What's up? Sat cats in this video, we are given some raw data and we are asked to perform a one way Unova. And if the another test is significant, we are asked to them perform either a chef or a turkey test. So we are given this raw data and this is, ah, weekly er visits between different hospitals. So in order to perform an Innova, I'm gonna be using the data analysis package on Excel, which is also what the book uses. So we're gonna do a nova single factor, and our input range is gonna be all of our data. And we do have labels in the first row, so make sure that's checked. We are doing this at a 0.5 alfa levels to make sure that coincides with what kind of tests your doing. And then our output ranges just where it's gonna summarize those results for us. So says the results of our one way and over test and what we really want to look at is our critical value and our test statistic. So we will have a significant result if our test value is larger than our critical value. So is 3.76 larger than 3.68 Yes, it ISS, so we can reject our null hypothesis. So to summarize our results, we would say there is enough evidence to conclude that there is at least one mean that is different from another mean. So because we have a significant unova TAAS, we can go ahead and perform a post talk test. And if you look, um, our sample sizes are equal, so we're going to be doing a two key test. And the test statistic for this test is found by taking the mean differences and dividing that by the square root of our mean square within groups multiplied. Fine. I'm sorry. Did. And then we're gonna divide that by end, and then our critical value is found with the end tables. Let's go back to our Excel spreadsheets so we can do some calculations. So let's do Let's do our pairs first. So we're gonna pair ex and why? Why? And Z and the and X So let's take the mean difference. So we're gonna take mean difference of X and why, why? And see and Z and facts, and then we're going to take the square root of our means square with end groups to buy by our sample size, which is all six. All right. And then we can calculate our test statistic by taking our numerator divided by our denominator. Okay, so these are our test statistics. I noticed that one of them's negative, but, um, an F value is always gonna be positive. So we can just ignore that and just consider it a positive value. So to find the critical value, we are going to go to our and table. So Kay is the number of means we have, which is three. So we have three categories. We have hospital X, Y, and Z and V is our total population. So the sample size all of our sample sizes together. So six times three. And we're going to subtract K from that. So we're gonna take 18 minus three, so it's gonna be 15. So que is three and V is 15. So 3.67 is our critical value. All right, let's go to our white board so we can write this down. All right, so, in orderto figure out if we have a significant para not We're going to see if our test statistic is larger than our cook about you. So it was 1.77 larger than 3.67 No. Is 2.10? No. Is 3.87? Yes. So we have one significant pair. It's between hospitals, uh, X and Z. So there is sufficient evidence to claim, uh, a mean difference exists between hair three and one. All right, that's it for this video. You guys, I hope you learned a lot. And also in its time.