Measuring Airline Networks Chantal Roucolle (ENAC-DEVI) Joint work with Miguel Urdanoz (TBS) and Tatiana Seregina (ENAC-TBS) This research was possible thanks to the financial support of the Regional Council of Midi Pyrenees.
Airline networks Airline networks are complex and dynamic Number of Airports served Number of markets served Direct or connecting flights, frequencies, schedules… 2
US airports 3
US domestic network in July 2005 4
US domestic network in July 2010 5
US domestic network in July 2013 6
Airline networks Airline networks are complex and dynamic Number of Airports served Number of markets served Direct or connecting flights, frequencies, schedules… Airlines make different choices 7
Frontier Airlines, July 2005 8
Southwest Airlines, July 2005 9
Airline networks Airline networks are complex and dynamic Number of Airports served Number of markets served Direct or connecting flights, frequencies, schedules… Airlines make different choices and their decisions evolve over time 10
Evolution: Delta Airlines July 2005 11
Evolution: Delta Airlines July 2010 12
Evolution: Delta Airlines July 2015 13
Airline network Airline networks are complex and dynamic Number of Airports served Number of markets served Frequencies, schedules… Airlines make different choices and their decisions evolve over time Two questions to address: Network characterization Network evolution: what are the drivers of the choice? Usefulness of network analysis: Does the network structure affect costs, prices, profitability, delays…? 14
Literature In most of the cases perfect hub-and-spoke networks (left) are compared with fully connected networks (right), For instance Brueckner (2004), Alderighi et al. (2005), Barla and Constantatos (2005), Flores Fillol (2009) or Silva et al. (2014). However reality is more complex Wojahn (2001) studies whether a mixed model can be preferred to minimize costs We want to get closer to this reality 15
Our objective Step 1: Network characterization Our approach: combine Graph theory and Principal Component Analysis (PCA) Graph theory: set of mathematical measures and tools to study networks Already used for airlines: Wandelt and Sun (2015), Dunn and Wilkinson (2016) or Du et al. (2016) study different network • properties focusing on the country level. Burghouwt and Redondi (2013) present a compilation of connectivity indicators for airports built from • graph theory. Lordan et al.(2016) study resilience with a sample of airlines from Europe, North America and China. • PCA aims to explain most of the information of the dataset through a reduced number of new variables, called principal components, calculated as linear combinations of the original variables Main findings: Airline network could be characterized by three indicators: Hubness , Resilience , Size Traditional distinction between LCC and Legacies could be reconsidered 16
Our objective Step 2: Network evolution: what are the drivers of the choice? Our approach: explain the evolution of the three indicators over time Use of macroeconomic indicators, air market characteristics, airline type as explanatory variables Estimation of a system of equations on panel data Main findings: Network Hubness , Resilience and Size have distinct drivers Strategies in terms of network evolution depend on the type of airline 17
Data Official Airline Guide, OAG Worldwide data on frequencies, schedules and aircrafts for the last 10 years Monthly data for the third quarter 2005-2015 Focus on the United States Domestic Market Advantage: most studied market with available data on fares Disadvantage: lack of international flights Data cleaning: Eliminating routes shorter than 200 miles or routes with less than 10 seats per flight Recoding of regional/feeder airlines Final data set: 125358 observations 28 operating carriers ranging from 19 to 25 per year City number from 413 to 517 and airports ranging from 435 to 537 per year. 18
Step 1: Network characterization Graph Theory measures: a lot of correlated indicators 19 19
Step 1: Network characterization Reduction of the information: use of PCA Three principal components explain 94.69% of the sample variability: “ Hubness ”, “ Resilience ” and “ Network Size ” Theoretical representation of network Hubness / Resilience map 20
Step 1: Network characterization PC2 : RESILIENCE point-to-point hub-and-spoke hub-and-spoke with several hubs with a unique hub PC1 : HUBNESS path or circle The distinction between LCCs and Legacies is nowadays unclear as highlighted in Jarach et al. (2009) or Bitzan and Peoples (2016). No distinction in term of Hubness (PC1) between Legacies and LCCs. Higher Resilience (PC2) values on average for LCCs 21
Step 1: Network characterization Network representation Size / Hubness and Size / Resilience maps WN WN When the network size increases, Hubness decreases to some level between 0 and -3, both for LCCs and Majors When the network size increases, Resilience seems to approach a level around -1, except for LCCs (Southwest case) 22
Step 2: Network evolution: what are the drivers of the choice? Simultaneous Equations Model 𝐻 𝐽 𝑗𝑘𝑢 = 𝛽 𝑗𝑘 + 𝛾 𝑗1 𝑢 𝑀𝐷𝐷 + 𝛾 𝑗2 𝑢 𝑀 + 𝛾 𝑗3 𝑧 𝑢−1 + 𝛾 𝑗4 𝑔 𝑢−1 + 𝛾 𝑗5 𝑒 𝐸𝑀𝑂𝑋 + 𝛾 𝑗6 𝑒 𝑉𝐵𝐷𝑃 + 𝛾 𝑗7 𝑒 𝑋𝑂𝐺𝑀 + 𝛾 𝑗7 𝑒 𝐵𝐵𝑉𝑇 + 𝜁 𝑗𝑘𝑢 where 𝑗 ∈ {1,2,3} indexes one of three network indicators: Hubness, Resilience, Size j indexes the airlines t indexes the year Explanatory variables: Time trends: 𝑢 𝑀𝐷𝐷 and 𝑢 𝑀 depending on airline type Macroeconomic indicators: 𝑧 𝐻 represents the output gap, and f the jet fuel prices, US domestic market characteristics: dummies to control for the 4 mergers occurred during the considered time frame 23
Estimation results Hubness Resilience Size (i=1) (i=2) (i=3) 𝛾 𝑗1 𝑢 𝑀𝐷𝐷 -0.067 0.071 7.681 (1.015) (1.613) (10.352)*** 𝛾 𝑗2 𝑢 𝑀 0.141 0.107 -0.934 (2.399)** (2.895)*** (0.459) 𝐻 𝛾 𝑗3 𝑧 𝑢−1 0.131 0.078 -0.364 (4.689)*** (2.342)** (0.700) 𝛾 𝑗4 𝑔 -0.345 -0.339 -1.081 𝑢−1 (2.686)*** (2.641)*** (0.521) 𝛾 𝑗5 𝑒 𝐸𝑀𝑋𝑂 -1.533 0.160 148.757 (3.283)*** (0.774) (4.101)*** 𝛾 𝑗6 𝑒 𝑉𝐵𝐷𝑃 -1.358 0.104 259.326 (4.523)*** (0.602) (22.377)*** 𝛾 𝑗7 𝑒 𝑋𝑂𝐺𝑀 -0.096 -0.236 74.008 (0.409) (0.985) (8.299)*** 𝛾 𝑗8 𝑒 𝐵𝐵𝑉𝑇 -0.886 -0.555 88.720 (1.249) (3.828)*** (2.749)*** Constant WN -0.922 2.928 409.236 Legacy AA 1.680 -3.665 -35.346 (3.101)*** (9.959)*** (75.839)*** (4.752)*** (18.206)*** (2.089)** LCC B6 3.594 -2.087 -359.558 Legacy AS -0.271 -4.757 -181.121 (24.247)*** (12.668)*** (48.688)*** (0.677) (15.322)*** (7.079)*** LCC F9 5.827 -3.722 -380.930 Legacy CO 1.250 -3.868 -85.541 (44.737)*** (26.114)*** (75.420)*** (3.615)*** (22.771)*** (3.553)*** LCC FL 4.372 -2.436 -339.937 Legacy HA 3.695 -1.620 -374.144 (25.315)*** (33.692)*** (27.508)*** (12.375)*** (6.563)*** (28.786)*** LCC G4 2.290 -3.671 -322.645 Legacy DL 0.930 -3.830 100.584 (7.760)*** (22.403)*** (49.086)*** (2.281)** (21.224)*** (3.261)*** LCC NK 1.376 0.560 -395.394 Legacy NW 0.348 -4.060 -36.161 (2.052)** (1.393) (68.473)*** (1.314) (24.469)*** (1.663)* LCC SY 4.500 -2.965 -421.380 Legacy UA -0.289 -3.718 15.540 (6.298)*** (19.657)*** (37.913)*** (1.293) (21.894)*** (1.475) LCC VX 3.725 1.335 -443.266 Legacy US -0.998 -3.564 16.677 (11.992)*** (1.373) (54.925)*** (2.852)*** (19.464)*** (0.595) ρ 0.3629 Observations 211 211 211 * p<0.1; ** p<0.05; *** p<0.01
Recommend
More recommend