Rural electric power requirements forecasts: detecting and correcting for weaknesses and bias.: An article from: Management Quarterly

This digital document is an article from Management Quarterly, published by National Rural Electric Cooperative Association on September 22, 1993. The length of the article is 1854 words. The page length shown above is based on a typical 300-word page. The article is delivered in HTML format and is available in your Amazon.com Digital Locker immediately after purchase. You can view it with any web browser.

From the supplier: Power Requirements Studies (PRS) suffer from two weaknesses in statistical forecasting for small rural electric systems. These are the unwarranted emphasis on trending and the statistical bias called autocorrelation. Such problems may lead to expensive managerial decisions based on faulty results. Since the economic, demographic and other data necessary in estimating factors that affect peak usage levels are scarce, trending has been a popular but flawed alternative, because it does not reveal the underlying causes of consumption. In addition, the ordinary least squares (OLS) regression methods used in PRS suffer from autocorrelation resulting in biased coefficients. Instead, the maximized likelihood estimate (MLE) model, which adjusts for correlation, may be used to yield better coefficients. Using actual consumption data, OLS estimates for the ten-year growth rate overstate the MLE forecast by 62% per annum.

Citation Details
Title: Rural electric power requirements forecasts: detecting and correcting for weaknesses and bias.
Author: Donald A. Murry
Publication:Management Quarterly (Magazine/Journal)
Date: September 22, 1993
Publisher: National Rural Electric Cooperative Association
Volume: v34 Issue: n3 Page: p13(6)

Distributed by Thomson Gale