Statistical significance and meaningfulness are important factors to evaluate in research. For instance, statistical significance implies the chance of rejecting the null hypothesis in a research in the event that it was true. The significance level is predetermining before collecting and analyzing the data which depends with the field of study – it may vary from subject to the other (Ellis & Steyn, 2003). On the other hand, statistical meaningfulness may also vary with the type of test and in t-tests and anova studies it reflects the effect size while in association tests it depicts the plausibility of the results. Some results may be statistically significant but spurious indicating that they are not meaningful.
Evaluating case scenario #3
The study assessed the differences between men and women on cultural competency scores. Statistically, the results are reasonable but due to the small effect size, they are not meaningful. Several aspects can be evaluated here spanning from the sample size to the p-value. The sample size was large enough for both the independent samples. However, the sampling approach was not randomized because the study utilized the convenience approach to select the sample subjects and this indicates that the study findings were not generalizable. This was not a true representative of the whole population. Additionally, there is difference in the competency scores between men and women because the p-value observed was less than the significance level (0.05) meaning that the null hypothesis was rejected, hence statistically significance level. However, since the effect size was small, perhaps less than 0.20, the results are not meaningful (Sullivan & Feinn, 2012).
Delegate your assignment to our experts and they will do the rest.
Evaluating case scenario #4
The case presented assessed the correlation between job satisfaction and income level – hence a correlation test of association. The sample size was sufficient (large enough) and drawn from all the three sectors and this tells that this was a true representation of the whole population. Statistically, a correlation coefficient of 0.87 indicates a strong positive correlation while a p-value less than 0.05 indicates a statistically significant association. However, the fact that there is no clear association to social change indicates that the findings were not meaningful. Tentatively, it indicates that the effect size was very small, perhaps 0.01 or less, indicating spurious association between income and job satisfaction (Hacking, 2016). This could have been brought by a third confounding factor or a lurking variable.
References
Ellis, S. M., & Steyn, H. S. (2003). Practical significance (effect sizes) versus or in combination with statistical significance (p-values): research note. Management Dynamics: Journal of the Southern African Institute for Management Scientists , 12 (4), 51-53.
Hacking, I. (2016). Logic of statistical inference . Cambridge University Press.
Sullivan, G. M., & Feinn, R. (2012). Using effect size—or why the P value is not enough. Journal of graduate medical education , 4 (3), 279-282.
