So far, what we've been doing is using marketing variables as independent variable to expense sales. But there are other things you can do with regression. For example, there are going to be times when you want to determine what variables are driving prices your marketplace. In this lesson, we're going to go through this scenario using a sports team as an example. By the end of this lesson, you should be able to describe how regression can help you determine how a set of independent variables are affecting a dependent variable like price. So imagine that you work for a sports team. An important question that you want to answer is, what are the variables that make ticket prices vary between teams within the league. Think about the NBA, the NFL, and so on. To address such questions, you can perform a regression where price would be the dependent variable and the other variables would be the independent variables. This chart shows data that you've collected from various sports teams. A is going to be the intercept, and then you have six other variables that you think are important that would drive price. One is going to be the number of wins by the team within the last five seasons, then you're going to add the average income level of the city. And you can assume here that, if the city is wealthy most likely the prices will be higher, because that's what the manager of this stadium can charge. The other thing would be team payroll, population size, and attendance as a percentage of capacity. If the attendance is very low, that means that people don't value the team, and therefore that would have an impact on the price. And last is whether the stadium is old or new. If you have a new stadium, you would have more fan engagement. They're more likely to come and check out the new stadium. So that might have an impact on the demand for tickets, and therefore tickets should be priced higher. So here I'm going to do the linear regression, where I'm going to measure A, B1, B2, B3, B4, B5, and B6, to measure the relative importance of each of these variables on price formation. Here is an example of a league in the US. And so what I find here is that some variables have a significant impact on price and some do not. For example, a new stadium has a P-value that is equal to 0.22, which means that having a new stadium does not have a significant impact on prices. On the other hand, the income level of city, the pearl of the team, or the number of wins do have significant impact on prices. Again I inferred this not only from the P-values, but also from the T-statistics that are above the 1.96 threshold. Now that we have analyzed continuous dependent variables, we are next looking at situations when the dependent variable is discrete like a buy or no buy decision.