The 21 st century has witnessed a heightened demand for higher education, with governments putting in place different measures to ensure that as many people as possible make it to tertiary institutions after secondary education. Consequently, universities across the world, including Qatar University, have registered an increase in enrollment. With that, questions have been asked on whether the increase in enrollment has been matched with a corresponding upgrade of campus facilities. Though the main purpose of a tertiary institution is to deliver quality education, the role of facilities such as fitness centers, food services, medical centers, transport, and support facilities for people with special needs cannot be downplayed. Besides affecting the quality of life on campus, previous studies have suggested that the quality of student services in universities affects the academic outcomes.
Theoretical frameworks
Higher education is widely regarded as part of the service industry. This means they have an obligation to provide the highest level of service to their customers; the main customers in higher education are students. With more and more private universities coming up, there is increased competition among universities to attract students. Universities cannot sustainably rely on government funding, and they must go out of their way to increase student populations to remain financially stable. That includes adjusting the campus environment to make it suitable for students from different cultures, including international students. A high student population is one of the factors that give a university a competitive edge over others. Freeman (1999) suggests that customers are stakeholders in any business, and the management should prioritize their satisfaction. Placing Freeman’s (1984) stakeholders’ theory in the context of higher education, university administrators need to understand and prioritize student needs to remain competitive. Thomas & Galambos (2004) assert that when a university treats its students as customers, the institution is likely to achieve success in effectiveness and recruitment.
Delegate your assignment to our experts and they will do the rest.
Most of student satisfaction surveys take two approaches: measuring the level of student satisfaction with the quality of education offered and gauging the level of total student satisfaction. Total student satisfaction measures the student experience in regard to both the quality of life on campus and the quality of the academic programs offered. The total student satisfaction plays a key role in determining whether a student will stay in a particular university until the end of their course (Appleton-Knapp & Krentler, 2006)
Problem statement
Globalization has pushed universities to be more business-minded; there is high competition among top universities to attract international students. Students are the main customers in tertiary education, so the profitability and financial health of universities are pegged on their ability to deliver high-quality services to the students (Douglas, Douglas, & Bernes, 2006). Conducting student satisfaction surveys is one of the strategies that university administrators can use to get feedback from the students. The management can use the feedback to improve the quality of academic programs and campus facilities. Students, as the main customers for learning institutions, need a platform to express their dissatisfaction with the quality of services offered (Elliot & Healy, 2001). Student dissatisfaction can have adverse effects on learning institutions.
Objectives
This Research study investigates the level of student satisfaction with the services offered by Qatar University. Qatar University and other institutions of higher learning can use the findings of this study to identify the areas of service delivery that need improvement and to make their services more students centered. This research focused on food, transport, medical, and special needs services. The study addressed the following research questions:
What is the overall student satisfaction level with the quality of services offered by Qatar University?
Is gender an important factor in determining the level of student satisfaction; is there a disparity between male and female students in terms of student satisfaction?
Is there a disparity in the level of student satisfaction among students in different years of study?
Literature Review
Due to the crucial role of student satisfaction in the success of learning institutions, there are plenty of literatures focusing on the topic. These literatures were reviewed to obtain a conceptual framework and provide information on the accepted models of measuring student satisfaction.
Çelik & Akyol (2015) made use of questionnaires to measure the level of student satisfaction with campus facilities among undergraduate students. The responses of the undergraduate student in the questionnaire were used as the dependent variables. The study focused on sports and cultural facilities. The main aim of the study was to use categorical data estimation methods to determine the predictors of student satisfaction with campus facilities. Çelik & Akyol (2015) collected data using written and self-administered questionnaires. The sample size was 1000 undergraduate students. The minimum sample size was calculated using a predetermined formula that aimed to maximize representation as well as proportionality. The questionnaires contained detailed questions, including the respondent’s demographic background and income levels.
Çelik & Akyol (2015) used logit models to analyze the responses in the questionnaires. The overall level of satisfaction with the campus facilities was assigned as the dependent variable; the responses were presented in a Likert scale format. For example, 1 was for ‘very dissatisfied ’ while 5 was for ‘very satisfied.’ The impact of the dependent variable in the logit model was then measured against independent variables such as age. The statistical analysis was performed using Stata. The level of significance of the statistical model obtained was 99 percent. The model was also compatible with small values of the Akaike and Bayesian Information Criteria.
According to the finding of Çelik & Akyol (2015), the factors affecting the level of student satisfaction with campus facilities and services were age, income level, whether the student is a tuition loan holder, the student’s faculty, and the student’s personal preference such as the type of music they listen to. The study found out that social sciences students had the lowest level of satisfaction. High-income students and tuition loan holders were found as less likely to be satisfied than low income and non-tuition loan holders respectively. Also, Çelik & Akyol (2015) concluded that age was a key determinant of the level of satisfaction. Regarding the overall level of satisfaction, Çelik & Akyol (2015) found out that roughly 50 percent of the students were dissatisfied with the facilities in the school.
Siming, Niamatullah, Gao, Xu, & Shaf (2015) investigated the factors influencing student satisfaction in higher learning institutions. They collected data by issuing questionnaires to students in different universities. The sample size was 200, and the respondents were selected using non-probability sample designs. The study asked the respondents to indicate their level of satisfaction in different areas: student experience, faculty preparedness, campus services and facilities, and teacher-student relationships. Siming et al. (2015) used the overall level of student satisfaction as the criterion variable. The responses for each question were given numerical numbers. For example, 1 represented ‘very poor’ while 5 represented very good. Siming et al. (2015) analyzed the collected data using SPSS software. The alpha value for student satisfaction and campus facilities and services was 0.7, indicating that their reliability was within the acceptable range.
Using SPSS software, Siming et al. (2015) performed a correlation analysis of the different variables with the criterion variable. Of the four variables, campus facilities and service had the highest correlation with the overall student satisfaction. Siming et al. (2015) also used regression models to determine the extent to which a change in each of the four variables affects the level of student satisfaction. Change in student experience had the highest impact on the total student satisfaction; student experience was followed by teacher-student relationship. Siming et al. (2015) also used descriptive analysis to investigate the relationship between the predictor variables and the criterion variable. The study concluded that campus facilities, student experience, faculty preparedness, and teacher-student relationship all had a significant impact on the level of student satisfaction.
Marshak, Van Wieren, Raeke Ferrell, Swiss, & Dugan (2010) covered the problems that special needs college students face in regard to the use of disability services and accommodations. This was a qualitative study conducted among 46 students with disabilities in the USA. There was no sampling as only the students who responded to invitation letters were interviewed. The disability conditions represented were cerebral palsy, visual impairment, learning disabilities, severe mental conditions, speech disorders, attention deficit disorder, and seizure disorder. The researchers conducted semi-structured interviews with the respondents; each interview session took about two hours. The responses of interest in the study were those relating to the student’s experience on campus and the use of special needs services.
Marshak et al. (2016) used editing analysis to interpret the qualitative data collected in the interviews. That involved going through interview recordings to identify the fragments that were relevant to the study questions. The data fragments were then sorted to identify patterns and structures that could be useful in the research. Multiples researchers analyzed the data to reduce bias. Investigator triangulation was also applied to eliminate bias. Investigator triangulation entails using more than one method to collect and analyze data on the same topic (Thurmond, 2001). The researchers individually reviewed the interview recordings so as comprehend the data. They then synthesized the data jointly, which entailed agreeing on the categorical themes exhibited by the data. They then coded the five categorical themes identified. A different set of researchers reviewed the coded transcripts to identify more themes under the five main categorical themes. Eleven sub-categorical themes were identified and coded.
The Marshak et al. (2016) qualitative analysis revealed that most special needs students had problems using the accommodations provided by the school. Emotional issues topped the reasons why special needs students are not comfortable using on-campus accommodations. These emotional issues include the need to avoid stigma and negative peer reactions, poor quality of the utilities received, and difficulties in explaining their special needs. Most of the respondents expressed concerns that using the accommodations provided by the schools would make them dependent on other students, thus exposing them to peer disapproval.
Kumar (2014) investigated the level of student satisfaction with different campus services and facilities among students in Sirsa District, India. It measured the level of student satisfaction with the regularity of teachers, teachers' behavior towards students in the classrooms, sports facilities, parking spaces, lab equipment, and course fee structures. Kumar (2014 ) then used simple percentages to analyze the collected data. The study concluded that students were least satisfied with lab facilities, IT tools, and lab facilities. Areas that recorded the highest level of student satisfaction were parking space, library, and teacher regularity and behavior.
Chandra, Ng, Chandra, & Priyono (2018) covers the relationship between the quality of service offered by post-secondary education institutions, student satisfaction, and student loyalty. Specifically, Chandra et al. (2018) worked on three research questions: the relationship between quality of service and student satisfaction, the relationship between quality of service and student loyalty, and the relationship between student satisfaction and student loyalty. Chandra et al. (2018) was an explanatory research that aimed to establish the relationship between the three variables. Explanatory researches are preliminary studies on a subject that has not been exhaustively covered before (Gelo, Braakmaan, & Benetka, 2008).
Chandra et al. (2018) used the quality of service offered by learning institutions as the exogenous variable. Student loyalty and the level of student satisfaction were assigned as the endogenous variables. The study distributed about 1100 questionnaires among students from different universities in Riau district, Indonesia. After expunging those that contained incomplete information, the researchers were left with 1000 questionnaires, which was way above the minimum sample size for populations exceeding 75, 000. Chandra et al. (2018) used IBM SPSS v21 to analyze the data collected. The analysis techniques used were Analysis of Variance (ANOVA) and Structural Equation Modelling (SEM). While analyzing the data, Chandra et al. (2018) took the respondent’s demographic characteristics into consideration.
In Chandra et al. (2018) study, most of the respondents indicated they were dissatisfied with the quality of services offered by their institutions. The main areas of concern were poor administrative services and uncomfortable classes. Regarding the influence of age on student satisfaction, Chandra et al. (2018) found that older students are more likely to be dissatisfied. This finding corroborates the conclusion of Çelik & Akyol (2015) regarding the relationship between age and student satisfaction. Chandra et al. (2018) found no significant disparity in the level of student satisfaction and loyalty between students in public universities and those in private universities. On the relationship between student satisfaction and loyalty, Chandra et al. (2018) concluded that student satisfaction does not have a significant impact on student loyalty.
Seeing as first-year students experience a sudden change in environment and social setting, Al-Sheeb, Hamouda, & Abdella (2018) sought to establish the factors determining the level of student satisfaction in their first year of study in public universities in Qatar. The study also investigated the correlation of the overall level of student satisfaction with the academic, social, and environmental aspects of campus life. According to Al-Sheeb, Hamouda, & Abdella (2018), the social aspects of campus life describe the interaction between the student and other members of the college. The environmental aspect entails the student’s utilization of campus resources while the academic aspects entail the acquisition of knowledge and skills. The study borrowed conceptual ideas from Astin’s (1984) developmental theory of higher education and Tinto’s (1975) theory of student departure. The two literatures had identified the most important aspects of first-year college life as course effectiveness, a sense of belonging, citizenship knowledge and skills, interaction with other people on campus, and utilization of campus facilities (Al-Sheeb, Hamouda, & Abdella (2018).
The study administered questionnaires to 282 students at Qatar University. The question measured the impact of the five student satisfaction determinants as per Astin’s interaction theory and Tinto’s student departure theory. Al-Sheeb, Hamouda, & Abdella (2018) interpreted the data collected using artificial neural networks and regression analysis. They used SPSS v. 24 in the analysis. The researchers first generated descriptive statistics to gain a general understanding of the data. They then calculated the Pearson’s correlation coefficient to derive the relationship between the variables. Multiple linear regressions were used to measure the impact of the five variables on the variance of overall student satisfaction. Al-Sheeb, Hamouda, & Abdella (2018) then used artificial neural networks and binary logistic regressions to predict the impact of the five variables on overall student satisfaction. The specific research questions were the correlation of the five determinants of student satisfaction with the total student satisfaction, the contribution of the five determinants to the variance in the level of overall student satisfaction, and the effectiveness of artificial neural networks and binary logistic regressions in predicting student satisfaction.
Al-Sheeb, Hamouda, & Abdella (2018) concluded that social, academic, and environmental aspects of college life have a positive correlation with the overall student satisfaction in the first year of study. These findings are consistent with those of Siming et al. (2015). The factors that had the highest correlation with the overall student satisfaction were course effectiveness and the sense belonging. The five variables combined had a 44 percent impact on the variance of student satisfaction. That means the overall student satisfaction in the first year of study can be enhanced by increasing the four variables.
Tessema, Ready, & Malone (2012) researched the impact of gender on student satisfaction and performance. They worked with the hypothesis that gender affects the overall student satisfaction with the courses they are studying. The second hypothesis was that gender affects academic performance. The study used data that was collected over nine years through student surveys. The university sent surveys to senior students to express their views on how satisfying the major curriculum was. The surveys were only sent to students who had registered more than 90 credit hours. The survey forms had Likert scales to measure the responses. For instance, 1 represented ‘very dissatisfied’ while 4 represented ‘very satisfied.’ The survey also obtained the demographic characteristics of the respondents such as age and the year of study. The academic scores of the students were obtained from the university's database and matched to the responses. The data analysis software used in the study was not indicated.
Tesema et al. (2012) used Analysis of Variance (ANOVA ) and correlation matrixes to interpret the collected data. Female students registered higher level s of major curriculum satisfaction than male students. However, the study concluded that there was no significant correlation of gender with major curriculum satisfaction. Tesema et al. (2012) note that one possible explanation for the phenomena is that female students tend to receive more academic and personal support from faculties than male students as revealed by Sax and Harper (2005).
Different literatures have suggested that one of the strategies universities can use to increase student retention is increasing student satisfaction. Archambault (2008) measured the effect of satisfaction on student retention. Like Al-Sheeb et al. (2018), Archambault (2008) borrowed theoretical constructs on student retention from Tinto (1975). Tinto (1975) had suggested that predictors of whether a student will drop out of college include the level of commitment, the student’s loyalty to the institution, and the social and academic integration. Archambault (2008) used a sample of 450 students from three universities in the USA. To increase the response rate, professors issued out the questionnaires before starting their lectures. The demographic characteristics of the respondents were indicated in the questionnaires. In particular, the student’s income level was noted since it has a significant influence on student retention. Archambault (2008) used structural equation modeling to test the hypotheses. The model of the study was improved by observing the goodness of fit indices and chi-square differences. The statistical software used in the analysis was not indicated. The SEM analysis did not reject the null hypothesis that there is no positive relationship between student satisfaction and student loyalty. This finding corroborates the findings of Chandra et al. (2018). Archambault (2008) concluded that there is a positive relationship between student satisfaction and student loyalty.
Huesman Brown, Lee, Kellogg, & Radcliffe (2007) explored whether the use of on-campus recreational and accommodation facilities had an impact on academic outcomes. The academic outcomes considered were GPA, persistence, and graduation rates. The data used in the study was obtained from the records department in one of the universities in the USA. Students in the institution are required to scan their identity cards to gain entry to campus facilities. The records department in the institution has electronic records on how frequently a particular student uses campus facilities. The student demographic characteristics and academic records were also obtained from the university records. Huesman et al. (2007) used descriptive statistics, logistic regression models, and simple ratios to interpret the data. The statistical analysis tool used was not indicated. The study concluded that living in campus residence halls in the first year of study has a positive impact on academic performance. Huesman et al. (2007) did not find any relationship between the rate of utilization of campus facilities and academic performance.
With globalization, more and more universities are targeting international students. Considering that international student’s come from diverse cultural backgrounds, universities may need to put in place additional measures to satisfy them. Yasin & Bélange (2015) explored the factors that influence student satisfaction among international students. The study targeted international students pursuing business courses at Laurentian University in Canada. The researcher issued questionnaires to 50 respondents who were selected using non-probabilistic sampling techniques. The questionnaire contained two parts: one collected demographic data while the other collected data on the research variables. The responses were in a Likert scale format, with 1 representing “strongly disagree” and 7 representing “strongly agree.” The questionnaire was based on the SERVQUAL model. SERVQUAL is an instrument that researchers use to measure consumer expectations and perceptions (Buttle, 1996). Yasin & Bélange (2015 applied analysis of variance (ANOVA) and regression models to establish the relationship between the variables under consideration. The statistical analysis tool used was Stata.
Yasin & Bélange (2015) concluded that the overall satisfaction among international college students is lower than what they expect when joining the institutions. Yasin & Bélange (2015) also established that age, gender, and work experience influenced the level of satisfaction among international students. Female students expressed a higher level of dissatisfaction than their male counterparts. The level of student satisfaction increased with work experience.
Data Analysis Techniques
Cronbach’s Alpha Reliabilty Test
Cronbach’s Alpha Reliability test is one of the most utilized measures of reliability in orgnaizational and social sciences (Bonnett & Wright, 2015). The test takes into account a several measurements and describes the reliability of the sum or mean of those measurements. These measurements may represent the raters, occassions, alternative forms or questionairre or test items. The alpha obtained from this test measures the internal consistency of the measurements in terms of reliability. Therefore, it can be applied when the questionairres are taken to measure the reliability of the information obtained.
Internal Validity using Pearson Correlation
Pearson Correlation is also referred to as the bivariate correlation and is a measure of how to variables; say X and Y correlate with one another. Pearson correlation is expressed with values that range from +1 to -1 with +1 showing that the variables have strong postive linear correlation and -1 showing the variables have strong negative linear correlation. Essentially, pearson correlation can be obtained by calculating the covariance of the two varaibles and dividing by the standard deviations. It can therefore show the essence of a variable with regard to another the extent to which the two variables relate linearly.
Factor Analysis using Principal Component Analysis (Varimax rotation)
Principal Component Analysis is a mathematical procedure that can be used to reduce a large set of variables to a small set of variables in multivariate analysis. The small set of variables retain the most of the information in the large set of variables (Budaev,2010). It is performed on a square symmettric matrix and is used in cases where the data collected has a lot of correlated variables that can be significantly reduced. Once, the prinicipal component analysis is performed on a dataset, the result enable the researcher to make meaningful conclusions on the data collected with the almost the same accuracy as it would have been if the data was tested using the large dataset (Budaev, 2010).
2-Sample T-test
A two-sample T-test is used to test whether the means of two independent samples are equal (Keselman et al., 2004). The two independent samples may either be paired or unpaired; paired sample refer to samples that have a one-to-one correspondence between the values in the two samples.The test is adminstered based on two hypotheses that is the null hypothesis and the alternate hypothesis. A test statistic is obtained using the t-test formula and is compared to the critical value based on a certain alpha level. If the test statistic is larger than the critical value then the null hypothesis is rejected. However, if not, then the we fail to reject the null hypothesis (Keselman et al., 2004).. This test can be used to test assumptions of datasets collected through the uses of hypotheses.
One-way ANOVA
The one-way ANOVA is a statistical test that is used to compare the means of two or more independent samples and determine if they is evidence that points out they are statistically different (Hesamian, 2016). The one-way ANOVA and the 2-sample T-test can be used to compare the means of two independent samples however, only the one-way ANOVA can be used to compare the means more than two independent samples. The one-way ANOVA utilizes hypotheses as well; the null hypothesis and the alternate hypothesis. To determine what hypothesis to accept, reject or fail to reject, the F-value is calculated and compared to the F-statistic. If the F-value is larger than the F-statistic, then we reject the null hypothesis and if it is smaller, we fail to reject the null hypothesis. The one-way ANOVA can be used to test the results of different groups of individuals taking the same questionnaire.
Mann-Whitney U test
The Mann-Whitney U test is a type of test that is nonparametric and is used to establish whether a randomly selected value from one of the populations will be less than or greater than a randomly selected value from another value selected from a second population (McKnight & Najab, 2010). The test can be used to determine whether values of certain variables in a sample were obtained from the populations with the same distribution. This test would be useful in this case to determine how closely different samples obtained from the same population relate to each other and how well they represent the population.
Stepwise Regression
Stepwise regression is a type of regression that formulates models by automatically eliminating predictor variables based on prespecified conditons (Bendel, 1977). The process involves step by step addition and subtraction of explanatory variables from a set through F-tests, t-tests, adjusted R 2 among other until a suitable model is reached that has a combination of predictor variables with the most significant impact on the dependent variable. The final model can be used to predict certain values or important aspects of a research based on a set of independent variables that may be already articulated.
Multivariate Regression
Multivariate Regression is a type of regression that is used to obtain a single regression model that has more than one outcome variable (Izenman, 2013). The model therefore would contain more than one predictor variable as well as more than one independent variable. The method is broadly utilized for the puposes of prediction of behavior of certain response variables based on changes in predictor variables until a desired degree of relation has been established. Therefore, this type of regression can be used to answer and find suitable combination of predictor variables to ensure a desired response variable is obtained.
MANOVA
Multivariate Analysis of Variance (MANOVA) is similar to ANOVA only that it has several dependent variables (Chatfield, 2018). MANOVA tests for the difference in two or more vectors of means while ANOVA tests for the differences that are present between two or more means. Just like ANOVA, a multivariate F value is obtained when doing research on several groups with several dependent variables. MANOVA manages to test the multiple dependent variables by creating new dependent variables which can maximize group differences.
References
Al-Sheeb, B., Hamouda, A. M., & Abdella, G. M. (2018). Investigating Determinants of Student Satisfaction in the First Year of College in a Public University in the State of Qatar. Education Research International , 14-28.
Appleton-Knapp, S. L., & Krentler, K. A. (2006). Measuring student expectations and their effects on satisfaction: The importance of managing student expectations. Journal of marketing education , 28 (3), 254-264.
Archambault, L. Z. (2008). Measuring student satisfaction and its impact on student retention: Developing a combined model for use in private, post-secondary institutions . Nova Southeastern University.
Astin, A. W. (1984). Student involvement: A developmental theory for higher education. Journal of college student personnel , 25 (4), 297-308.
Buttle, F. (1996). SERVQUAL: review, critique, research agenda. European Journal of Marketing , 30 (1), 8-32.
Çelik, A. K., & Akyol, K. (2015). Predicting Student Satisfaction with an Emphasis on Campus Facilities in a Turkish University. International Education Studies , 1913-1939.
Chandra, T., Ng, M., Chandra, S., & Priyono. (2018). The Effect of Service Quality on Student Satisfaction and Student Loyalty. Journal of Social Studies Education Research , 109-131.
Douglas, J., Douglas, A., & Barnes, B. (2006). Measuring student satisfaction at a UK university. Quality assurance in education , 14 (3), 251-267.
Elliott, K. M., & Healy, M. A. (2001). Key factors influencing student satisfaction related to recruitment and retention. Journal of marketing for higher education , 10 (4), 1-11.
Freeman, R. E. (1999). Divergent stakeholder theory. Academy of management review , 24 (2), 233-236.
Gelo, O., Braakmann, D., & Benetka, G. (2008). Quantitative and qualitative research: Beyond the debate. Integrative Psychological and behavioral science , 42 (3), 266-290.
Huesman Jr, R. L., Brown, A. K., Lee, G., Kellogg, J. P., & Radcliffe, P. M. (2007). Modeling Student Academic Success: Does Usage of Campus Recreation Facilities Make a Difference?
Kumar, V. (2014). Students’ Satisfaction Level in Higher Educational Institutes: A Study of Public Institutes in Sirsa. International Journal of Engineering and Management Research , 145-149.
Marshak, L., Wieren, T. V., Ferrell, D. R., Swiss, L., & Dugan, C. (2010). Exploring Barriers to College Student Use of DisabilityServices and Accommodations. Journal of Postsecondary Education and Disability , 151-163.
Sax, L. J., Bryant, A. N., & Harper, C. E. (2005). The differential effects of student-faculty interaction on college outcomes for women and men. Journal of College Student Development , 46 (6), 642-657.
Siming, L., Niamatullah, Gao, J., Xu, D., & Shaf, .. (2015). Factors Leading to Students’ Satisfaction in Higher Learning. Journal of Education and Practice , 1735-1742.
Tessema, M., Ready, K., & Malone, C. (2012). Effect of Gender on College Students’ Satisfaction and Achievement: The Case of a. International Journal of Business and Social Science , 145-156.
Thomas, E. H., & Galambos, N. (2004). What satisfies students? Mining student-opinion data with regression and decision tree analysis. Research in Higher Education , 45 (3), 251-269.
Thurmond, V. A. (2001). The point of triangulation. Journal of nursing scholarship , 33 (3), 253-258.
Tinto, V. (1975). Dropout from higher education: A theoretical synthesis of recent research. Review of educational research , 45 (1), 89-125.
Yasin, Y. M. & Bélanger, C. H. (2015). Key Determinants of Satisfaction among International Business. International Journal of Business and Management , 1833-1840.
Bonett, D. G., & Wright, T. A. (2015). Cronbach's alpha reliability: Interval estimation, hypothesis testing, and sample size planning. Journal of Organizational Behavior , 36 (1), 3-15.
Immink, K. A. S., & Weber, J. H. (2014). Minimum Pearson distance detection for multilevel channels with gain and/or offset mismatch. IEEE Transactions on Information Theory , 60 (10), 5966-5974.
Budaev, S. V. (2010). Using principal components and factor analysis in animal behaviour research: caveats and guidelines. Ethology , 116 (5), 472-480.
Keselman, H. J., Othman, A. R., Wilcox, R. R., & Fradette, K. (2004). The new and improved two-sample t test. Psychological Science , 15 (1), 47-51.
Hesamian, G. (2016). One-way ANOVA based on interval information. International Journal of Systems Science , 47 (11), 2682-2690.
Bendel, R. B., & Afifi, A. A. (1977). Comparison of stopping rules in forward “stepwise” regression. Journal of the American Statistical association , 72 (357), 46-53.
Izenman, A. J. (2013). Multivariate regression. In Modern Multivariate Statistical Techniques (pp. 159-194). Springer, New York, NY.
McKnight, P. E., & Najab, J. (2010). Mann ‐ Whitney U Test. The Corsini encyclopedia of psychology , 1-1.
Chatfield, C. (2018). Introduction to multivariate analysis. Routledge.
