Being able to determine statistical significance is one of the most important skills in data science. If you observe a trend in your data, for example, is it statistically meaningful, or just some random noise in the data? Being able to construct a useful hypothesis and assess it via hypothesis testing is essential.
That’s why we’re excited to announce the latest addition to our R Data Analyst path: Hypothesis Testing in R.
Ready to start learning? Click the button below to dive into Hypothesis Testing in R, or scroll down to learn more about this new course.
What is Hypothesis Testing in R?
This course is designed to help you build a working understanding of critical statistics concepts like significance testing, and take you hands-on with A/B tests, chi-squared tests, and more.
Much like our Python Hypothesis Testing course, Hypothesis Testing in R asks you to write code and analyze real-world data (including data from the game show Jeopardy!) as you learn how to test hypotheses scientifically.
It starts with a focus on statistical significance, and you’ll learn about important concepts like p-values and representing distributions as you start to dig into the data with your coding skills. Then, the course moves into chi-squared tests, which enable us to scientifically quantify the difference between sets of observed and expected categorical values.
You’ll learn about multi-category chi-squared tests, and then dig into a new guided project that challenges you to apply the programming skills and statistics knowledge you’ve acquired to come up with a winning Jeopardy! strategy.
You’ll analyze questions from the long-running TV quiz show to find patterns. Then, you’ll apply your hypothesis testing skills and your new knowledge of chi-squared tests to determine which patterns are meaningful.
By the end of the course, you’ll have built a strong understanding of hypothesis testing, and you’ll have experience applying tests like significance and chi-squared tests in real-world data science scenarios.
Why Learn This?
Hypothesis testing is critically important for being able to tell the signal from the noise when you’re analyzing data. Determining whether a result is statistically significant helps you know when it’s safe to draw conclusions from the patterns you find.
Giving your analysis this level of statistical rigor is particularly important for anyone who plans to work in data analysis or data science. Companies aspire to be data-driven, and will look to their data teams for direction. If you don’t understand which of your results are genuinely significant, you could end up driving your company in the wrong direction.
Hypothesis testing provides a firm scientific and statistical grounding for data analysis. Without this grounding, it will often be impossible for you to assess whether you’ve actually uncovered a meaningful pattern in your data.
Start learning hypothesis testing today:
Charlie is a student of data science, and also a content marketer at Dataquest. In his free time, he’s learning to mountain bike and making videos about it.