Quantitative Studies Data Analysis Paper

Group 09

Aizaaz Saeed (110116595)

Nusrat Nowrin Sara (110120437)

Sanjana (110121179)

Ashmita Rana (110105312)

Babak Sehat (110091220)

Odette School of Business, University of Windsor

Course: BSMM8320-05 Quantitative Studies

Dr. Gokul Bhandari

April 05, 2023

Acknowledgement

Researchers extend their deepest gratitude to everyone who supported and participated in the

research. The researchers would like to express their deep gratitude to and the lecturers, students,

staff, and professors of the University of Windsor for their invaluable contributions to this study.

Executive Summary

The aviation industry has seen significant growth over the past decade, thanks to low-cost

airlines and rising incomes of the middle classes. This growth comes with challenges, however,

due to the constantly changing business environment. Like any other industry, the aviation

industry is susceptible to market changes such as seasonal factors and terrorism. Airlines can be

prepared for any unforeseen circumstance and make informed business decisions with the right

analytics and research. This study examines the factors that impact passenger satisfaction. These

include gender, flight time and number of flights per annum, departure delays, amount spent in

airport, passenger age and scheduled departure hours. Research shows that passengers'

satisfaction is directly affected by their age, number of flights per amun, and arrival delays, and.

However, they are not affected by airport spending, or scheduled departure hours. These insights

could be used by airlines to improve customer satisfaction.

Literature Review:

The aviation industry has invested considerable effort into researching customer satisfaction with

airline passengers. There are various elements that can influence passenger contentment, and this

review highlights the primary influences on airline customer satisfaction.

The airline's level of service is an important factor in passenger satisfaction. Paraskevas (2002)

and Buhalis (2002) state that airlines must offer superior service to passengers to maintain

customer loyalty. This encompasses many aspects such as cabin crew behavior, food quality,

comfort and cleanliness. Jain (2018) states that those passengers who are satisfied with their

travel experiences will be even more contented if they receive top-notch treatment.

Flight cancellations or delays are another critical factor that can influence passenger satisfaction.

Studies have indicated that passengers experience less contentment when there is a delay or

cancellation, making punctuality an essential aspect of travel experiences for passengers. Any

delay or cancellation could cause frustration and inconvenience during your trip.

Passenger satisfaction is also affected by the cost of airline travel. According to Liang and Zhang

(2018), passengers are more satisfied if they believe their airfare to be affordable and reasonable.

With low-cost airlines now commonplace, air travel has become more accessible, leading to

higher satisfaction levels among passengers.

Studies have indicated that passengers who are older tend to be more satisfied (Mao et al. 2020).

Gender can also have an effect on passenger satisfaction levels; Mok and de la Cruz (2019) note

that female passengers tend to report higher satisfaction ratings than their male counterparts.

Passenger satisfaction is also affected by the type and type of airline. Chatterjee (2017) noted

that full-service airlines had higher ratings for passenger satisfaction than budget carriers.

Furthermore, the length of a flight may have an effect on passenger feelings; short-haul flights
tend to be more popular than long-haul ones (Gudmundsson 2005). Airline customer satisfaction

is greatly influenced by several factors. These include the level of service provided, flight

punctuality and cost, passenger demographics as well as airline type and flight type. Airlines

should take these into account in order to improve passenger satisfaction and service quality for

all travelers.

RESEARCH QUESTION AND HYPOTHESES

Research Questions

The research question of this paper is to examine the factors affecting customer satisfaction

regarding airlines. By understanding the factors that determine customer satisfaction in the

airline industry, businesses can improve their services to retain existing customers and gain an

edge over their competitors.

Hypothesis

H0: Age has no impact on Airline passenger satisfaction.

H1: Age impacts Airline passenger satisfaction

H0: Number of Flight per annum has no impact on Airline passenger satisfaction

H2: Number of Flight impacts Airline passenger satisfaction

H0: No. of Loyalty has no impact on Airline passenger satisfaction.

H3: Departure delay impacts Airline passenger satisfaction

H0: Shopping at the airport has no impact on Airline passenger satisfaction.

H4: Shopping at the airport impacts Airline passenger satisfaction

H0: Eating and Drinking has no impact on Airline passenger satisfaction.

H5: Eating and Drinking impacts on Airline passenger satisfaction.

H0: Scheduled Departure Hour has no impact on Airline passenger satisfaction.

H6: Scheduled Departure Hour Impacts on Airline passenger satisfaction

H0: Arrival Delay in minutes has no impact on Airline passenger satisfaction.

H7: Arrival Delay in minutes impacts Airline passenger satisfaction

DATA PREPARATION AND COLLECTION

This survey employs exclusively secondary data obtained from a sample of 2000 flyers. The data

sets encompass various variables, such as satisfaction levels, airline status, age, gender,

frequency of annual flights, travel type, expenditure on shopping at the airport, consumption of

food and drink at the airport, travel class, scheduled departure time, delay in departure and

arrival, cancellation of flights, flight duration in minutes, and flight distance.

A summary of each variable in the dataset:

Satisfaction: This dataset includes a variable that indicates the satisfaction levels of customers in

an airport sample. It utilizes a Likert scale ranging from 1 to 5, where 1 represents the lowest

satisfaction level and 5 represents the highest. This variable serves as the dependent variable in

the analysis since its purpose is to examine airline customers' satisfaction levels. For

convenience, satisfaction has been divided into two categories: less satisfactory (1 to 3) and more

satisfactory (4+).

Airline Status: The dataset includes a variable that lists the various airline classes operating at

an airport. This variable is ordinal, since they are ranked from lowest to highest; with blue being

the lowest-ranked and platinum class being highest-ranked. The airlines have been divided into

three groups: top tier ones (gold/platinum status); mid-tier ones (silver airline status); and low
tier ones (blue class).

Age and Gender: The dataset contains variables that illustrate the disparities in the customer

types present in the airport's sample size. Age is a ratio dataset that represents the different ages

of the 2000 customers within the sample size. The age of the customers in the dataset ranged

from 15 to 85, and we classified them into three age groups: young adults (15-37 years), middle-

aged adults (38-60 years), and senior citizens (61 years and above). Gender, being nominal data,

indicates whether the customer is male or female. The dataset includes two gender categories,

namely male and female. From the dataset, it was discovered that 45.45% of the customers were

male, while 54.55% were female. The distribution of customers in these categories can be seen in

the table and graph below.

Number of Flight per annum and Type of Travel: These variables are collected in a customer

survey. The first is the number of flights taken per year by each customer in the sample size,

which is considered continuous or ratio data. The second type of data is nominal and reflects the

reasons for travel reported by customers in the sample, including business travel, personal travel,

and mileage tickets.

Shopping, Eating, and Drinking at the Airport: These variables are related to customer

behavior at the airport. The first variable reflects the amount of money spent on shopping by

each customer in the sample size. The second variable reflects the amount of money spent on

food and drinks at the airport by each customer in the sample size.

Class of tickets: This variable represents the different types of flight tickets purchased by

customers in a sample size. This variable is classified as categorical data and includes three ticket

classes: Economy, Economy Plus, and Business.

Scheduled Departure Hour: This variable reflects the departure time of flights for each

customer in a sample size. This variable is categorized as interval data, with flight times ranging

from as early as 5 am to as late as 11 pm. The departure hours are grouped into three categories:

early flights from the 5th to the 10th hour, midday flights from the 11th to the 16th hour, and late

flights from the 17th to the 22nd hour.

The departure and arrival delay in minutes: These two variables track the number of delays,

in minutes, experienced by customers during their departure and arrival flights. Both of these

variables are considered ratio data and are strongly correlated with a correlation coefficient of

0.96. Due to this high correlation, the focus will be on the variable that tracks departure delay in

minutes.

Flight Time and Flight Distance: These two variables measure the duration of air travel for

each customer in a given sample size. The flight time variable represents the number of minutes

that the flight lasts, while the flight distance variable measures the distance, in meters, between

the take-off and destination points. Both of these variables are considered continuous or ratio

data.

Flight Cancelled: This variable indicates whether the flight that each customer in a sample size

was planning to take was canceled or not. This variable is categorized as nominal data.

FINDINGS FROM DATA ANALYSIS

A. Exploratory Data Analysis

Missing Data: The dataset includes a range of factors that may influence customers' satisfaction

with the airport and airlines' services. As such, the dataset is considered to be of high quality.

However, there are some customers who did not provide responses to certain questions within
the dataset. A table has been included below to illustrate the variables with unanswered

questions.

Missing Data Variables

Variable Departure Delay in Arrival Delay in Flight time in

minutes minutes Minutes

Missing Values 50 57 42

Avgerage value 15 minutes approx 15 minutes 112 minutes

added approximately approximately

Standardization of Data:

Standardization of data is the process of transforming data so that it has a mean of 0 and a

standard deviation of 1, The standardization process involves subtracting the mean of the data

from each data point and then dividing the result by the standard deviation of the data. The

resulting standardized values are unitless and represent the number of standard deviations away

from the mean. In our provided data we standardize the all quantitative data, so that it can be

easily comparable with each other. It is done in our excel sheet.

Satisfaction Level
According to the dataset, approximately 51% of customers reported higher levels of satisfaction

with the airport, while 49% reported lower levels of satisfaction. The satisfaction histogram is

presented below, and it is skewed to the left.

Age

The box plot of the dataset is approximately symmetrical, indicating that the satisfaction variable

follows a normal distribution. The box plot is displayed below. Additionally, the dataset suggests

that middle-aged individuals tend to fly more frequently then first category and then third

category which is older, while older individuals fly the least. This analysis is presented in the bar

chart below.
Gender and Satisfaction Level

The data shows that, on average, male passengers reported higher levels of satisfaction (3.52)

than female passengers (3.25). This finding was obtained with a standard error of 0.02 and a

confidence level of 95%, which resulted in a margin of error of 0.04. Consequently, male

passengers were found to have higher satisfaction levels. Furthermore, the dataset indicates that a

lower proportion of female passengers reported higher satisfaction levels, while a higher

percentage of male passengers reported higher levels of satisfaction. This analysis is illustrated in

the graph below.

 Gender Satisfaction
70%

60% 58%
55%
50% 45%
42%
40%

30%

20%

10%

0%
High Satis. Low Satis.

Female Male

Class and Satisfaction Levels:

As per observation on available data it is found, In terms of ticket class, Eco tickets had the

highest average satisfaction level of 3.39, followed by Eco Plus tickets with an average

satisfaction level of 3.28, and Business Plus tickets with an average satisfaction level of 3.2. The

margin of error for this analysis was 0.04, indicating that the difference in satisfaction levels

between the ticket classes was statistically significant. The graph is mentioned below.

Avg. Class Satis.

3.45 3.39
3.40
Avg. Satisfaction

3.35 3.28
3.30
3.25 3.20
3.20
3.15
3.10
Business Eco Plus Eco
Class Level
Airline Status and Flight Cancellation:

Out of the total available sample size, only 1.8% of flights were cancelled, with 72% of those

cancelled flights belonging to the Blue airline status, 16.7% belonging to the Silver status, and

11% belonging to the Gold and Platinum status, as Passengers with Platinum airline status

reported with Top Tier.

Airline Status and Satisfaction Level:

The satisfaction levels of passengers with Top Tier, Mid Tier, and Low Tier airline status were

analyzed, with Mid Tier status passengers reporting the highest average satisfaction level of 3.91,

followed by Top Tier status passengers with an average satisfaction level of 3.72, and Low Tier

status passengers with an average satisfaction level of 3.16. The margin of error for this analysis

was 0.04.

Avg. Tier Satisfaction

4.00 3.91
3.90
3.80 3.72
3.70
3.60
3.50
3.40
3.30
3.16
3.20
3.10
3.00
Top Tier Mid Tier Low Tier
Type of Travel and Satisfaction Level:

Passengers traveling for business purposes reported the highest level of satisfaction, with 72% of

those passengers indicating a higher satisfaction level. Passengers traveling for mileage purposes

reported a 60% satisfaction rate, while passengers traveling for personal reasons reported a lower

satisfaction level of 8%. Business travelers had the highest average satisfaction level of 3.79,

followed by Mileage travelers with an average satisfaction level of 3.51, and Personal travelers

with an average satisfaction level of 2.51. The margin of error for this analysis was 0.04. further

box plot is attached below which show data show normal Distribution.

Travel Type
100% 92%
80% 72%
60%
60%
40%
40% 28%
20% 8%
0%
Business travel Personal Travel Mileage tickets

High Satis. Low Satis.

Age and Satisfaction Level:

There was a weak negative linear relationship between age and satisfaction level that is -0.256,

with middle-aged customers reporting the highest level of satisfaction 65% and older people

reporting the lowest level of satisfaction 19%.

Number of Flights per annum and Satisfaction Level:

There was a weak negative linear relationship between the number of flights per annum and

satisfaction level -0.243, with passengers who flew less frequently reporting a higher level of

satisfaction than those who flew more often. Furhter visiting frequency has been categorized in

three parts 0 to 25, 26 to 50, and 51+.

Flights P.A Category

90.0% 81.1%
80.0%
70.0%
% of Satisfaction

56.9% 60.7%
60.0%
50.0% 43.1% 39.3%
40.0%
30.0% 18.9%
20.0%
10.0%
0.0%
0 - 25 26 -50 51+
Age Bracket

High Satis. Low Satis.

Spending at the Airport and Satisfaction Level:

There was a weak negative correlation between spending at the airport and satisfaction level,

with no significant correlation between shopping, eating/drinking, and satisfaction level.

Scheduled Departure Hour and Satisfaction Level:

Passengers with early flights and midday flights reported the highest average satisfaction level of

3.41 and 3.36 respectively, while passengers with late flights reported the lowest average

satisfaction level of 3.33.

Departure Average Satisfaction Level

3.44
3.42 3.41
3.40
3.38
3.36
3.36
3.34 3.33
3.32
3.30
3.28
Avg. Satisfaction

Early Flights Midday Flights Late Flights

Departure Delay in Minutes and Satisfaction Level:

Flights delayed up to 12 minutes had an average customer satisfaction level of 3.15, while flights

delayed for more than 12 minutes had an average customer satisfaction level of 3.374. There was

a weak negative correlation of -0.1 between departure delay in minutes and the customer

satisfaction level.

Flight Time in Minutes and Satisfaction Level:

Flights lasting up to 48 minutes had an average customer satisfaction level of 3.44, while flights

lasting longer than 48 minutes had an average customer satisfaction level of 3.36. There was a

weak correlation of 0.01 between flight time in minutes and satisfaction level.
Correlation of Variables: The correlation of the variables present in the data is calculated to

check the relationship between the variables, the value close to +1 high positive relationship, the

number close to 0 represent no relationship and number close to -1 represent the negative

relationship. The correlation table is shown below:

1 2 3 4 5 6 7 8
Satisfaction (1) 1.0000
Age (2) -0.2561 1.0000
No of Flights p.a. (3) -0.2436 0.2846 1.0000
Arrival Delay in Minutes (4) -0.0915 0.0160 0.0353 1.0000
No. of other Loyalty Cards (5) 0.1213 -0.4615 -0.2556 0.0067 1.0000
Shopping Amount at Airport (6) 0.0162 -0.0110 -0.0878 0.0013 0.0088 1.0000
Eating and Drinking at Airport (7) -0.0353 0.1066 -0.0797 0.0257 -0.0372 0.0421 1.0000
Scheduled Departure Hour (8) -0.0020 -0.0081 0.0020 0.0679 -0.0240 -0.0031 0.0431 1.0000

Covariance of Variables:

Covariance is a statistical measure that shows the relationship between two variables.

Specifically, it measures how much two variables change together. A positive covariance

indicates that the two variables move in the same direction: when one variable increases, the

other variable tends to increase as well, and when one variable decreases, the other variable tends

to decrease as well. On the other hand, a negative covariance indicates that the two variables

move in opposite directions: when one variable increases, the other variable tends to decrease,

and vice versa. The covariance of variables is shown in table below:

1 2 3 4 5 6 7 8
Satisfaction (1) 1.000
Age (2) -0.256 1.000
No of Flights p.a. (3) -0.243 0.284 0.999
Arrival Delay in Minutes (4) -0.092 0.016 0.035 0.999
No. of other Loyalty Cards (5) 0.121 -0.461 -0.255 0.007 0.999
Shopping Amount at Airport (6) 0.016 -0.011 -0.088 0.001 0.009 0.999
Eating and Drinking at Airport (7) -0.035 0.107 -0.080 0.026 -0.037 0.042 0.999
Scheduled Departure Hour (8) -0.002 -0.008 0.002 0.068 -0.024 -0.003 0.043 0.999
B. Predictive Analysis

The multi-regression is used in the predictive analysis, the dataset contains 2000 samples. The

descriptive statistics of the data of all variables are calculated in the excel file and presented in

the Appendix. We have included 8 variables in our multi-regression model.

Ŷ = b0 + b1x1 + b2x2 + b3x3 + b4x4 + b5x5 + b6x6 + b7x7

Where:

Ŷ: Airline passenger satisfaction b0: intercept

b1 – b8: the slope of their respective variables

X1: Age

X2: Number of flights per annum

X3: No. of another loyalty card

X4: Shopping amount at airport

X5: Eating and Drinking at the airport.

X6: Scheduled Departure Hour

X7: Arrival Delay in Minutes

We have used Excel for the regression output, the output of the multi-regression analysis in excel

is shown below:

Regression Statistics
Multiple R 0.324238129
R Square 0.105130365
Adjusted R Square 0.101985742
Standard Error 0.93676905
Observations 2000

ANOVA
 df SS MS F
Regression 7 205.3633 29.33761 33.43179
Residual 1992 1748.052 0.877536
Total 1999 1953.415

Standard
Coefficients Error t Stat P-value
Intercept 4.263412343 0.103241 41.29553 7.9E-270
Age -0.011959838 0.001405 -8.51436 3.25E-17
No of Flights p.a. -0.013085644 0.001559 -8.39419 8.77E-17
Arrival Delay in Minutes -0.001974579 0.000519 -3.801 0.000148
No. of other Loyalty Cards -0.020691451 0.020789 -0.99533 0.319697
Shopping Amount at Airport -2.4127E-05 0.000391 -0.06171 0.950802
Eating and Drinking at Airport -0.000513763 0.00041 -1.25398 0.209998
Scheduled Departure Hour 0.000590749 0.004516 0.130805 0.895943
The Scatter Diagram of the multi-regression equation is presented in appendix.

From the multi-regression output above, we have constructed, the following multi-regression

equation:

Ŷ = 4.26 -0.012 x1 - 0.013 x2 – 0.0019 x3 - 0.002 x4 + 0.000024 6 x5 – 0.00051 x6 – 0.00059

x7

The slope tells us how much the dependent variable (y) changes for each unit change in the

independent variable (x). A positive slope indicates that as x increases, y also increases, while a

negative slope indicates that as x increases, y decreases. The y-intercept (b) tells us the value of y

when x = 0. It represents the starting point or the value of y when the independent variable has

no effect on the dependent variable.

The above equation shows that most of the independent variables have a negative relationship

with the dependent variable having a negative slope.

Coefficient of determination (R^2):

We have also calculated the R^2 of the model. R^2 is a statistical measure that represents the

proportion of variation in the dependent variable that is explained by the independent variables in

a regression model. It is also known as the coefficient of determination. R^2 is a number

between 0 and 1, where 0 indicates that the model does not explain any of the variations in the

dependent variable and 1 indicates that the model explains all of the variations in the dependent

variable. In general, a higher R^2 indicates a better fit of the model to the data.

The R^2 which we got for our regression model is 0.105 or 10.5%, which suggested that model

only 10.5% variation in dependent is explained by the independent variables.

Hypothesis Testing

The Hypothesis that we have made above should be tested, we are testing the hypothesis based

on the 5% level of significance (which means we reject the null hypothesis if the p-value of the

variable is below 5%). From the output of the regression, which is presented in the appendix, we

can conclude that apart from No. of Other Loyalty Cards, Shopping amount at the airport, Eating

and Drinking at the airport and Schedule Departure Hour, all other variables are significant and

will be helpful in predicting the satisfaction of the customer in airlines. The summary of the

hypothesis is presented below:

Null Hypothesis P-value Action

Age doesn’t have an effect on Below 5% Reject the null hypothesis

satisfaction

No. of Flight per aum doesn’t Below 5% Reject the null hypothesis

have an effect on satisfaction

No. of other Loyalty Cards Above 5% Fail to reject null hypothesis

doesn’t have an effect on

 satisfaction

Shopping Amount at Airport Above 5% Fail to reject null hypothesis

doesn’t have an effect on

Satisfaction

Eating and Drinking at Above 5% Fail to reject null hypothesis

Airport at the airport doesn’t

have an effect on Satisfaction

Scheduled Departure Hour Above 5% Fail to reject null hypothesis

doesn’t have an effect on

Satisfaction

Arrival Delay in Minutes Below 5% Reject the null hypothesis

doesn’t have an effect on

Satisfaction

From the above analysis, we can conclude that the Age, No. of flights per anum and arrival delay

in minutes have effect on the satisfaction, and should be used to predict satisfaction.

Final Multi-Regression Analysis

In our final regression analysis, certain variables were removed based on their high p-values

(above 5%), along with other variables. The multiple R, which represents the coefficient of

multiple correlation indicating the correlation between the dependent and independent variables,

was reported as 32.2%, indicating a positive and strong relationship between the variables. The

R-squared and adjusted R-squared, which represent the goodness of fit of the linear regression
model and indicate whether the chosen model is appropriate, were both reported as 10.4% in the

final regression analysis.

Therefore, the final multi-regression equation:

Ŷ = b0 + b1 x1 + b2 x2 + b3 x3

Where:

Ŷ: Airline passenger satisfaction b0: intercept

b1 – b5: slope of their respective variables

X1: Age

X3: No. of flights per anum

X4: Arrival Delay in minutes

Output is presented below:

Regression Statistics
Multiple R 0.322447
R Square 0.103972
Adjusted R Square 0.102625
Standard Error 0.936435
Observations 2000

ANOVA
Df SS MS F
Regression 3 203.1003 67.7001 77.20289
Residual 1996 1750.315 0.876911
Total 1999 1953.415

Coefficients Standard Error t Stat P-value

Intercept 4.19164 0.062294 67.28784 0
Age -0.0116 0.001265 -9.17011 1.14E-19
No of Flights p.a. -0.01263 0.001526 -8.27632 2.29E-16
Arrival Delay in Minutes -0.002 0.000518 -3.8606 0.000117

Therefore the final multi-regression equation is,

Ŷ = 4.19 - 0.0116 x1 - 0.013 x2 – 0.002 x3

From the slope of the equation, we can conclude that all the independent variables are negatively

related with the dependent variables.

Discussion, implications of your findings, and conclusion:

In a nutshell, our research findings suggest that the customer’s airline satisfaction is based on

four characteristics: Gender, Age, No. of flights P.A, and delay in arrival time. Therefore, the

management of the airline industry should focus on these things while devising strategies to

improve customer satisfaction in the airline industry. The practical implications of findings that

airline satisfaction is affected by age and gender are significant for airlines seeking to improve

their customer experience. Here are some potential implications: Tailor services to specific

demographic groups: Airlines may need to consider tailoring their services and offerings to

specific demographic groups based on age and gender. For example, younger passengers may be

more interested in on-flight entertainment, while older passengers may prefer more comfortable

seating options. Target marketing efforts: Airlines may need to target their marketing efforts

based on the age and gender of their target audience. For example, advertising campaigns

targeting younger passengers could focus on the entertainment options available on flights, while

campaigns targeting older passengers could focus on comfort and convenience. Training staff:

Airlines may need to train their staff to be more sensitive to the needs of different age and gender

groups. For example, staff may need to be trained to offer more assistance to older passengers or

to be more attentive to the needs of female passengers. Identify areas for improvement: Airlines

can use age and gender as a basis for identifying specific areas for improvement in their

customer experience. For example, if older passengers are consistently reporting low levels of
satisfaction with seating options, airlines may need to consider investing in more comfortable

seating options for this demographic. Monitor customer satisfaction: Airlines can use age and

gender as a basis for monitoring customer satisfaction over time to identify changes in

satisfaction levels. Overall, understanding the effects of age and gender on airline satisfaction

can help airlines improve their customer experience, tailor their services, and better meet the

needs of their customers.

Airline satisfaction research can be improved in several ways in the future. Here are some

suggestions: Use a representative sample: The research should aim to include a representative

sample of airline passengers to ensure that the findings are applicable to the wider population.

This can be achieved through random sampling techniques and by ensuring that the sample

includes a diverse range of participants. Include a range of satisfaction measures: The research

should use a range of satisfaction measures, including both objective and subjective measures.

This could include factors such as on-time performance, in-flight services, and customer service.

Use multiple data collection methods: To ensure a comprehensive understanding of airline

satisfaction, the research should use a range of data collection methods, such as surveys,

interviews, and focus groups. This will allow for a more in-depth exploration of the factors

influencing satisfaction.

Use advanced analytical techniques: The research should use advanced analytical techniques,

such as machine learning and predictive modeling, to identify patterns and trends in the data.

This will enable the identification of key drivers of satisfaction and allow airlines to develop

targeted strategies for improvement.

References:
Chatterjee, S. and Chakraborty, S. (2017). “Factors affecting passengers’ satisfaction on

domestic airlines: An empirical study”. Journal of Air Transport Management, 59, pp. 13-20.

Gudmundsson, S.V. (2005). “The impact of route length on air passenger satisfaction: An

empirical analysis”. Journal of Air Transport Management, 11(4), pp. 259-272.

Han, H., Hyun, S.S., Kim, W. and Lee, J. (2019). “Factors affecting passengers’ loyalty to full-

service airlines and low-cost carriers: Differences between South Korea and Taiwan”.

Journal of Air Transport Management, 75, pp. 1-9.

Jain, P.K. and Gupta, S. (2018). “Factors affecting passengers’ satisfaction in Indian aviation

industry: An empirical study”. Journal of Air Transport Management, 72, pp. 65-75.

Jeon, S., Kim, Y. and Lee, C. (2012). “Airline service quality and passenger satisfaction: A case

study of Korean Air”. Journal of Air Transport Management, 18(4), pp. 242-245.

Liang, J. and Zhang, F. (2018). “A study on Chinese air passengers

Appendix:
Satisfaction Eco. Satis.Eco. Satis. Mid Tier Satis.

Mean 3.3685 Mean 3.393791844

Standard Error 0.022104257 Standard Error 0.024309068
Median 4 Median 4
Mode 4 Mode 4
Standard Deviation 0.988532421 Standard Deviation 0.985342233
Sample Variance 0.977196348 Sample Variance 0.970899316
Kurtosis -0.521335767 Kurtosis -0.488996655
Skewness -0.350725984 Skewness -0.370123355
Range 4 Range 4
Minimum 1 Minimum 1
Maximum 5 Maximum 5
Sum 6737 Sum 5576
Count 2000 Count 1643
Confidence Level(95.0%) 0.043349795 Confidence Level(95.0%) 0.047680044

Mid Tier Satis. Busi. Satis. Early Flights Satis.

Mean 3.907216495 Mean 3.786699108

Standard Error 0.034105555 Standard Error 0.023218226
Median 4 Median 4
Mode 4 Mode 4
Standard Deviation 0.671801531 Standard Deviation 0.81528711
Sample Variance 0.451317297 Sample Variance 0.664693073
Kurtosis -0.784799898 Kurtosis 0.892282277
Skewness 0.110737176 Skewness -0.760650002
Range 2 Range 4
Minimum 3 Minimum 1
Maximum 5 Maximum 5
Sum 1516 Sum 4669
Count 388 Count 1233
Confidence Level(95.0%)0.067055368 Confidence Level(95.0%) 0.045551638
 Early Flights Satis. Not Delayed
NotSatis.
Delayed Satis. Flight time 48 mints Sa

Mean 3.414705882 Mean 3.649350649

Standard Error 0.0389104 Standard Error 0.100861351
Median 4 Median 4
Mode 4 Mode 4
Standard Deviation 1.014659081 Standard Deviation 0.885054767
Sample Variance 1.02953305 Sample Variance 0.783321941
Kurtosis -0.489181325 Kurtosis -0.467753507
Skewness -0.407518286 Skewness -0.410264393
Range 4 Range 3
Minimum 1 Minimum 2
Maximum 5 Maximum 5
Sum 2322 Sum 281
Count 680 Count 77
Confidence Level(95.0%) 0.076399164 Confidence Level(95.0%) 0.200882791

Flight time 48 mints Satis.

Mean 3.43533123
Standard Error 0.054900444
Median 4
Mode 4
Standard Deviation 0.977474611
Sample Variance 0.955456615
Kurtosis -0.444278647
Skewness -0.431233268
Range 4
Minimum 1
Maximum 5
Sum 1089
Count 317
Confidence Level(95.0%) 0.108016597
 Scatter Plot
Satisfaction Age
Linear (Age) No of Flights p.a.
Arrival Delay in Minutes No. of other Loyalty Cards
Shopping Amount at Airport Eating and Drinking at Airport
Scheduled Departure Hour
5
4

3
2
1

0
0 100 200 300 400 500 600 700 800 900 1000

Table 1:

Sum of Average of Count of

Row Labels Satisfaction Satisfaction2 Satisfaction2
15 -37 2302 3.5 664
38 – 60 3166 3.6 869
61+ 1269 2.7 467
Grand Total 6737 3.4 2000
Table 2:

Row Labels Sum of High Satisfaction. Sum of Low Satisfaction.

15 -37 55.0% 45.0%
38 – 60 65.0% 35.0%
61+ 19.1% 80.9%
Grand Total 139.0% 161.0%

Table 3:

Row Labels Sum of Satisfaction Average of Satisfaction2 Count of Satisfaction2

Female 3679 3.3 1132
Male 3058 3.5 868
Grand Total 6737 3.4 2000