The problems with Randomised Controlled Trials
ฝัง
- เผยแพร่เมื่อ 11 ก.พ. 2017
- Are randomised controlled trials better than others? In this video, Angus Deaton discusses the difficulties of applying the results to actual policies. This video was recorded at the American Economic Association in Chicago in January 2017.
Produced by EconFilms
![ใจเสาะบนเกาะนาคี - อ๊ะอาย สกุณาพร เสียงวิหค [Official MV] | ค่ายเพลงเป็นหนึ่ง](http://i.ytimg.com/vi/jbcmGQkfyOg/mqdefault.jpg)
Can't believe he summed up all that in 2 min... Very well articulated
this man has big brain
Awesome video and informative message! This is what I have been thinking about for the statue of educational research.
Estoy leyendo su artículo coescrito con N. Cartwright. Es un excelente texto.
Wow! I loved it when he mentioned my country Kenya❤
Nobody claims that randomised controlled trials guarantee that the groups are the same. The point is that they will be as similar as you can afford to increase N.
Have you read Leamer's "Tantalus on the Road to Asymptopia?"
That's also what seems to me.
Now, if N is too small, a randomized controlled trial is likely to suffer from the equalization problem, while some other methods which are not randomized are less prone to suffer from it.
I think, randomized controlled trials look like the ideal trials when N is large enough, but in practice, I wonder if it is more like a methods with pros and cons.
Thank you for your input. Now STFU.
I mean, duh? Is anyone seriously arguing the opposite of what this man's saying? There's ways to adjust for randomised groups being equalised. And you can use alternative methods like Propensity Score Matching if you're worried about equalisation.
It is well known what we want. But who can tell us how we can get it? In 1972 I have learned that unemployment is due to the fact that people do not search enough. He also got the Nobel prize ( Edmond Phelps). That is what Economics in the West has become or it was always like that. Amartya Sen wrote that in1943 in Bengal 5 million people died of starvation because those who were employed in the war effort have eaten too much. He also got the Nobel Prize.
wooo pop offf Harris!!!
Transform all negative impact and add positive impact = the result is success and control it.
Die m what does this guy have a degree?
Boiler up!
Sad that people without any idea of RCTs make such comments. High time that such presentations are deleted. Only knowledgeable people should make comments.
I will have to say that this video is wrong. The goal of RCT has never been to make sure that the control and target groups are "equalised", but rather to make sure that the treatment variable is not caused by any other confounder variable, and it is only the result of pure chance.
This is what common sense looks like. Critical thinking common sense. Funny, you don't have to be a doctor of anything to understand principles!!!!! Now we know one reason why they change course so often on treatments and why it often does not even work!!! Because TRUE SCIENCE IS EXACT AND SPECIFIC!