Get startedGet started for free

Wrapping up

1. Wrapping up

Well done! You've reached the end of this course. We'll briefly review what you learned, I'll provide some tips from my experience, and then I'll link to some helpful resources as you continue on with your interview prep.

2. Chapter 1: Probability and sampling distributions

In chapter 1, we focused on baseline probability and statistics concepts that any and all data scientists should expect to be tested on in interviews. We talked about conditional probabilities including Bayes' theorem, touched on central limit theorem, and lastly outlined some more notable probability distributions that you should come to know and love.

3. Chapter 2: Exploratory data analysis

In chapter 2, we focused on some concepts that live on the more practical side of statistics for data science. We went over descriptive statistics, talked about visualizing categorical data, learned some encoding techniques, and talked about analyzing the relationship between two or more variables.

4. Chapter 3: Statistical experiments and significance testing

Chapter 3 was all about testing. This meant an overview of uncertainty estimates like confidence intervals, an intro to hypothesis testing, a look at power analysis, and finally, we talked about the multiple comparisons problem and how to address it.

5. Chapter 4: Regression and classification

In our last chapter, we looked at statistical modeling. We went over linear regression, logistic regression, talked about dealing with data irregularities, and finally, visualized the bias-variance tradeoff and what it means in practice.

6. Some advice

So we covered a lot of ground in this course, but there are a couple things that I wanted to share that I didn't really figure out until I interviewed a bunch of times. First, simulate the interview environment. It's easy to convince yourself you know something by practicing with your method of choice in a comfortable setting. Instead, try to mimic the interview as closely as possible. Similarly, practice explaining big concepts. If you know something really well, you can teach it. Start simple. Can you effectively explain confidence intervals, the central limit theorem, and logistic regression to a student? Keep practicing until you can. The next two points are more general than just statistics, but I found them helpful. Know the product well. Having a sense of familiarity with the company's offerings gives you a huge advantage for case study interviews, which can often blend with stats. Lastly, come prepared with ideas. While you're getting familiar with the product, write down any features or project ideas that you're interested in. Don't be afraid to share these during your interview.

7. Resources

I wouldn't be in this position teaching if it wasn't for tons of great data science interview prep available online. For easy access, I compiled all of the resources that I found in a github repo that you should check out. There were a few links that helped me especially and are worth outlining here. If you read through these couple of resources below on top of the material you covered in this course, I really think you'll be in good shape.

8. Good luck and thank you!

That's it! We really came a long way in this course - congrats again on seeing it through. It's really been a pleasure to be a part of your interview prep so thank you for sticking with me for this long. Lastly, good luck during your interviews! With preparation comes confidence, so keep working hard and good things will happen.