Dimensioning performance estimation of the airline industry : path-analysis based modelling / Hashem Salarzadeh Jenatabadi

• Main Author: Jenatabadi, Hashem Salarzadeh
• Format: Thesis
• Published: 2013
• Subjects: HA Statistics
• Online Access: http://studentsrepo.um.edu.my/5738/1/Thesis.pdf; http://studentsrepo.um.edu.my/5738/

Estimating the performance of airline industries has always been of interest to airline management teams and researchers. In this regard, some researchers focused on financial performance, and some just focused on non-financial performance. There are also studies that considered both financial and non-financial performance in their models. The main objective of this research is to integrate the different dimensions of performance indicators in one latent construct as an overall performance. Latent variables are the proxies of measured phenomena reflected in observed variables, which cannot be directly measured. In other words, latent variables present a degree of abstraction that permit a researcher to illustrate the relationship among a class of variables that have common characteristics. The main motivation of this study is to find a comprehensive model for estimating and improving airline performance based on internal indicators, including airline capacity and internal operation, and external indicators including the economic situation. The findings of this study provide a method for designing a simultaneous model for estimating global airline performance. To achieve the objectives of this study, research methodologies such as Structural Equation Modelling (SEM) and path analysis are employed. In path analysis, prior to model fitting, the measurement model is utilized to confirm and verify the reliability of the measurement indicators employed for indicating the latent constructs. In the structural model, only cross sectional data is applicable and longitudinal path analysis is not usable. In this study, 214 airline companies were selected using stratified sampling from a list of active companies in 2009. The validity of the constructs and the constituent variables were verified with content and construct validity testing. The final model, which has the potential to be used in airline companies, is extremely close to the needs and the requirements of the industry as all redundant measures were eliminated.