Predict revenue passenger miles by using multiple regression

Lim, Poh Luan (2008) Predict revenue passenger miles by using multiple regression. Universiti Malaysia Sabah. (Unpublished)

[img]
Preview
Text
ae0000001924.pdf

Download (1MB) | Preview

Abstract

This dissertation is about to form a best linear regression model in order to predict the domestic revenue passenger miles of United States air transportation industry, which is a measure of airline's passenger traffic in the future. Prediction of Revenue passenger miles is important for airline management in order to make various decision based on it. Besides, we are interested to analyze the interaction effects in multiple regression. Analysis also focus on some important factors that influencing revenue passenger miles such as population, number of airlines, operating revenue from passengers, gross national product of United States, number of American planes in an accident and number of fatalities from aircraft accidents. In this study, the way to list out all possible models is introduced and elimination procedures are carried out in order to get the selected models. Eight selection criteria is employed to get the best model. By carrying out the Wald test, the variables which are eliminated before the best model is formed, is tested whether the decision to remove the variables is acceptable or not. This is followed by randomness test; the purpose of this test is to test the randomness of the observation residuals. In the last section of the project, revenue passenger miles will be predicted base on the best model. Besides, comparison between estimated value and actual value is made, and it is found that the variation of them is not critical. Hence, the best model obtained can be said as a good model in predicting revenue passenger miles.

Item Type: Academic Exercise
Keyword: linear regression model, domestic, airline's passenger traffic, revenue passenger, airline management
Subjects: Q Science > QA Mathematics
Department: SCHOOL > School of Science and Technology
Depositing User: SITI AZIZAH BINTI IDRIS -
Date Deposited: 20 Feb 2014 10:28
Last Modified: 12 Oct 2017 11:50
URI: https://eprints.ums.edu.my/id/eprint/8291

Actions (login required)

View Item View Item