Conditional rate structures: a unique statistical approach to energy use assessment and confidence intervals
A unique statistical approach to the problem of estimating residential energy use is presented. Such estimates have historically been based on ad hoc methods without a solid theoretical infrastructure, and as a consequence, the results have been difficult to quantitatively evaluate. As a first step in rectifying these shortcomings, a constructive proof is given of a consistent estimator and confidence levels for the estimate are derived. In particular, it is shown that the appropriate rate structure to use to impute actual energy use from expenditure figures is the average rate structures weighted by the conditional probabilities at each expenditure level. Associated with the Cartesian product space of rate structures by expenditure levels is a path space which leads to the appropriate formulation of confidence levels.
- Research Organization:
- Oak Ridge National Lab., TN (USA)
- DOE Contract Number:
- W-7405-ENG-26
- OSTI ID:
- 6702710
- Report Number(s):
- CONF-780802-4
- Resource Relation:
- Conference: American Statistical Association meeting, San Diego, CA, USA, 14 Aug 1978; Other Information: Portions of document are illegible
- Country of Publication:
- United States
- Language:
- English
Similar Records
Statistical variability and confidence intervals for planar dose QA pass rates
Correction of confidence intervals in excess relative risk models using Monte Carlo dosimetry systems with shared errors
Related Subjects
29 ENERGY PLANNING
POLICY AND ECONOMY
ELECTRIC POWER
RATE STRUCTURE
POWER DEMAND
FORECASTING
RESIDENTIAL SECTOR
ECONOMETRICS
STATISTICS
ECONOMICS
MATHEMATICS
POWER
320100* - Energy Conservation
Consumption
& Utilization- Buildings
298000 - Energy Planning & Policy- Consumption & Utilization
292000 - Energy Planning & Policy- Supply
Demand & Forecasting