From the course: Learning Data Analytics: 1 Foundations

Discovering skills of the data analyst

From the course: Learning Data Analytics: 1 Foundations

Discovering skills of the data analyst

“

- [Instructor] If a carpenter is starting a woodworking project, they don't just show up with a hammer. They have a set of tools at their disposal. Some tools, like a hammer and a nail gun, are similar in nature, but they might choose different tools based on the scenario that they're facing. A seasoned carpenter is not only leveraging tools but also leveraging their experiences over time. So the carpenter has learned not only what tool to use but what tool is best for the job at hand. When someone is new to a trade, like an apprentice, they haven't amassed a tool set of a seasoned professional and they don't have all of those experiences to leverage. So here we go. We've so far defined data analysis. We talked about how, in some ways, we're all analyzing data. We discussed the organizational roles and also some job roles. Let's dive into the skills of a data analyst. And keep in mind, you might be a seasoned professional or you may just be the apprentice. The skills required are not just software skills. They're also soft skills. The fundamentals for data are tools agnostic. That means these concepts can be applied to any tool that works with data. The first skill is understanding the basic question or even being able to create a basic question to answer the data. So here's an example of a basic question. Are we meeting our targets on getting orders shipped after we complete the sale? This would lead me to formulate another question. How many days does it take for us to complete an order and get it shipped and what is the target? Finding and gathering basic data to answer the questions is a skill for anyone who works with data at any level. So I ask, where is the data for the orders? Where is the data for shipping? How do I access this data? How much of it do I have? And how much do I need to answer the questions? Understanding the quality of the data is a critical skill. Anyone can make numbers show up. So understanding and communicating where you found the data and the quality of the data is critical. Is it keyed directly in by customer who makes an order? Does shipping complete their shipping through a system or are they telling someone who tracks it on a spreadsheet? It's important to identify the quality of the data and learn things about what impacts data quality. Another key skill is to determine what data is important to answering the specific question. All too often, you have access to more columns of data than what you need to answer a specific question. This is important because it helps define what cleaning and transformation you will need to do and exactly how much of it you will need to do. You'll also need to able to create valid data through calculations. In a perfect world, everything we need exists already, but we don't live in a perfect world. Hear me out and don't stop just because I said something that sounds like math. Here's an example. We have a date that something was ordered. We have a date in which it was shipped. But our dataset doesn't specifically state the number of days between. We can easily use those two dates to write a function that tells us the number of days from order to shipped. The scenario I presented here could be accomplished using any tools dedicated to data. I think a major skill for any data analysts, and one that's really lacking for most data analysts, is presenting the information in a clear and understandable format. This doesn't mean explaining orders and shipping data and the fact that it's stored in two different systems and that you had several menial steps and several really highly complicated steps. It means did you answer the question with a visual that is actionable and actually answers the question. As you grow more seasoned, you might learn more data tools where you will expand into deeper data skills and you might even pick up coding skills. However, if you cannot create or survive a pivot table, you should really start there. Datasets will continue to grow. And new datasets are always being created. So the skills you need will continue to grow and change over time. Just remember that not that long ago tools like Power BI and Tableau didn't exist yet, but building a core foundation on working with data will allow you to work successfully with any tool that is built for data. As we grow more innovative, data will continue to grow. And the supply and demand for people with data skills will continue to increase.

Contents