numiqo

numiqo

296,000 subscribers

⏱ 👁 28,328 views

Principal Component Analysis (PCA) Explained Simply

Video Overview & Insights

Principal Component Analysis (PCA) is a method that reduces the number of variables in a dataset by creating new variables (“principal components”) that are combinations of the original ones and capture the most variation in the data—often making the data easier to visualize, compress, or model.

“

If you’d like, you can find our book Statistics Made Easy here: https://numiqo.com/statistics-book

— @numiqo

► Principal Component Analysis Calculator

https://numiqo.com/statistics-calculator/factor-analysis/principal-component-analysis-calculator?example=pca_wine

“

2:54 🤤

— @trollLolLol-x3w

► Example data

https://numiqo.com/statistics-calculator/factor-analysis/principal-component-analysis-calculator?example=pca_wine

“

😍

— @elenadagnelli7896

► PCA Interactive

https://numiqo.com/lab/pca

“

Amazing! Thank you so much

— @MurielZampieri

► E-BOOK

https://numiqo.com/statistics-book

“

I understood this so well, best video ever!!!

— @LusunguMusonda

More User Perspectives

@

very good explained, thanks a lot

@sarvarbek_rahmatjonov

@

This is a well detailed explanation, but It doesn't explain how the principal components are found, mathematically. I know that they axes with the most variance, but how do I actually calculate it? and where did the eigen vectors spawn from? why can't they just be normal vectors?

@shedrackjassen913

@

good lessons, thank you

@florencemalongane9752

@

Thanks God, finally i can easly understand

@yofriarmon9520

@

very warm and detailed at once

@rabahidaoud2914

@

Such a great explanation. I really struggled with PCA until now. Thanks!

@jamesthornton5611

@

Dearest Hannah,
Where have you been until now? I am elated to have discovered your channel. Thank you for a great video!

@ruthstephenz

@

Good miss hanna u made stats easy

@talhaansari8414

@

Best explanation!!!!!!!!!!

@zelalemmarkos8996

@

You always make complex topics easy. Thanks for taking the time to make this. Keep up the great work!

@sadhak5689

@

The best Video on YT regarding PCA so far!

@drachenschlachter6946

@

wonderful! Thank you

@garrett_h2o

@

This is the best explanation of PCA ever! (the interactive tool makes it so much easier to visualize)

@TheMuser

@

Very well explained.

@kabronell

@

thanks for your fantastic explanation

@sardargeo

@

Honestly that’s amazing how you broke it down step by step, I immediately bought your textbook, please dive deeper into machine learning that would be awesome

@MohamedHassan-vq2xk

@

I want to understand,if for example in PC1 one variable is positive and PC2 same variable is negative ,how to interpret that . Wether that will be positively impacting or negative.please also include the loading plot .

@AjayThakur-nk2ve