Quantifying Uncertainty with Bayesian Statistics

As a response to this sort of criticism, many have promoted parameter estimation as a better method over hypothesis testing. For example, you could estimate the difference in the treatment and placebo groups, along with the 95% confidence interval as a measure of the uncertainty in that estimate. However, confidence intervals are often misinterpreted as meaning there is a X% change the parameter falls in the interval. Instead, the correct interpretation is obtuse: if you did your experiment an infinite number of times and calculated the confidence interval for each of those experiments, then X% of the time the X% confidence interval would contain the true parameter. For any one experiment though, there is no probability calculated to tell you if your confidence interval actually contains the true parameter, the parameter is either in the interval or not.