Rizki Mayandi Hasibuan

Introduction to data Domestic and foreign major companies invested billions in Vietnam’s e-commerce industry. In 2018, five Vietnamese companies were among Southeast Asia’s topten most-visited e-commerce websites. The ecosystem has seen rapid development in terms of product diversity, technical infrastructure, and support services. E-commerce models for consumer-to-consumer, business-to-business, and consumer-to-business transactions have developed gradually over time. Emerging business ideas include selling through social media and mobile phones. The evolution of selling from websites to live broadcasts demonstrates the worldwide e-commerce industry’s growth. Electronic businesses may potentially benefit from the growing digital content industry. Additionally, many domestic and foreign businesses have begun to develop cross-border e-commerce. This market will continue to expand in the coming years. The data set consists of 11 questions to measure customer perception in the online environment. The sample size is equal to 485. The questionnaire has been responded to by participants who bought from e-commerce websites. We want to classify the questions of this research to get the best results. The two multivariate methods for the analysis are exploratory and confirmatory factor analysis. We start with the exploratory factor analysis and continue to drag the appropriate number of factors. Exploratory data Analysis Exploratory data analysis (EDA), which originated centuries ago, is a data analysis approach that emphasizes pattern recognition and hypothesis generation from raw data. It is suggested as the first step of any data analysis task for exploring and understanding data, and has been applied in many disciplines such as Geography, Marketing, and Operations Management. However, even though EDA techniques, such as data visualization and data mining, have been used in some procedures in auditing, EDA has not been employed in auditing in a systematical way. This dissertation consists of three essays to investigate the application of EDA in audit research. The study contributes to the auditing literature by identifying the importance of EDA in auditing, proposing a framework to describe how auditors could apply EDA to auditing, and using two cases to demonstrate the benefits that auditors can gain from EDA by following the proposed framework. First of all, we checked the presence of missing values in the data. There are no missing values. For finding the outliers, we perform the data by Rosner test. The results showed that there is no outlier there. By PCA method, the scree plot of the data is shown in below: A common method for determining the number of PCs to be retained is a graphical representation known as a scree plot. A Scree Plot is a simple line segment plot that shows the eigenvalues for each individual PC. It shows the eigenvalues on the yaxis and the number of factors on the x-axis. It always displays a downward curve. Our scree plot tells us that we can drag three factors from the data to measure customer perception in the online environment. Before this, we examined the sample adequacy and the validity of the data. KMO is a test conducted to examine the strength of the partial correlation (how the factors explain each other) between the variables. KMO values closer to 1.0 are considered ideal while values less than 0.5 are unacceptable. This statistic for out data is equal to 0.74 which is ideal. Bartlett’s test for Sphericity compares your correlation matrix (a matrix of Pearson correlations) to the identity matrix. In other words, it checks if there is a redundancy between variables that can be summarized with some factors. The value of this statistic is less than 0.05. The three factors are shown in the below table: Factor 1 H1 0.747 H2 0.806 H3 0.792 H4 0.852 2 H5 0.733 H6 0.785 H7 0.851 H8 0.538 3 H9 0.936 H10 0.772 H11 0.412 All the factors are considered latent variables. There are three latent variables. We can call the three factors as follows: 1. Hedonic value 2. Perceived Mental Benefits 3. Electronic Loyalty These are the three factors that could measure customer perception in the online environment. Confirmatory Factor Analysis Factor analysis is a family of statistical strategies used to model unmeasured sources of variability in a set of scores. Confirmatory factor analysis (CFA), otherwise referred to as restricted factor analysis, structural factor analysis, or the measurement model, typically is used in a deductive mode to test hypotheses regarding unmeasured sources of variability responsible for the commonality among a set of scores. It can be contrasted with exploratory factor analysis (EFA), which addresses the same basic question but in an inductive, or discovery-oriented, mode. Although CFA can be used as the sole statistical strategy for testing hypotheses about the relations among a set of variables, it is best understood as an instance of the general structural equation modeling (SEM). In that model, a useful distinction is made between the measurement model and the structural model. The measurement model (i.e., CFA) concerns the relations between measures of constructs, indicators, and the constructs they were designed to measure (i.e., factors). The structural model concerns the directional relations between constructs. In a full application of SEM, the measurement model is used to model constructs, between which directional relations are modeled and tested in the structural model. (PsycINFO Database Record (c) 2012 APA, all rights reserved). In the last part, we dragged the three factors. Now, we can make a structural model equation and consider some hypotheses to investigate the relationship between the factors. The model is shown as follows: Hypotheses: H1: PMB significantly impacts HV H2: HV significantly impacts ELOY H3: PMB significantly impacts ELOY The regression standard coefficients are shown in here: Coefficient T statistic PMB --< 0.424 8.581 --< ELOY 0.275 4.302 PMB --< ELOY 0.564 8.606 HV HV After analyzing the survey data in R software, the result in above Table 5 shows that all criteria to assess the mediating role of hedonic value are satisfied. Therefore, hedonic value is a partial mediator in relationship-perceived mental benefits and electronic loyalty. Because all the t- statistics are higher than 1.96, we can say that all the mentioned hypotheses are significant. Reliability and validity assessment of the model A Cronbach’s alpha coefficient (CA) higher than 0.7 was used to evaluate scale reliability. A scale has convergent validity when the composite reliability (CR) is equal to or more than 0.7. ‫متغیرها‬ PMB HV ELOY CRONBACH COMPOSITE RELIABILITY Validty )Alpha>0.7( )Cr>0.7( )AVE>- - - We see that all the measurements are ideal. It means that our model is a significant and valid model. We perform an Exploratory Factor Analysis to reduce the dimension and to understand which latent factors affect customer perception in the online environment. In addition, confirmatory factor analysis was performed to research how well the data fit the model. CFA was also used for testing hypotheses that there are relationships between the observed variables and the latent factor or construct. There are some other multivariate methods that could be used in extending the research. Canonical correlation analysis is used to identify and measure the associations between two sets of variables. Canonical correlation is appropriate in the same situations where multiple regression would be, but where are there are multiple intercorrelated outcome variables. Canonical correlation analysis determines a set of canonical variates, orthogonal linear combinations of the variables within each set that best explain the variability both within and between sets. References 1. Fabrigar, L. R., & Wegener, D. T. (2011). Exploratory factor analysis. Oxford University Press. 2. Gorsuch, R. L. (1988). Exploratory factor analysis. In Handbook of multivariate experimental psychology (pp. 231-258). Springer, Boston, MA. 3. Khoa, B. T. (2022). Dataset for the electronic customer relationship management based on SOR model in electronic commerce. Data in brief, 42, 108039.