Prediction of World Crude Oil Price with the Method of Missing Data

Xiaotong LI, Shaohui SUN, Taohua LIU

Abstract


As the fluctuation of oil price plays an important role in global political and economic situation, forecasting the price of oil is significant. In this paper, we analyze the data of the world crude oil price using ideas of treating with the missing data, i.e. we take the predictor as missing data and use the EM algorithm to establish time series model. We give the predictive values of weekly world crude oil price of January and February in 2011 using the data of 2009 and 2010. Meanwhile, we found that the method based on missing data is more effective than normal time series method by comparing the predictive value with reality data. In addition, this method is also applicable to the case that historical observations have missing data.
Key words: World Crude Oil Price; Forecast; Missing Data; EM Algorithm; Time Series

Keywords


World Crude Oil Price; Forecast; Missing Data; EM Algorithm; Time Series

References


Roderick J. A. Little & Donald B. Rubin (1987). Statistical analysis with missing data. New York: Wiley and Sons, Inc..

Nordheim EV. (1984). Inference from non-randomly missing data: An example from a genetic study on Turner’s Syndrome . J. Am. Statist. Assoc., 79, 772-780.

Horton N.J. (1988). Laird NM. Maximum likelihood analysis of generalized linear models with missing covariates. Statistical Methods in Medical Research, 8(1), 37-50.

Chen Xiaolin & Wan Sishui (2007). A kind of mixed Normal distribution parameter estimation of EM algorithm and data expansion, Suzhou University Journals (Natural science edition), 23(3).

Lu Wangyong, Wu Yaoguo &Ma Hong (2007). The lognormal distribution parameter estimation based on EM algorithm, statistics and decision.

Zhang Xing & Hao Wei (2007). The study of filling method of incomplete or missing data.




DOI: http://dx.doi.org/10.3968/j.ans.1715787020110401.002

DOI (PDF): http://dx.doi.org/10.3968/g1776

DOI (indexed/included/archived): http://dx.doi.org/10.3968/g4689

Refbacks

  • There are currently no refbacks.


Copyright (c)



Share us to:   

Reminder

We are currently accepting submissions via email only.

The registration and online submission functions have been disabled.

Please send your manuscripts to ans@cscanada.net，or  ans@cscanada.org  for consideration. We look forward to receiving your work.

 

 Articles published in Advances in Natural Science are licensed under Creative Commons Attribution 4.0 (CC-BY).

 ADVANCES IN NATURAL SCIENCE Editorial Office

Address: 1055 Rue Lucien-L'Allier, Unit #772, Montreal, QC H3G 3C4, Canada.

Telephone: 1-514-558 6138
Website: Http://www.cscanada.net; Http://www.cscanada.org
E-mail:caooc@hotmail.com; office@cscanada.net

Copyright © 2010 Canadian Research & Development Centre of Sciences and Cultures