Dean C. Mountain

A Bayesian Integration of End-Use Metering and Conditional-Demand Analysis

Traditional methods of estimating kilowatt end uses load profiles may face very serious multicollinearity issues. In this article, a Bayesian framework is proposed to combine end uses monitoring information with the aggregate-load/appliance data to allow load researchers to derive more accurate load shapes. Two variants are suggested: The first one uses the raw end-use metered data to construct the prior means and variances. The second method uses actual end-use data to construct the priors of the parameters characterizing the behavior of end uses of specific appliances. From a prediction perspective, the Bayesian methods consistently outperform the predictions generated from conventional conditional-demand formulation.

Modeling Ontario Regional Electricity System Demand Using A Mixed Fixed And Random Coefficients Approach

Abstract In examining the municipal peak and kilowatt-hour demand for electricity in Ontario, we begin by exploring the issue of homogeneity across geographic regions. A common model across municipalities and geographic regions cannot be supported by the data. We consider various procedures which deal with this heterogeneity and yet reduce the multicollinearity problems associated with regional specific demand formulations. The recommended model controls for regional differences assuming that the coefficients of regional-seasonal specific factors are fixed and different while the coefficients of economic and weather variables are random draws from a common population for any one municipality by combining the information on all municipalities through a Bayes procedure.

Estimating the Short-Run Income Elasticity of Demand for Electricity by Using Cross-Sectional Categorized Data

Abstract This study uses the 1980 energy application survey conducted by Ontario Hydro to estimate a short-run or conditional demand for electricity model. Two-step inference procedures are developed to take account of the special nature of the data in which the income variable is recorded in categorical form. Comparisons of short-run income elasticities with other studies, using the complete information of income variable, are also made.

Time-of-Use Prices and Electricity Demand: Allowing for Selection Bias in Experimental Data

We address self-selection in time-of-use experiments. Our methodology is especially appropriate when 1) theory does not provide an exclusion restriction between the participation and consumption equations, or 2) the demand system contains a large number of parameters estimated from a difficult objective function. We find that correcting for selection bias is important. Generally, small commercial establishments are not very responsive to time-of-use pricing. However, for some subgroups (such as those with neither electric heating nor air conditioning), significant responsiveness occurs given a sufficiently short peak period and a sufficiently large peak/off-peak price differential.

Age, Trend, and Cohort Effects in a Macro Model of Canadian Expenditure Patterns

A quadratic almost ideal demand system allowing for age, cohort, and trend effects is developed at the macro level. The model is estimated by maximum likelihood, using a three-tier iterative/search method applied to pooled 1961–1992 time series for five regions of Canada and six categories of expenditure. Hypothesis tests indicate support for the model specification. Elasticities are compared with those reported in other studies, with special attention to food. Effects of demographic and trend variables on elasticities and expenditure shares are investigated. An overall conclusion is that such effects can be very important in a macro demand system.

Factor price misspecification in bank cost function estimation

Abstract Many studies of bank productivity implicitly assume that banks face imperfect factor markets in accessing labor and capital such that, in renting the same factor of production, at the same time, one bank will pay a price that will vary greatly from that of another bank. Usually, this implicit assumption is introduced by researchers’ simple expedience in calculating a factor price by dividing total cost attributable to a factor by the number of units rented. The range of factor prices so obtained, however, exceeds the reasonable bounds commonly observed in integrated factor markets. Our study contends that the wide variety of labor factor prices implicitly assumed is in fact a reflection of a variegated labor market and that the wide variety of financial capital costs is a reflection of incomplete specification of funds’ costs. We contend that, particularly in cross-sectional studies, it would generally be better for researchers to assume that banks faced competitive factor markets, thereby allowing the factor price term of cost functions to be eliminated. Not only would such elimination allow for a better estimate of true economies of scale and efficiency; it would also simplify greatly the estimation of many models. In this paper, we review briefly the significance of specifying factor prices in cost functions. Then we look at some actual factor prices that are reported in studies and used as inputs to cost function estimation. We conduct some simple tests to show what the reported factor prices in banking may actually represent. Having shown that factor prices reported are subject to misspecification, we estimate a set of cost functions with and without factor price specifications. We conclude by demonstrating that the improper specification of factor prices can affect inferences regarding measurement of inefficiency and returns to scale. Finally, we suggest methods by which these misspecifications may be rectified by use of time series, regional and international factor pricing data.

Income distribution and aggregation/disaggregation biases in the measurement of consumer demand elasticities

Abstract We investigate the issue of aggregation and disaggregation biases in demand elasticities. Drawing on income distribution data for seven countries we calculate the likely range of differences between elasticities evaluated at average income and corresponding aggregate average elasticities.

A Combined Structural and Flexible Functional Approach for Modeling Energy Substitution

Abstract In theory, a flexible functional form can approximate an arbitrary elasticity of substitution; however, when faced with an actual finite data set, a parsimonious parametric functional form that imposes more structural restrictions may yield a more accurate approximation about underlying substitution. Therefore, for uncovering the underlying degree of input substitution a data-exploration strategy is suggested that combines the parametric family of a system of quadratic log-ratio demand equations and conventional flexible functional forms. This allows testing for more restrictive hypotheses about substitution. These issues are examined in the context of interfuel substitution at the two-digit SIC level for manufacturing industries in Ontario and Quebec, Canada. A basic tenet of the approach of this article is that although letting data speak for itself is preferred, economic theory should be used wherever possible, and a simple model is preferable to complicated models unless the evidence suggests...

The response of an industrial firm to alternative electricity rate structures : An optimization model for simulation applications

Abstract A theoretical linear programming model of the response of an industrial firm to hypothetical time-of-use and peak demand electricity rates is presented. The firm minimizes total cost by annual, weekly, and daily production scheduling. It may also change the proportions of energy input supplied by electricity, natural gas, and oil, and in the long run it may expand or contract its plant size. Realistic values are assigned to the parameters of the model and the model is used in simulation experiments to study the effects of alternative electricity rate structures on two types of firm - a ‘light manufacturing’ firm and a ‘heavy manufacturing’ firm. It is found that under certain circumstances the introduction of hypothetical but plausible time-of-use and peak demand rate structures can have a major impact on industrial production schedules, electricity load factors, and other variables of interest.

Energy Demand with Declining Rate Schedules: An Econometric Model for the U.S. Commercial Sector

We specify and estimate a model of the demand for electricity and natural gas in commercial buildings using data from the Commercial Building Energy Consumption Survey. Although not observed, declining rate schedules are approximated by a downward sloping function fitted to billing data for individual survey units. Marginal prices (rates), temperature variables and a large number of building characteristics are incorporated into the model as explanatory variables. Demand and rate schedule equations constitute a simultaneous system, with prices and quantities jointly determined. The effects on price elasticities of using (endogenous) marginal rather than (exogenous) average prices are estimated to be quite large. (JEL Q41)