 Hi, this is Dr. Don. I have another problem out of Chapter 9 on correlation. We're given some data on two variables, row 1 and row 2, and we're asked to calculate the correlation coefficient R, first letting row 1 be x, and then letting row 2 be x, to see if it impacts the correlation coefficient. Now, if you look in Larson, you're given these humongous equations to use to find R, but we can do it much, much faster using stat crunch, and I'm going to show you a shortcut to solving this problem. I'm going to open up stat crunch, get the data in there, so we have our data. Now, normally you could go to summary stat correlation, select those two, and click compute, and you'd have the correlation coefficient minus 0.512, but there's no way to reverse, and the reason for that, of course, stat crunch realizes it doesn't matter for pure correlation whether row 1 is x or row 2 is x, but that's not the question we have to solve. So let's go back to stat, and we'll do regression this time, simple linear, first time I'm going to select row 1, row 2 is the y variable, and I'm just going to click compute, and we get this information. There's our correlation coefficient minus 0.512, which is the same I'm pretty sure as we got before. Let me get some more room here, move this over, and now I'm going to do that again, stat regression, simple linear, this time row 2 is x, row 1 is y, click compute, and we get results again. I'm just going to close this up so you can see this shows when row 1 is the y, the correlation coefficient is minus 0.512, and when row 2 is the dependent variable y, we get the same correlation coefficient, so hope this helps.