whenever you work with a histogram you should be able to describe it or characterize it somehow and some of the most common terms that we use to describe histograms are those that you'll see right now so we talked about symmetric histograms skewed histograms and we'll often talk about you know modal or bimodal asymmetric histogram is exactly what you would think it's something like what you're seeing in this first picture symmetric histograms can be either perfectly symmetric or approximately symmetric but in our line of work based upon sampling a lot of times we're working with approximately symmetric histograms as you would see in this picture you can see that what I've got on this left side of the middle is not a perfect mirror image of what I have on the right side but it's pretty close and as long as it's in that vicinity of being similar on the left and on the right then we would describe it as being an approximately symmetric histogram in a histogram that is skewed to the right is one that would look like this so you could see that the tail is long on that right side I actually worked with a histogram recently that was skewed to the right that was doing some data analysis on incomes of a number of people that were part of my sample and most people had incomes annual incomes that were in the zero to a hundred thousand range that was kind of this cluster but then we had some outliers who made an awful lot of money and so they were really skewing the average and so that's why this is called skewed to the right they were skewing that average to the right based upon these out these extreme values being so far out to the right and then skewed to the left would be the long tail would be on the left side may be a variable that we would see data skewed to the left would be the number of hours that you slept last night and so if we if we pull the number of people how long did you sleep last night and we looked at the distribution it might look something like this the bulk of people might sleep somewhere between you know five and eight hours and then you'd have some outliers in that very low extreme who would be skewing the average and skewing some of our statistics to the left a little bit so long tail to the right it's skewed to the right long tail to the left we say it's skewed to the left we'll also use the terms you know modal and bimodal you know modal suggests that the histogram only peaks once so this is the classic picture for a you know modal histogram this is also the the type of histogram that will probably end up working with most in this class because a lot of data that will look at follows what we call that bell curve or that normal curve and that's kind of what we're seeing with with this type of a histogram and this histogram has those properties where it is symmetric where it is you know modal there is one distinct peak and we can contrast that with a bimodal histogram a bimodal histogram is where there are two distinct peaks so make sure that there really is that trend to two distinct peaks in order to characterize it as a bimodal histogram okay so hopefully you can apply these terms now let's check out the next video and we'll dig into stem-and-leaf plots and even when we're talking about stem-and-leaf plots and not just histograms what we're also going to be able to use some of these terms