Stratified Sampling In 3 Mins: Easy Explanation for Data Scientists

In this video, I’ll continue my series on sampling methods by talking about Stratified Sampling. I’ll introduce you to some of the major pros and cons of this technique using a simple, real-world example.
My other videos on Sampling Techniques ⤵️
Simple Random Sampling in 3 Mins: • Simple Random Sampling...
Systematic Sampling In 2 Mins: • Systematic Sampling In...
🟢Get all my free data science interview resources
www.emmading.com/resources
🟡 Product Case Interview Cheatsheet www.emmading.com/product-case...
🟠 Statistics Interview Cheatsheet www.emmading.com/statistics-i...
🟣 Behavioral Interview Cheatsheet www.emmading.com/behavioral-i...
🔵 Data Science Resume Checklist www.emmading.com/data-science...
✅ We work with Experienced Data Scientists to help them land their next dream jobs. Apply now: www.emmading.com/coaching
// Comment
Got any questions? Something to add?
Write a comment below to chat.
// Let's connect on LinkedIn:
/ emmading001
====================
Contents of this video:
====================
00:00 Introduction
00:18 Stratified Sampling
01:14 Pros of Stratified Sampling
01:54 Cons of Stratified Sampling
03:27 In The Next Video

Пікірлер: 3

  • @dvo66
    @dvo66 Жыл бұрын

    Hi Emma, I had an interview couple of weeks back and i got the role. They had one scenario based question about testing a fair coin which was just like one of your other video. However, now I got to know that the team I'll be joining also does data engineering tasks. So my question is if i take this role will it affect my profile for future changes as I dont want to get into data engineering? thanks

  • @KhalilMuhammad

    @KhalilMuhammad

    Жыл бұрын

    Emma's response is likely to be more reliable than mine, but permit me to share my 2 cents. It's rare to find Data Science roles, especially junior ones, that don't involve a little bit of Data Engineering --- even in research. The engineering aspect helps you ensure you're getting and transforming the right data for your DS task, but also that you're post-processing them in the manner that would help monitor/maintain the models. DS solutions don't work in a vacuum, so more often than not, a Data Scientist is required to wear multiple hats. If you're lucky to be in a large team, you can outsource/delegate some of those engineering tasks to a specialist. In general, in my humble opinion, it's usually a huge plus for your future prospects if you're adept at not just Data Science but also the engineering bits that support your ability to solve business problems with your DS skills. PS: Congratulations on the job offer! And thanks Emma for helping all of us :)

  • @robertwilsoniii2048
    @robertwilsoniii20487 ай бұрын

    Strata should always be based on uncorellated categories. Each strata should be orthogonol to each other.