A researcher conducts research to answer a particular question called a hypothesis. Research must involve hypothesis testing to accept or reject a claim. For it to accept or reject a claim, the set confidence interval must be attained. The confidence interval is calculated from a sample population and contains a range of values, one of them being the actual value (Kock, 2016). Confidence intervals are similar to significance levels and p values and are used to reject or accept the null hypothesis. A confidence interval given as [21 26] indicates that the actual value lies between numbers 21 and 26. The null hypothesis is accepted when the value obtained lies in this interval; otherwise, it is rejected.

An example of using both hypothesis testing and confidence interval is when investigating the mean body temperature of a normal person and under normal conditions. In this example, the null hypothesis claims that the mean body temperature is 98.6 degrees. The 95% confidence interval is constructed as [98.0 and 98.5]. The next step involves establishing whether the mean body temperature is 98.6 degrees (Tofighi & Kelley, 2020). Since 98.6 does not lie in the confidence interval, the null hypothesis is rejected. Even when p values are used instead of the confidence interval, then the p-value obtained is less than 0.05, indicating that the null hypothesis is rejected.

References

Kock, N. (2016). Hypothesis testing with confidence intervals and P values in PLS-SEM. International Journal of e-Collaboration (IJeC), 12(3), 1-6.

Tofighi, D., & Kelley, K. (2020). Indirect effects in sequential mediation models: Evaluating methods for hypothesis testing and confidence interval formation. Multivariate Behavioral Research, 55(2), 188-210.