Hypothesis Testing
Confidence intervals and hypothesis testing are well-known and widely used tools in healthcare research that enable statistical inference about population parameters from representative samples. Hypothesis testing is used to determine whether a statistically significant difference exists between two groups. Usually, the groups incorporated are a treatment group and a control group of the sample.
Confidence Intervals
Confidence intervals, however, represent the range of values within which a valid parameter, such as the mean or proportion, has the possibility of being discovered (Hespanhol et al., 2019). Together, these tools enable researchers to draw clear conclusions about treatment efficacy or the relationship between two variables.
Examples of Using Confidence Interval
Drug Testing
For example, a researcher may want to test the effectiveness of a new drug for lowering blood pressure (BP). A sample of patients can be recruited and assessed, and then randomly assigned to either the control group, which receives the placebo, or the treatment group, which receives the pills. After that, BP will be measured for each party to calculate a confidence interval for the difference in mean values.
Suppose the confidence interval does not include zero. In this case, the result indicates a statistically significant difference between the treatment and control groups, allowing the researcher to reject the null hypothesis of no difference (Hespanhol et al., 2019). Conversely, if the confidence interval includes zero, the researcher cannot conclude that there is a significant difference; therefore, the null hypothesis cannot be rejected.
Cancer Treatment
Another example of healthcare utilizing these methods is a clinical trial of a new cancer treatment. Patients are randomly assigned to a control or a treatment group, and the proportion in remission is measured. Thus, the testing-the-hypotheses method will determine whether a significant disparity in the proportion of patients achieving remission persists between the two groups. The confidence interval will estimate the range of the proportion of patients in remission in the population. This information will help researchers determine whether a treatment is effective and can be recommended, so this combined method is effective.
Reference
Hespanhol, L., Vallio, C. S., Costa, L. M., & Saragiotto, B. T. (2019). Understanding and interpreting confidence and credible intervals around effect estimates. Brazilian Journal of Physical Therapy, 23(4), 290–301.