Article

A test of space-time arma modelling and forecasting of hotel data

  1. Phillip E. Pfeifer†,
  2. Samuel E. Bodily‡

Article first published online: 27 DEC 2006

DOI: 10.1002/for.3980090305

Issue

Journal of Forecasting

Journal of Forecasting

Volume 9, Issue 3, pages 255–272, May/June 1990

Additional Information

How to Cite

Pfeifer, P. E. and Bodily, S. E. (1990), A test of space-time arma modelling and forecasting of hotel data. J. Forecast., 9: 255–272. doi: 10.1002/for.3980090305

Author Information

  1. University of Virginia, U.S.A.

  1. †

    Associate Professor of Business Administration at The Colgate Darden Graduate School of Business Administration. He received his PhD from the School of Industrial and Systems Engineering at the Georgia Institute of Technology. His research interests include forecasting, statistical model building and decision theory and their application to business problems. He has published in such journals as the Journal of Financial and Quantitative Analysis, the Journal of the Royal Statistical Society and Technometrics.

  2. ‡

    Samuel E. Bodily is a Professor at the Colgate Darden Graduate School of Business Administration, University of Virginia, specializing in decision analysis, risk analysis, decision support systems and applications of management science. He received his SM and PhD (1976) in Operations Research at MIT. His publications have appeared in Harvard Business Review, Interfaces, Journal of Financial and Quantitative Analysis, Management Science, Operations Research, Sloan Management Review and elsewhere. His book, Modern Decision Making: A Guide to Modeling with Decision Support Systems, was published by McGraw-Hill.

Publication History

  1. Issue published online: 27 DEC 2006
  2. Article first published online: 27 DEC 2006
  3. Manuscript Received: SEP 1988

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (987K)

Keywords:

  • Space-time modelling;
  • Space-time;
  • ARMA;
  • STARMA

Abstract

This paper describes the application of space-time ARMA modelling to demand-related data from eight hotels from a single hotel chain in a large US city. Important spatial characteristics of the space-time process are incorporated into the model using a simple weighting matrix based on driving distances between the hotels. Using a hold-out sample, the forecasting performance of this space-time approach was found to be superior to eight separate univariate ARMA models.

Get PDF (987K)