Statistical Analysis Example: E-banking Use by Customers with Different Education Levels

Draw a conceptual model

Is your time best spent reading someone else’s essay? Get a 100% original essay FROM A CERTIFIED WRITER!

Save 25%

The conceptual model that represents the e-banking scenario is that which checks the association between the attitude towards e-banking and the various other variables in the dataset. The model relates the attitude towards e-banking to the level of education, sex, age group, usefulness among other factors.

Observed and latent variables

Observed variables include the sex, age group and the level of education while the latent variables include usefulness of e-banking and the individuals' attitude towards e-banking.

Research problem

The study is concerned with determining if the age group, sex, level of education and usefulness each have a significant influence on the attitude towards the e-banking services. Various statistical tests are conducted to test the various hypotheses.

Importance of literature review

A literature review is crucial before beginning this study since it ensures that the researcher is well informed of what other research works say on the same subject. The relevant library books for review, in this case, include those that relate to the societal perspective of e-banking and contemporary money management. The literature review should as well cover the books on statistical analysis using SPSS especially the independent sample t-test

Hypotheses to be tested

Hypothesis 1

H0: There is no significant difference between the customer intentions to use e-banking with varying level of education.

H1: There is a significant difference between the customer intentions to use e-banking with varying level of education

Hypothesis 2

H0 The regression model is not significant.

H0: The regression model is significant.

Hypothesis 3

H0: There is no significant correlation between the customer intentions to use e-banking and age.

H1: There is a significant difference between the customer intentions to use e-banking and age.

Statistical tests for these hypotheses

Hypothesis 1: independent sample t-test

Hypothesis 2: linear regression

Hypothesis 3: correlation test

Question 2

Regression analysis

This is a statistical technique that is used in numerically determining the relationship between one dependent or response variable and another one or more independent variables. In a case where we one independent variable, the procedure is called simple linear regression. In a case where we have more than one independent variable, the procedure is called multiple linear regressions.

Correlation analysis

This is a procedure that is used to numerically determine the strength of association between two or more variables in a data set. It leads the researcher to obtain a correlation coefficient which usually is a value between -1 and 1.

One way ANOVA

ANOVA is a statistical technique used to compare three or more sample means. An F statistic is obtained from the ANOVA output that is used in concluding whether or not the means differ significantly. In one way ANOVA, one of the groups under study has further subgroups.

Cross-tabulations

This is used in testing if there is an association between two or more categorical variables. This is done using the chi-square test. We usually reject the null hypothesis if the P-value or the significance code is less than 0.05.

Frequency analysis

This is used to help obtain the descriptive statistics of the various components of a given dataset. The frequencies, when running as well, leads to a display of histograms and bar charts that are usable in determining the distribution of the various variables in a dataset. Factor analysis

This is a statistical technique that is used in describing the variability among various correlated variables that are observed. The factor analysis is used in searching for joint variation between various latent variables.

Cluster analysis

This is a statistical technique that involves the grouping of a set of items or variables into one same group known as the cluster. The clusters in one way or another are usually similar.

PART 2

Question 1(regression output)

Dependent variable: customer attitude on the ease of use

Independent variable: usefulness, web security.

Regression model:

Customer Attitude on the ease of use= 1.152+0.474 Usefulness+0.308 Web security

Usefulness: an increase in usefulness by 1 causes a corresponding increase in the customer attitude by 0.474

Web security: an increase in the web security by 1 causes a corresponding increase in the customer attitude by 0.308

Question 2(regression output)

Dependent variable: intention to use e-banking

Independent variable: customer attitude.

Regression model:

Intention to use e-banking = 0.641+ 0.843 Attitude

Attitude: an increase in attitude by 1 causes a corresponding increase in the customer intention to use e-banking by 0.843.

Question 3

All the five components of the E-banking model exhibit relatively strong positive correlations. The highest correlation on both upper and lower side of the matrix is that between ITOU and the customer's attitude towards the use of e-banking. The lowest correlation is that between the variables web services and EOU.

Question 4

Dependent variable: customer's intention to use e-banking services.

Independent variable: level of education.

Hypothesis

H0: There is no significant difference between the customer intentions to use e-banking with varying level of education.

H1: There is a significant difference between the customer intentions to use e-banking with varying level of education.

To test this hypothesis, we conduct the independent sample t-test. The results are as shown below:

From the output above, we fail to reject the null hypothesis since the P-value was found to be 0.729 which is greater than 0.05. Therefore, there is a significant difference between the customer intention to use e-banking with varying level of education.