E-commerce. A study of the factors that influence the e-consumer's trust-building model of initial trust and purchase intention

In this section, we will provide a brief description of the tests that we used in our statistical analysis.

Independent-Samples T-test
It is a parametric test used to find a relation between a categorical variable and a dichotomous cardinal variable. The T-test is used to compare the means of two samples or independent groups in order to understand if the groups are statistically different. The first step is the calculation of the means of each sample; whether a significant difference between them exists, we can infer that the two samples come from two different populations; on the other hand, if the means are not different, we can state that the samples come from the same population.

One-way ANOVA test
It is used to determine whether there are any significant differences between the means of two or more independent (unrelated) groups. Through the one-way ANOVA test it is possible to compare a polythomic categorical variable and a scale variable. The one-way ANOVA is an omnibus statistical test and does not indicate which specific groups were significantly different from each other; it only shows that at least two groups were different. Since three, four, five or more groups can be compared in the study design, determining which of these groups differ from each other is important. To do this, it is possible to use a Post-hoc test. In particular, in this dissertation we used the Bonferroni test.

Crosstabs and Chi-square test
It is a test used to study the relationship between two variables, that can be either two categorical or two ordinal variables. This test aims at verifying the frequency distribution of two or more variables, in order to study all the possible combinations. The Chi-square test is employed to investigate the relationship between two categorical variables. It allows to understand if the two variables influence each other or if they are independent. The numerical value of the Chi-square varies from 0 to 1. Whether the two variables are related the value will be close to 1. Moreover, the Chi-square allows us to confirm or reject Null Hypothesis (H0) or the Alternative Hypothesis (H1). The former is true when the values are identical to each other, the Chi-square is thus non-significant and, as a result, the result obtained is merely a sample case. The latter is true when the Chi-square is significant. However, the significance level must be verified by the means of the analysis of the p-value.

Bivariate correlation
It is a test used to relate two cardinal variables. Also in this test it is important to consider the p-value to check if our test is significant or not. Furthermore, we have to take into account the so-called Pearson Correlation (r), a statistical measure of the strength of a linear relationship between paired data. This coefficient defines the intensity of the relationship between the two variables analysed by the test. The value of the Pearson Correlation varies between -1 and +1. The more the r value gets close to the outer value, the more the relationship between the variables is intense; if the value of r tends to zero, the relationship is weak. When the value of r is close to -1 the variables are inversely proportional, i.e. when the independent variable increases, the dependent variable diminishes. On the contrary, when the value of the Pearson Coefficient is close to 1, when the independent variable increases the same does the dependent variable.

Spearman correlation
It is a test used to relate two cardinal variables. Also in this test it is important to consider the p-value to check if our test is significant or not. Furthermore, we have to take into account the so-called Correlation Coefficient, a statistical measure of the strength of a relationship between paired data. This coefficient defines the intensity of the relationship between the two variables analysed by the test. The value of the Correlation Coefficient varies between -1 and +1. The more the Correlation Coefficient gets close to the outer value, the more the relationship between the variables is intense; if the value of the Correlation Coefficient tends to zero, the relationship is weak. When the value of the Pearson Coefficient is close to -1 the variables are inversely proportional, i.e. when the independent variable increases, the dependent variable diminishes. On the contrary, when the value of the Pearson Coefficient is close to 1, when the independent variable increases the same does the dependent variable.

Factor analysis
Factor analysis identifies unobserved (i.e., latent) variables that explain patterns of correlations within a set of observed variables. It is often used to identify a small number of latent variables that explain most of the variance embedded in a larger number of observed variables. Thus, factor analysis is about data reduction.