@@nhamiltondwight I did some digging. It has something to do with the distribution of your data set. That is, by definition, 0.5IQR is 50% of your data. Comparing against a normally distributted data set that is slightly less than 1STD (68%). Thus, if you use 1IQR (~2STD) you would include "too many" outliers. If you use 2IQR (~4STD) you would exclude too many "possible" outliers. Thus, 1.5 is somewhat the goldilock zone and it is closest to ~3STD or 99% confidence levels for a normally distributed data set.
3 years after posting, this video is so useful! I wish my teachers taught like you.
Glad you found it helpful! Thank you. :)
Finally a simple Tutorial that isn’t 10+ minutes long
Glad I could help! :)
Super simple explanation, thank you!
Glad it was helpful! You're welcome!
that was super helpful to understand the concept of the IQR, thanks!
Glad it was helpful! You're welcome!
Succinct and easy to understand!
Thanks! Glad you found it easy to understand.
This was helpful for my test!
How do you do this when there is an uneven number of data points in Q1 and Q3?
Great job!! Question about acceptable range - could the 6.5 be -6.5? Of course it depends on the data, would that be permissible? Thank you!
Hi! Awesome question! Yes... for example, if you're looking at something like temperature, then values may be negative.
"Brevity is the soul of wit" Congrats
:) Thank you!
Thank you so much 🥺♥️,it really helped me a lot😅
You're welcome!! So glad to be able to help. :-D
Well Explained.
Glad it was helpful!
I was looking forward to using this but your formulas aren't the same as mine for some reason. Both of mine are subtraction. Sad
Thank you so much hey❤.
You're welcome 😊
Thanks
You're welcome! :)
How do you do this when you have two median numbers
Thank you ma'am.... 😊😊😊
You're welcome! 😊
Q1 is 9.25 isn't it?
Hi... Q1 is 9.5 (the average of 9 and 10).
erm....might be good to fix the subtitles for this lol
where does the 1.5 comes from?
@@nhamiltondwight I did some digging. It has something to do with the distribution of your data set. That is, by definition, 0.5IQR is 50% of your data. Comparing against a normally distributted data set that is slightly less than 1STD (68%). Thus, if you use 1IQR (~2STD) you would include "too many" outliers. If you use 2IQR (~4STD) you would exclude too many "possible" outliers. Thus, 1.5 is somewhat the goldilock zone and it is closest to ~3STD or 99% confidence levels for a normally distributed data set.
HOW DID YOU RESEARCH ALL OF THAT!!!