research Report No. 142, McMaster University Program for Quantitative Studies in Economics and Population
Economopoulos O, Jefferies K (1986) General service experiment — objectives, data requirements and sample design. Report R-86-7, Rates and Strategic Conservation Department, Ontario Hydro, Toronto
Haitovsky Y (1966) Unbiased multiple regression coefficients estimated from one-way classification tables when the cross classifications are unknown. J Am Statist Assoc 61:720–728
Haitovsky Y (1968) Regression analysis of grouped observations when the cross classifications are unknown. Rev Econ Stud 35:77–89
Haitovsky Y (1973) Regression estimation from grouped observations. Hafner, New York
Houthakker HS (1955) The combined use of differently grouped observations in least squares regression. Harvard University (unpublished)
Hsiao C, Mountain DC, Ho Illman K (1995) A Bayesian integration of end-use metering and conditional demand analysis. J Bus Econ Statist 13:315–326
Platt HD, Einhorn MA, Ignelzi PC, Poirier DJ (1981) Regional load curve models: specification and estimation of the DRI model, Vol. 1. Electric Power Research Institute, Palo Alto, California
Poirier DJ (1976) The econometrics of structural change. North Holland, Amsterdam
Prais SJ, Aitchison J (1954) The grouping of observations in regression analysis. Rev Int Statist Institute 22:1–22
Suits DB, Mason A, Chan L (1978) Spline functions fitted by standard regression methods. Rev Econ Statist 60:132–139
White KJ (1978) A general computer program for econometric methods — SHAZAM. Econometrica 46:239–240
Author information
Authors and Affiliations
Additional information
The work reported in this paper was supported by Ontario Hydro. We acknowledge gratefully the cooperation and assistance of Evelyn L. Lawson of Ontario Hydro in the provision of data and other aspects of the project. Able research assistance was provided by Renqun Wang at McMaster University. Dean C. Mountain is a member of the McMaster School of Business; when the project began he was Superintendent of Load Research in the Rates Department of Ontario Hydro. The other authors are associated with the McMaster Department of Economics. The authors thank the reviewers and the editor for helpful comments on an earlier draft of the paper.
Rights and permissions
About this article
Cite this article
Denton, F.T., Feaver, C.H., Mountain, D.C. et al. Industry-region load profiles: econometric estimation based on marginal totals. Ann Reg Sci 30, 223–246 (1996). https://doi.org/10.1007/BF01581974
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01581974