So lets start talking about distributions. Distributions of data points for a variable in a population. Now there are many, many, many different distribution types and they are quite different for discreet data types and for continuous data types. The one that we are going to be interested in, obviously is for continuous data types. That is the format in which the data types where most of the analysis that we do in medical statistics come in is continuous data types and most important of all of those is the normal distribution. Now the normal distribution really is the most common type of random variable distribution and it passes that there's some pattern to this distribution to the actual data points such that there's a high frequency of certain values. So certain actual values occur much more commonly than others. The further away, the bigger the difference between an individual value and those values that occur very commonly, the less common they become. Now that means that there is some symmetry to this is you get father away from both sides away from the mean, you get less and less common values. This curve is a bell shape, usually referred to as being bell shaped and that symmetry in the bell shape of the curve allows us to come up with a rule of thumb that is called the empirical rule. Now have a look at this. Let me remind you just of the standard deviation. Remember? And we had a set of sample data points and we can plot them all on an x-axis and we can also plot exactly where the mean is. The standard deviation is the average distance of all of values and the mean. So we just look at all the values. The difference between that value and the mean, we sum all of them up and divide it by how many there are, so a type of mean. The mean or the average in distance away difference with the mean. So look at the bell-shaped curve, a normal distribution at the bottom. It says, the following if we include all values that are within one standard deviation, that's the average distance away average difference away from the mean. If we included all values that are within one standard deviation away from the mean. If the values are normally distributed, we'll get about 68% of all the values. If we include all values that are within two standard variations away from the mean, we're gonna include about 95%. Now that's going to ring a bell with you, that should ring a bell with you. If we were to include 95% of all values, that means we're left with five and five on either side means 2.5 on either side, 0.025 on each side, 2.5% on each side. So if we found a value that's further than two standard deviations away from the mean, those were values would occur very infrequently. We might be talking about values, there that are very significant to find and that's exactly how we're going to look at Statistical tests. It's the same principle. Lastly, if we go about three standard deviations away from the mean, we include all of those values, that would be about 99.7%. So this is just a rule of thumb. We can't use this rule when we do statistical analysis, but we're going to work on this kind of premise. I just want to remind, you might come across the standard normal distribution, that is really where we have a mean of zero and a standard deviation of exactly one.