5 Concepts in Statistics You Should Know | Data Science Interview

🚀 Land your dream data job using datainterview.com/.
====== ✅ Details ======
Dan, formerly a data scientist at Google and PayPal, reviews 5 fundamental topics candidates need to review in preparation for data science interviews. These are topics that are asked in business-case, statistics, and statistical-coding rounds. For more prep content, check out datainterview.com/
👍 Make sure to subscribe, like and share!
====== ⏱️ Timestamps ======
0:00 Intro
00:51 Central Tendency
05:05 Dispersion
06:17 Correlation
10:42 Normal Distribution
12:53 Hypothesis Testing
20:00 Other Concepts to Know
20:41 Conclusion
====== 📚 Other Useful Contents ======
1. Principles and Frameworks of Product Metrics | KZbin Case Study
Link: / principles-and-framewo...
2. How to Crack the Data Scientist Case Interview
Link: / crack-the-data-scienti...
3. How to Crack the Amazon Data Scientist Interview
Link: / crack-the-amazon-data-...
====== Connect ======
📗 LinkedIn - / danleedata
📘 Medium - / datainterview

[@abdallahelmoctar7635]

Such a simple and straight forward refresher. I'm grateful for your work

[@WebsterLincoln]

I would describe that as a positively skewed normal distribution, not an exponential distribution. Also, it's the 68-95-99.7 rule

[@mahmutozmen1261]

Thanks for such a great content and your effort. Would you mind explaining further why you think that mode = median? Since this graph seems like a positively skewed graph, I though mode is around 3, median 4 or 5 and mean between 6 and 10.

[@AllieZhao]

These are crucial concepts. Thanks

[@shir0tei]

Thanks for the video! I The correlation formula is wrong though, the covariance is the numerator divided by n.

[@basmaelkhamlichi8223]

Hypothesis testing and P value nicely explained, thank you!

[@DataInterview]

Thank you!

[@SaramaKamal]

Could you mention tools used to design and present your slides thanks!!!

[@jcokonkwo]

I definitely appreciate the explanation then the applied DS examples right after. Thank you!

[@DataInterview]

That's the best way to learn :)

[@HarryPotter-st2cn]

Great content. Is non-normal distributions listed separately to put emphasis on it? I believe it will be included within the concept of the overall distributions

[@jacksun7999]

6:43 should the numerator be cov(X,Y)? Seems there is a 1/(N-1) term missing.

[@anirbansarkar6306]

Can you help me understand on what basis have you assumed population standard deviation to be 20?

[@dreamingaparisdream3178]

Also where is the link for Meta Statistical Interview questions video please?

[@benxneo]

could you give me ideas for data science projects that deliver value to businesses

[@Foba_Bett]

I am binge-watching your channel ! 😎 In the correlation section - why not just straight up remove the outliers? 🤔

[@gaboqv]

that's what he is telling with a fancy name, you will use quartiles to confirm which of the points are outliers

[@RedShipsofSpainAgain]

11:16. I think you have a typo: The Normal distribution should be 68-95-99.7%, not 65-95-99.7%

[@bandai2]

could you also use Spearman Correlation if you have outliers in your data?

[@eresque7766]

late but yeah u could

[@pal999]

If you're using a real world example, you shouldn't "ASSUME" the SD to be something. Can you find out how it's determined in real world?

[@dreamingaparisdream3178]

For the normal distribution, is it 66-95-99.7 rule or 68-95-99.7?

[@TheNIK21HIL]

it is 68% within 1 SD. it must be a typo on Dan's end. The graph though does represent it correctly.

[@ASHISHDHIMAN1610]

@@TheNIK21HIL yeah typo

[@stanislavdidenko8436]

2pm - poisson distribution

[@BrianSalamone]

1:08 8 hours a day in Facebook????? What is the X at the bottom?

[@michaell9804]

You failed to mention bayes theorem and binomial distribution which is used here just as heavily as normal distribution particularly when quantifying the probability distribution of the accuracy of unsupervised learning models. This video is not comprehensive at all

[@Omegageekk]

If you thought a video titled “5 concepts in statistics you should know” would be a comprehensive breakdown of literally every stats concept you need for data science, then I have a bridge to sell you.