Chapter 5: Results
5.1. Regression results
As the data sample is very large only variables with a p-value of under 0.001 will be presented in this section. Where coefficients are not significant, blank spaces have been included to represent this fact.
Table 18: Regression results for numerical factors Arrival Departure Variable Estimate Sign Estimate Sign Load Factor
Passengers 0.046 + 0.065 +
Arrival delay n/a 0.507 +
Scheduled Turnaround Time 0.019 + -0.055 -
When analyzing the numerical factors as shown in Table 18, the largest estimation coefficient is the arrival delay for departures. Given all else constant for minute of arrival delay, the departure delay increases by 0.507 minutes, roughly 30 seconds.
Although the correlation plot in Figure 13 may suggest a one-to-one relationship, regression considers all data, most of which is contained below 350 minutes. Another interesting observation is that load factor is negatively correlated to arrival delay, opposite to what one might expect. This may be that due high load factors may possible cause a departure delay and therefore pilots have a higher incentive to fly faster to make up the departure delay.
In the case of categorical variables, R automatically sets the first element in the vector as the control variable and therefore all coefficients are interpreted in relation to this variable. Although this is not ideal because it does not display the effect of the control variable, it provides a relative analysis of categorical variables and their effect on flight delays.
Table 19: Regression results for airlines
Arrival Departure Airline Estimate Sign Estimate Sign
Air Asia 18.400 + -17.250 -
‧
Airline Estimate Sign Estimate Sign Cebu Pacific Airlines 7.373 +Shenzhen Airlines 20.960 +
Sichuan Airlines 17.170 +
Singapore Airlines -17.070 -
Spring Airlines -6.705 - associated with arriving early (i.e. those with very negative coefficients) are all long-haul airlines (Emirates, Delta and KLM). For departures, two Taiwanese airlines (Far
‧
coefficients followed by two long haul airlines, United and Turkish. All the negative coefficients for departure delays belong to LCCs. This is particularly interesting as AirAsia has one of the highest arrival coefficients but one of the lowest departure coefficients. This may suggest an extremely efficient turnaround operation to turn the arrival delay into an early departure.Table 20: Regression results for airports Arrival Departure Estimate Sign Estimate Sign Amsterdam 28.970 + -8.891 -
‧
Estimate Sign Estimate Sign Jakarta 16.530 +‧
國立 政 治 大 學
‧
N a
tio na
l C h engchi U ni ve rs it y
39
Arrival Departure Estimate Sign Estimate Sign Urumqi 29.460 +
Vancouver
Vienna -11.350 -
Weihai 30.750 + Wenzhou 19.400 +
Wuhan 22.280 +
Wuxi 42.760 + 13.630 +
Xiamen 21.340 + Xian
Xuzhou
Yancheng 26.120 + Yangon 21.300 + Yangzhou 23.350 + Yantai 34.840 + Yinchuan
Zhangjiajie 17.740 + Zhengzhou 18.190 +
For destinations, Asahikawa was set as the control airport as shown in Table 20.
Dubai has been excluded from the list as it is solely operated Emirates and Emirates solely operates to Dubai. Thus, the effect of Dubai has been captured in the Emirates variable. At first glance, there are more significant coefficients for arrival than departure flights. Most of the arrival coefficients are positive which, under the normality assumption, could imply that flights from Asahikawa tend to arrive earlier rather than later. The largest arrival coefficients are Jeju, Wuxi and Nanjing whereas Okayama and Nanning have the most negative coefficients.
Similarly, for departure coefficients many airports display a negative value which suggests that flights to Asahikawa may delayed. Once again Wuxi had the highest positive coefficient. This kind of behavior, also displayed by Koror Palau, may be related to its high positive arrival coefficient. Other positive coefficients include Delhi and Honolulu. The lowest negative coefficients are from Daegu, Istanbul and Chiang Mai.
‧
國立 政 治 大 學
‧
N a
tio na
l C h engchi U ni ve rs it y
40
Table 21: Regression results for aircrafts
Arrival Departure Aircraft type Estimate Sign Estimate Sign Airbus A320
Airbus A321 8.778 +
Airbus A330-200 8.580 +
Airbus A330-300 9.574 +
Airbus A340-300 9.559 +
Airbus A350-900 12.800 +
Airbus A380 24.630 + -26.240 -
Boeing 737-400
Boeing 737-700 13.490 +
Boeing 737-800 5.282 +
Boeing 737-900
Boeing 747-400 8.408 +
Boeing 747-800 Boeing 757 Boeing 767-300
Boeing 777-200 -6.476 -
Boeing 777-300 10.720 + -6.049 - Boeing 787-8
Boeing 787-9 Embraer E190
McDonnel MD90 9.026 + 10.020 +
In terms of the aircraft coefficients shown in Table 21, using the Airbus A319 as a control variable, arrival flights all have a positive coefficient which implies that A319’s may generally arrive early. Once again, there are more arrival coefficients than departure coefficients suggesting that aircraft types play a greater role in arrival delays than in departure delays. The most notable observation is that the largest aircraft, Airbus A380 has the highest arrival delay coefficient and the lowest negative departure delay coefficient.
‧
Table 22: Regression results for temporal values
Arrival Departure
Estimate Sign Estimate Sign
2015 2.096 + 1.847 +
‧
國立 政 治 大 學
‧
N a
tio na
l C h engchi U ni ve rs it y
42
Categorical variables related with time have been summarized in Table 22. On average, flight delay performance has not decreased from 2014 to 2016. The only notable improvement is that flights from 2016 tend to arrive earlier. This is contrary to results found in the descriptive statistics. Furthermore, since all coefficients for months are positive, it can be implied that January is the month where flights arrive the earliest and June to September the latest confirming trends found using descriptive statistics.
Weekdays do not show much significant results. However, Saturdays seem to be day where most flights arrive late and Tuesdays where flights depart the earliest. This corresponds to Figure 4: Number of flights operated per weekday where Tuesdays are the least busy and Saturdays the busiest day of operations.
Regressing flights by hour group also provide an interesting trend. Using the midnight group as a reference (00:00-00:59), flights after 11:00 arrive late with 21:00-21:59 arriving the latest. On the other hand, flight departures after 11:00 tend to depart early. For departure flights, only the 06:00-06:00 group displayed a positive coefficient which means that flights in this hour group will most probably be delayed.