Confidence interval provides an approximated range of values that is probable to include an unknown parameter of a population. The approximated range is computed from a given data sample set. Confidence interval acts as one way to assist a researcher evaluate the possible value of a wider population. It offers the reasonable range of values, bracketed by upper and lower limits which incorporate the true value or unknown population approximated by the sample odds ratio, correlation coefficient or mean. It is normally reported either as 99%, 95% or 90%. Confidential intervals can be employed descriptively. Confidence intervals more typically used in statistical testing and can as well be employed to establish clinical significance since it provides possible value of sample which can include the true value or the unknown value and thus it can be applied to evaluate if the data can impact current medical practices (Fethney, 2010).).
Clinical Significance versus Statistical Significance
One of the main contrivances between statistically significant and clinical significant is the application of the word significance in the two cases. Statistical importance is frequently misinterpreted as clinically essential result. Significance is literally equated to importance, although statistically, significance contains a far more limiting connotation. Statistical significance measures quantify the study results probability as a result of chance. On the other hand, clinical significance is the effect of the magnitude of the real treatment that will establish if the if outcomes of a trial are probable to impact the existing medical practices (Ranganathan et al., 2015). In my opinion, the two terms are very diverse in the meaning and maybe a different term should be used instead of statistical significance such as statistical relevance to eliminate the conflict the current term significance brings in the term statistical significance.
Fethney, J. (2010). Statistical and clinical significance, and how to use confidence intervals to help interpret both. Australian College of Critical Care Nurses, 23(2), 93-97.
Ranganathan, P., Pramesh, C. S., & Buyse, M. (2015). Common pitfalls in statistical analysis: Clinical versus statistical significance. Perspective in Clinical Research, 6(3), 169-170.