Fig. 4
From: The analysis of continuous data from n-of-1 trials using paired cycles: a simple tutorial
Illustration of technique of pooling a prior variance with the variance from a given patient (in this case patient number 5). The 95% confidence limits are shown. Information from the other patients is assumed to be available, and various possible weights in terms of ‘prior degrees of freedom’ are considered. The point estimate is unaffected, but depending on prior degrees of freedom assumed, the estimated variance and the critical value of the t-distribution will change