Objective 1
To understand about the spread and the dispersion of the consumer demographic graphics characteristics their descriptive statistics were performed. The report1 below represents descriptive statistics.
The descriptive statistics indicate that the average of a consumer is 1.97. it had a standard deviation of 0.811 and skewness of 0.48. This is implied that age had approximately a standard normal distribution. The buying frequency had an average of 2.04 this indicated that most consumers had a buying frequency of two-three times (van der Ploeg et al, 2014). From the descriptive statistics, most of the variables followed a standard normal since they had a skewness that has a close to zero.
The purchasing intention had an average of 1.60 which meant that most of the consumers had an intention of purchasing. It had a standard deviation of 0.491 and skewness 0.07 which indicated that it had a standard deviation.
The following hypothesis was used to test the claim of the proportion who had a buying intention.
H0: The proportion of people who had the intention of buying doesn’t differ
Versus
H1: The proportion of people who had the intention of buying was greater than 50%
A Pearson chi-squared test was carried out to investigate the hypothesis. The test has a p-value less than zero. Thus the null hypothesis was rejected. Therefore, the proportion of people who had a buying intention was greater than 50% (Grenouillet et al, 2011). This implied that most people had a buying intention.
Report 1
| . |
Objective 2
A Cronbach’s test was performed to investigate the internal reliability of WOM. The Cronbach’s test had a coefficient of 0.864, this indicated that there was internal reliability. Thus there was a consistent in the WOM credibility factor (Wong, 2013).
The factor scores of the factor WOM credibility were calculated and there are in the output the report 2 below. The descriptive statistics for the factor scores indicated that there were 153 observations. The factor scores had a standard deviation of 1.25 this indicated that there was less variability among the consumer’s response. They also had an average of 3, this indicated that most women credibility factor responses among the consumers had a neutral response (Bhutta et al, 2012).
A test was carried out to investigate whether the overall scores for WOM credibility differed from 12 based on the following hypothesis.
H: the average overall scores of WOM credibility is 12
Versus
H: the average overall scores for WOM credibility is different from 12
An independent t-test was carried out to investigate the above hypothesis. The output for the test is in the report 2 below. The t-test had a p-value of zero, which was less than 5% level of significance thus, the null hypothesis was rejected (Panchal et al, 2013). Therefore the average overall scores for WOM credibility was statistically significantly different from 12.
An analysis of variance was performed to investigate whether the overall scores for wom credibility differs among gender. The following hypothesis below was used to investigate the claim that wom credibility is different for gender.
H0: the average overall factor scores for wom credibility is the same between genders.
H1: the average overall factor scores for wom credibility differs among gender.
The output for the ANOVA is in report 2 below. The ANOVA test had a p-value of 0.00 which is less than 5% level of significance thus the null hypothesis was rejected (Alper et al, 2011). Therefore, the overall factor scores for whom credibility differs among gender. This implied that the overall average scores for a male are different from that of females.
A test was carried out to investigate whether the average overall scores differs with the buying frequency the following hypothesis was used to investigate the claim.
H0: the average overall factor scores for WOM credibility is the same for buying frequency
H1: the average overall factor score for WOM credibility differs among the buying frequency.
The output for the ANOVA is in report 2 below. The ANOVA test had a p-value of 0.00 which was less than 5% level of significance thus null hypothesis was rejected (H0). This lead to the conclusion that the average overall factor scores for WOM credibility are different from those who had a buying frequency of once or more than once (Sakar et al, 2011).
Report 2
# Internal reliability test
Factor analysis
Descriptive statistics:: factor scores
#test for the significance
#wom Based on gender
#wom based on the buying frequency
Objective 3
To investigate the association between the various items of the factor homophily and various predictor variables such as gender, age, marital status, and occupation. The homophily had H1, H2, H3, and H4. All the homophily factor items were used as the response variables. The output of the model fitted is represented in the report 3 below.
When H1 was used as the response variable the analysis of variance had a p-value of 0.000 which was less than 5% level of significance, therefore, the null hypothesis that all the explanatory variable were insignificant was rejected (Baglin, 2014). The conclusion is that the explanatory variables used were statistically significant in explaining the homophily (H1)
When H2 was used as the response variable the analysis of variance had a p-value of 0.89 which was greater than 5% level of significance, therefore, the null hypothesis that all the explanatory variable were insignificant was accepted. The conclusion is that the explanatory variables used was not statistically significant in explaining the homophily (H2)
When H3 was used as the response variable the analysis of variance had a p-value of 0.165 which was greater than 5% level of significance, therefore, the null hypothesis that all the explanatory variable were insignificant was accepted. The conclusion is that the explanatory variables used was not statistically significant in explaining the homophily (H3) (Bhutta et al, 2012).
When H4 was used as the response variable the analysis of variance had a p-value of 0.035 which was less than 5% level of significance, therefore, the null hypothesis that all the explanatory variable were insignificant was accepted. The conclusion is that the explanatory variables used was statistically significant in explaining the homophily (H4)
A regression model was used to investigate the association between homophily and the buying frequency. When the homophily items H1, H2, H3, and, H4 as the response variable, the null hypothesis being tested, that all the explanatory variables were insignificant was rejected since all the models of p-value 0.00 which was less than 5% level of significance. Therefore there was an association between all levels of homophily and the buying frequency.
Report 3
#anova table for the above
#H2 response variable
#anova table for H2 table
#h3 response variable
#anova table for h3 response variable
#h4 response variable
#anova table for h4 response
Objective 4: regression
To investigate the relationship between WOM credibility and the overall scores homophily, authority, and reviewability. The WOM credibility acted as the response variable and the other variables were used as the explanatory variables. The overall factor scores for the homophily, authority, and reviewability were calculated and used as the single independent variable for WOM credibility. The fitted regression model was . this implied the overall WOM credibility increased by 0.383 units per unit increase in all independent variable (Wong, 2013). The following hypothesis was used to investigate whether all the independent variables were significant in explaining the wom credibility.
H0: the overall scores are not insignificant in explaining the wom credibility
H1: the overall scores are significant in explaining the wom credibility
The analysis of variance was is in report 4. The test had a p-value of 0.00 which was less than 5% level of significance, thus the null hypothesis was rejected. Therefore the explanatory variable is statistically significant in explaining the wom credibility.
To investigate the relationship between WOM credibility and the overall scores for the independent variable and gender are significant. The fitted model was . To test whether the explanatory variables were significant in explaining the model the following hypothesis were formulated:
H0: the explanatory variables are not insignificant in explaining the wom credibility
H1: the explanatory variables are significant in explaining the wom credibility
The ANOVA test had a p-value of 0.000 which was less than 5% level of significance thus the null hypothesis was rejected. Therefore, the explanatory variables are significant in explaining the model (Baglin, 2014).
Report 4
| a. Dependent Variable: average_scores |
References
van der Ploeg, T., Austin, P.C. and Steyerberg, E.W., 2014. Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints. BMC medical research methodology, 14(1), p.137.
Grenouillet, G., Buisson, L., Casajus, N. and Lek, S., 2011. Ensemble modelling of species distribution: the effects of geographical and environmental ranges. Ecography, 34(1), pp.9-17.
Wong, K.K.K., 2013. Partial least squares structural equation modeling (PLS-SEM) techniques using SmartPLS. Marketing Bulletin, 24(1), pp.1-32.
Bhutta, M.M.A., Hayat, N., Farooq, A.U., Ali, Z., Jamil, S.R. and Hussain, Z., 2012. Vertical axis wind turbine–A review of various configurations and design techniques. Renewable and Sustainable Energy Reviews, 16(4), pp.1926-1939.
Panchal, V., Gupta, A., Tiwari, D.P. and Rathi, N., 2013. Evaluation Of Just In Time (JIT) Elements In Banking Sector Using Anova Technique. International Journal of Innovative Research in Science, Engineering and Technology, 2(2), pp.460-468.
Alper, B., Riche, N., Ramos, G. and Czerwinski, M., 2011. Design study of linesets, a novel set visualization technique. IEEE transactions on visualization and computer graphics, 17(12), pp.2259-2267.
Sakar, E., Keskin, S. and Unver, H., 2011. Using of factor analysis scores in multiple linear regression model for prediction of kernel weight in Ankara walnuts. J. Anim. Plant Sci, 21(2), pp.182-185.
Baglin, J., 2014. Improving your exploratory factor analysis for ordinal data: A demonstration using FACTOR. Practical Assessment, Research & Evaluation, 19(5), p.2.
