Since it is the primary goal of all medical studies to be able to apply findings to other populations, it is important to eliminate the possibility of misleading results. For this purpose, statistical significance is used. It implements mathematical deductive logic to calculate the probability that the results obtained during the research are not chance findings and will be repeated if the experiment is conducted again. Generally, it depends on the sample size: the bigger it is, the more chances there are that the results are real. Statistical significance is expressed as a probability (p), which is conventionally set at 0.05. This implies that the results of the research can be called statistically significant only under the condition that the compatibility with the null hypothesis is small (Chung & Storey, 2014).
In contrast, clinical significance answers whether the difference between the old and the new way of treatment found as a result of the study is substantial enough to recommend altering the old practice. There are cases when the improvement in therapy is insufficient to be a grounded cause for changing the clinical approach (Chambrone & Armitage, 2016).
Yet, the study can be clinically significant even if the null hypothesis could not be rejected. For instance, if two types of drugs are tested and it is found out that the new one produces the same effect as the old one, there are still differences in practice. It may be so that the new one is more affordable to patients or produce fewer side effects, which means that although they are the same, the new drug can be recommended as a substitution.
If the credibility of the results from a qualitative study is questioned, they are still clinically significant. For example, it may be unclear if music produces a positive effect on people suffering from depression. On the other hand, it is clear that it is soothing and never leads to an aggravation of the condition. Thus, it may mean that this therapy may be applied in clinical settings.
References
Chambrone, L., & Armitage, G. C. (2016). Commentary: Statistical significance versus clinical relevance in periodontal research: Implications for clinical practice. Journal of Periodontology, 87(6), 613-616. Web.
Chung, N. C., & Storey, J. D. (2014). Statistical significance of variables driving systematic variation in high-dimensional data. Bioinformatics, 31(4), 545-554. Web.