The main aim of this paper is to discuss the joint choice decision problem (airline choice and flight choice ) of air passengers. We try to find the factors that have significant effects on this choice decision. The air passengers ' revealed preference (RP ) data and stated preference (SP ) data -were collected through field questionnaire survey. Using multinomial logit models we obtained pretty good results. From the estimation results of these models, we found the variables which significantly influenced the joint choice decision of air passengers were safety and equipment, crew and staff services, early arrival time, late arrival time, fare, delaying time, in-flight food and drink services, and inertia!. We also found that there was no significant scale difference between RP data andSP data. The ratio of corresponding variables in the RP model and SP model was also not significantly different. It implies that we can use SP model to explain the joint choice behavior of air passengers.