5 Essential Technical Skills for Data Analyst
Want to learn data analyst skills but don't know where to start? I'll share a road map you can follow; no prior knowledge is required. As I mentioned in my previous post, Top 3 non-technical skills for effective data analyst, there is no end to learning in this field, so relish the learning process.
The 5 essential skills to learn are:
Data analyst jobs can vary quite a bit from job to job. You don't have to have all five skills to land a career as a data analyst; I know this firsthand. However, Excel and math are essential.
Many of us have heard this before; an effective way to learn any new skill is through doing. So, the approach I suggest taking when learning any new skill is to gain basic knowledge on each of these topics. Don't go too deep too quickly. If you do, it can overwhelm you and lead to procrastination, take this advice as coming from someone who has been there and done that.
Once you have the basic knowledge, start working on a project. Working on projects is a great way to test your knowledge and understanding and gain new knowledge because the chances are there will be things you won't know and will have to research to solve the challenges encountered.
1. Excel
Microsoft Excel is one of the most popular business intelligence tools used globally. It's been around since 1985. It's useful and effective for basic tracking, calculations, and analysis. It's excellent for small datasets but struggles with large datasets. That said, it still has its place even in this age of big data and won't be going away anytime soon.
Here are some foundational things you should learn to do in Excel:
• How to gather and organise data
• How to create formulas
• How to use relative and absolute references
• How to create charts
• How to create Pivot Table
• How to use Power Query (aka Get & Transform)
A side note on Power Query. It's not foundational, but it's worth learning early in your journey. It's a powerful automation tool and will save you a lot of your precious time wrangling and transforming data into a usable format for analysis.
Resources
► Excel Introduction- Learn Excel Basics Playlist by Leila Gharani
► Excel Charts Playlist by Leila Gharani
► Excel Pivot Tables Explained in 10 Minutes by Leila Gharani (13:21)
► Excel Pivot Tables Made Easy- And Why Things go Wrong by MyOnlineTrainingHub (13:17)
► Excel Power Query by Leila Gharani (9:01)
2. Math
In-depth knowledge of math isn't required for data analysts. You can succeed in this role with just high school math. The topics that you need to be familiar with (by that, I mean a good sense of the theory) are basic statistics, probability, and algebra. Some people say calculus is a required topic, but I beg to differ. It's essential if your goal is to become a data scientist.
If it's been a while since you last went through these topics, it's a good idea to refresh your knowledge. From time to time, I revisit these, especially statistics and probability! Statistics and probability was my least favourite math topic. It was never taught to me in a way that makes intuitive sense nor in a practical way. In my first year in uni, I barely passed statistics 101- there was a lot of guessing!
Resources
► Khan Academy-Statistics & Probability by Khan Academy
► Khan Academy-Algebra Basics by Khan Academy
► Brandon Faltz Stat 101 by Brandon Faltz.
His website has links to all his stat videos, from beginners to advance.
However, focus on these:
► Population and Sample Data (26:46)
► Descriptive Statistics I Playlist
► Descriptive Statistics II Playlist
► Introduction to Probability
3. Visualisation
Data visualisation (viz) is essential when analysing data. It makes it easy for humans to consume a large amount of data and see patterns otherwise missed if looking at data. Many visualisation tools are available on the market, such as Tableau, Power BI, Qlik Sense, Sisense etc. Tableau and Power BI is the most popular. I would recommend you choose one of the two to learn. Don't learn both simultaneously. Once you know one well, others become pretty easy to pick up. I've personally chosen to invest my energy into Tableau. Both Power BI and Tableau are excellent tools in the visualization space. Tableau won me over because of its comprehensive support and community.
Resources
► Free Tableau Training Videos by Tableau
► Tableau eLearning by Tableau. Tableau curates a learning journey based on role. It's great for those not sure where to start. It's not free, but it's very affordable- USD 10/ month.
4. SQL
SQL, pronounced Sequel, stands for Structured Query Language. It is a programming language that enables you to communicate with databases to manage all its data. It was first developed in the early 1970s by two IBM researchers, Raymond Boyce and Donald Chamberlin.
Depending on your company, you may not need to learn this immediately, but it's an invaluable skill. I only started applying SQL in my role not long ago. Access to the company's database was not available to me until recently.
Resources
► SQL by W3School
► MySQL for Data Analytics and Business Intelligence by Udemy. This course costs AUD 69.99, and you get lifetime access to the content. Udemy offers specials frequently, so wait for the special if you don't want to pay full price.
► SQL Fundamentals by DataCamp. It's a subscription-based platform with various courses taught by industry experts. The free account has limited access to the courses. Check out their pricing schedule if you're interested in signing up.
5. Python
I've read that Python is one of the most straightforward programming languages to learn. It's versatile, and it's in high demand. You don't need it to do data analytics, but you should learn it if you want to become a data scientist.
With Python, you can prepare data for analysis, perform statistical analysis, create meaningful data visualisations, predict future trends from data, and do more, such as web scraping. I have embarked on learning the basics of Python.
Resources
► Python by W3School
► Intro to Python for Data Science by DataCamp
► Python Basics: A Practical Introduction to Python 3 by David Amos & Dan Bader
I hope this blog has given you clarity on where to start your journey. To move the needle closer toward your goal, remember to take action daily. Set aside one hour each day to learn. Reflect on your accomplishment at the end of each week; you'll get a good dose of dopamine hit to continue. Happy learning!