Suppose that there were 226977 visitors to your website over a period of a week, and of those 56330 clicked on the button to get more information about your product. If you wanted to model the probability distribution of the number of visitors who clicked the button, you would typically estimate the mean of the distribution to be equal to the observed number of visitors who clicked, that is the sample mean: 56330. Now, suppose that you have data on visits collected at a different time. This time 27213 Visitors, out of a total of 108879, clicked the button. If you assume that the probability that a visitor clicks the button is determined by the earlier data (i. e. 56330 visitors clicked out of 226977), what is the probability of seeing these new data? Using the numbers from the previous problem, you should have gotten a fairly low probability that exactly 27213 visitors out of a total of 108879 clicked the button (assuming p=56330/226977). A more useful question would consider a range of click counts, specifically: What is the probability that the number of visitors who clicked the button is 27213 or fewer?