One of the most significant benefits of local regression is that it allows you to easily estimate a regularized derivative. It's practically the best method for differentiating any measurements.
@aabhagoyal91943 ай бұрын
thanks mam
@mhjlakkis80384 ай бұрын
Thank you so much for this content
@jihu-pf1ku4 ай бұрын
Awesome
@mikehynz4 ай бұрын
Very helpful, one of the best on bagging and random forests I have seen.
@thilinawee4 ай бұрын
Thank you for the simple explanation. I was stuck in a research paper with a causal graph diagram which did not include much information. This video saved my day <3
@nishah40584 ай бұрын
Hui superb lecture.. but I have one doubt I hope u will clear it. All of the videos related to lasso used regression model to explain it.. since it’s also a feature selection so can we use this as a feature selection for classification problem?? As PCA is used for both regression and classification. And moreover classifications means related to categorical data which by default convert into numerical values. So can we use lasso for classification problem also as a feature selection,if yes then why there is not any example of it? Thanx in advance
@paulhowrang5 ай бұрын
at 9:45 , when you divided data into two strata by education, are the graphs correct? when you select low education strata, plot Y(a=1) and Y(a=0) (treatment and no treatment), still you cannot observe contra factual, how come you have double line graph again in both cases Ya=1 and Ya=0? How are you observing both effects (doubly line graph) within both treatment and control group? Was that a hypothetical graph?
@aryaassadian66955 ай бұрын
This way truly informative! Thanks!
@aravindsreekumar32786 ай бұрын
Amazing explanation. Thank you
@concoursmaths82706 ай бұрын
great lesson!
@mojtabamohtasebi60826 ай бұрын
Great explanation 👌
@mojtabamohtasebi60826 ай бұрын
Perfect
@nachomacho70277 ай бұрын
You are a goddess Leslie... your voice... your intellect <3
@nachomacho70277 ай бұрын
Finally I get this stupid topic...
@nachomacho70277 ай бұрын
these videos are all extremely well done. clean recordings, good explanations, thanks for your efforts!!
@davidwang89717 ай бұрын
great explantion! the only thing I do not understand why it is called "natural" xxxx effect? thx!
@xuyizhen008 ай бұрын
great illustration of Verma and Pearl's inductive causation algorithm. Spirtes et al. was the first practical application of the algorithm. this video explains things better than reading a book for an hour.
@achmadsamjunanto64108 ай бұрын
is there any cutoff, of how much the associations are called strong or not? to qualitatively change results.
@teddybear58288 ай бұрын
thx for teaching well
@fabianaltendorfer118 ай бұрын
Very cool, thank you!
@Alkis058 ай бұрын
7:56 Hey, I recognize that. It's Sugeno fuzzy-logic! Makes sense, since we are talking about inference. I been wondering how one could mix graphs and fuzzy logic, but wasn't exactly looking for it. What a nice surprise.
@syedhasan7739 ай бұрын
Hello miss, great video, but just one thing. How do we assume that the potential outcomes are independent of the treatment? Isn't this a bit counterintuitive? If we want to measure the causal effects between the treatment and the outcome then why are we assuming them to be independent? Thanks again for the video.
@deepshahsvnit9 ай бұрын
Please share codes in desciption box
@fanwinwin10 ай бұрын
great
@cozzel399510 ай бұрын
Are you by any chance Burmese? I am just curious. Thank you for the video.
@FernandaPeres11 ай бұрын
Great video! Thank you very much!
@Zumerjud Жыл бұрын
Very easy to understand. Thank you!
@davidwang8971 Жыл бұрын
well-explained!
@davidwang8971 Жыл бұрын
This is the best expalnation for ignorability I have ever heard!
@alghanimaa Жыл бұрын
are there any code examples with this tutorial?
@alghanimaa Жыл бұрын
so you cannot have a collider in DAG? a collider is said her to be undirected...
@emmettfitzgerald3184 Жыл бұрын
Awesome explanation!
@haoli5727 Жыл бұрын
very well explained! good work!
@kan3259 Жыл бұрын
Why do we need the penalty term? can we not just have the RSS without it?
@kaylairish2224 Жыл бұрын
Thank you so much for such an amazing explanation!
@feifang1406 Жыл бұрын
The best explanation I heard for IPW estimator!
@valentinrack6028 Жыл бұрын
beutiful slides, and vey clear also. Thank u <3
@raquelmirman1508 Жыл бұрын
This was really helpful, thanks a lot!
@vulong9763 Жыл бұрын
greate video.
@johnt529 Жыл бұрын
Is there a way to calculate the y value of the QQ plot in your example (-96,900)?
@user-tz6zs5kh3v Жыл бұрын
what do you mean by average?? I've been trying and nothing
@baxoutthebox5682 Жыл бұрын
Thank you so much for sharing. So many stats profs are unlistenable. You, however, are great!
@workouts2114 Жыл бұрын
I love your videos well explained.
@wilsonjp23 Жыл бұрын
Soo good! Ty!
@harinathan5778 Жыл бұрын
In the voting example, let's say we didn't/couldn't find a variable like M to use. If we just proceeded by controlling for for P and E, couldn't we say that the resulting analysis gives the ACE for A "for people who use the website?" In other words, that it would only apply to this sub-population?
@lesliemyint1865 Жыл бұрын
Because S is inherently conditioned on (there's nothing we can do about this because that's just the data we have), our ACE estimate will indeed only apply to the subpopulation of people who use the website. But because of the collider stratification bias (conditioning on S) even this subpopulation ACE estimate will be biased. That is, even if our goal is just to estimate the causal effect of treatment for people who use the website, we will have bias in estimating this effect. (This is sometimes referred to as a lack of internal validity.) In order for the subpopulation ACE estimate to not be biased, we need to have some way of dealing with the A <- U1 -> S <- U2 -> Y noncausal path. (Perhaps we can find a proxy for one of the unmeasured variables.)
@nl7247 Жыл бұрын
If the potential outcomes are independent of treatment, then why given treatment to intervene? Thanks.
@lesliemyint1865 Жыл бұрын
Exchangeability is independence of each potential outcome (Y^a=1 and Y^a=0) and treatment but that doesn't mean that the causal effect is zero. This is because the causal effect is a contrast of the two potential outcomes whereas exchangeability makes a statement about the relationship between each potential outcome and treatment in turn. (The video's example is actually one in which exchangeability holds but there is a nonzero causal effect.)
@ernestsia7798 Жыл бұрын
Hi Leslie, I'm a medical student in Indonesia in the progress of conducting relatively "new" research about travel health, this video helps me a lot since the research contains many independent variables and has not yet found any control variables. I'm planning to use sensitivity analysis as a way to cover the weakness of this research. Thank you Leslie :)