Once you have the logic of your story laid out. It's time to rip it apart, find any mistakes you've made, and make it better. Your goal during these steps will be to identify all the different holes in the logic of your argument, or the assumptions you made about the context and motivation you were using to frame that argument. So that the data story was perfectly polished by the time you present it to the people who will ultimately determine the fate of your recommendation. In business contexts, this is a step you should do with your team. Here's Lindsay Penningale, data scientist from Airbnb, talking about how she asks for feedback from her team when she has a data story. I'm a data scientist on a team of engineers, and a PM. I always just like to send out my team like, hey guys, took a look at this and here's what I'm thinking. And there are people on on the team who know our product better than I do, who can say, you know what? Like, sanity check. That's crazy. And that's immensely helpful. I could have someone else who says, oh, that's great. Could you also look at this? I might have a certain set of skills, but someone else may have a separate set of skills that is immensely valuable to the way I approach a question. >> I suggest that you try to get feedback about your storyboard from everyone you can. Try to get feedback from other people in your data analytics team. But also from your stakeholders. So that they can tell if your assumptions are way off base or your recommendations aren't relevant. You might be nervous to do this at first. But data analysis teams work together. And everyone can improve and everybody can make mistakes. When groups work together, the outcomes are almost always better than when one person works alone. Let's hear what Elena Graywall, a manager on the data science team from AirBnb, has to say about getting feedback, and making mistakes. >> So, there are so many times we have gotten things wrong, so I have many examples of that. And Scott said, I think a really important culture to have on any team, is the culture of bringing forward any errors and that being celebrated. That we understand that everyone will make mistakes. And the most important thing is actually to say when you have realized that you've made a mistake. So that we can correct it. So I think the biggest problems that companies will have, is when someone's made a mistake and they're either too afraid or worried to bring it forward. And so, that's definitely a huge part of our culture. >> Obviously every analysis situation will be different. The next set of videos will go over some common logical fallacies that get people into trouble. Make sure to look out for them in your own data stories, and when you're trying to help somebody else with their data story. Cuz after watching the next set of videos, you are hungry for more resources to help you really good of identifying inconsistencies and logical arguments. I recommend that you consider buying a book or taking A class in logic and reasoning. They're even some great classes about logic and reasoning here in Corsera. Learning about logic in general will be very helpful for learning how to structure and interpret your data analysis. We'll also make you more confident in your ability to construct bullet proof arguments, and identify when and how an argument is weak. if you can find the time to take a course or read a text book about making logical arguments, I'm confident that you won't regret it. In the mean time, the next few videos will get you started learning how to identify the most common logical fallacies found in data analytics.