@@LiquidBrain Say a bioinformatician is concluding information from gene expression data. i imagine that there would be conclusions and inferences that they would like to draw but their statistical/mathematical knowledge maybe limited. so the challenges would include what type of stats/maths would they need to learn in order to apply their stat knowledge to the gene expression data. also how would one know where to begin learning stat/maths models to further improve their conclusions from being drawn from the data. for example at the end of the video you mentioned some discrete probability distributions that could be applied but you were still unsure on the full potential of what stat/math model could be applied.
For myself, don't think there's going to be one direction of stat to learn for bioinformatics since it involved way too many different type of research from here and there. Even until now, I keep on finding things I never heard before on a weekly basis on analysis of different projects. Might sound cringey, but perhaps the best thing to learn, is to learn how to learn and where to find the correct information that you can confidently rely on, and be comfortable about information that contradicts your current belief system. Statistics is also more of an art than a science with many unexplained justification and usages that relies on tradition rather than actual real world situation (e.g. p value
6:58 **Chi Square is a type of continous ditsturbution
Many thanks for your explanation. you explained a statistical topic in a romantic way lol amazing 👍
I am not sure but I was expecting much more than this.
To be honest, me too
Loved your video and the cats :)😊
great explaination, thank you!
This is a great video, thank you! Also, I think about the square hole video every time I do model selection. Thank you for including that reference!
Thank you!!!
Hi there, what challenges from gene expression data could discrete mathematics he applied to.
Hi, not sure what you mean by challenge. Do you mean why we don't apply a t test in the calculation of deg?
@@LiquidBrain Say a bioinformatician is concluding information from gene expression data. i imagine that there would be conclusions and inferences that they would like to draw but their statistical/mathematical knowledge maybe limited.
so the challenges would include what type of stats/maths would they need to learn in order to apply their stat knowledge to the gene expression data.
also how would one know where to begin learning stat/maths models to further improve their conclusions from being drawn from the data.
for example at the end of the video you mentioned some discrete probability distributions that could be applied but you were still unsure on the full potential of what stat/math model could be applied.
For myself, don't think there's going to be one direction of stat to learn for bioinformatics since it involved way too many different type of research from here and there. Even until now, I keep on finding things I never heard before on a weekly basis on analysis of different projects. Might sound cringey, but perhaps the best thing to learn, is to learn how to learn and where to find the correct information that you can confidently rely on, and be comfortable about information that contradicts your current belief system. Statistics is also more of an art than a science with many unexplained justification and usages that relies on tradition rather than actual real world situation (e.g. p value
Outstanding job!
good job 😇
This video made my day. Thank!
Oh man! This is amazing 😍😍😍
Awesome~
The content itself is good but children, animals and women on the video drive me crazy.
Why choose 0.5 as the log offset?
Usually we use 1 to make a zero zero again and avoid the negative infinity, here I do it because its looks nicer (it shift the curve to the left)