Date of Award
2016
Document Type
Open Access Master's Thesis
Degree Name
Master of Science in Applied Natural Resource Economics (MS)
Administrative Home Department
College of Business
Advisor 1
Latika G Lagalo
Committee Member 1
Gary Campbell
Committee Member 2
Yeonwoo Rho
Abstract
This paper forecasts electricity retail sales using monthly data by sectors from January 2001 through December 2014 and compares the results to the actual data from January 2015 to April 2015. This forecasting shows electricity sales have a significant seasonal pattern. Three models are developed to capture this pattern and all of them are proved to be appropriate for cyclical data. These three models are the model of regression with dummy variables and ARMA disturbances, the autoregressive distributed lags model, and seasonal difference model. AutoRegressive Distributed Lag model helps us know how current and lagged values of average retail sales price, population, and the Industrial Production Index affect the current retail sales data.
Recommended Citation
Han, Jing, "FORECAST ELECTRICITY RETAIL SALES IN THE US BY END-USE SECTORS", Open Access Master's Thesis, Michigan Technological University, 2016.