 Chapter nine is t-tests, and in this chapter, we're going to talk about what's called the one sample t-test, the repeated measures t-test, and the two sample t-tests, along with a few versions of Cohen's D, a measure of effect size that's useful for t-tests. So that's the what. In terms of why we study this, it's actually nice because t-tests are one of the easiest ways of comparing groups. It's one of the easiest inferential tests there is. And by extension, it's also one of the most common. You'll see t-tests in a million research presentations and articles. In the psychological sciences, especially in experimental psychology, they're all over the place. And so this is a great tool to have when you're working with data. It also serves as the foundation for several of the following chapters. You can think of them as themes and variations. Analysis of variance is a nice extension of t-tests. You can think of regression and correlation as being a continuous version of t-tests. So it builds into a lot of other things. Now, in terms of what for, what would you use this for? Well, the fact is you do implicit versions of t-tests all the time. And looking, for instance, at people from Utah and you're comparing them to the U.S. population, you're taking one sample and comparing it to a population. So maybe you're looking at something like the cost of living or family size or political attitudes or international experience. Anything that you can measure quantitatively, you can put a number on, that's something you can do with a one-sample t-test. Or in the case of a two-sample t-test, if you're comparing two different groups of people, people do this a lot when they're comparing men and women or when they're comparing Democrats and Republicans or the comparing people who graduated from college with people who didn't. Again, you want to look at things like income, you want to look at well-being, you want to look at levels of social support, something you can put a quantitative number on, that's a great time to use a two-sample t-test. Or a repeated measures t-test is for anytime you're doing a before and after, you want to look at the effect of some kind of intervention. Like, for instance, you go to the gym every day, are you any stronger after a month? You get better lighting, natural lighting at work or maybe even a raise, are people happier? Are they more likely to show up for work after that intervention than before? These are all examples of things that you could measure explicitly, but you also do intuitive versions of them all the time. And so the t-test and its variations, the one-sample, two-sample and repeated measures, are great, simple tools for looking at whether differences between groups are a fluke, that's our null hypothesis, or something meaningful and worth looking into more closely. Take it from there and you will find that you do some version of the t-test all the time.