Controlled Experiments: Crash Course Statistics #9
ฝัง
- เผยแพร่เมื่อ 4 ก.ค. 2024
- We may be living IN a simulation (according to Elon Musk and many others), but that doesn't mean we don't need to perform simulations ourselves. Today, we're going to talk about good experimental design and how we can create controlled experiments to minimize bias when collecting data. We'll also talk about single and double blind studies, randomized block design, and how placebos work.
Crash Course is on Patreon! You can support us directly by signing up at / crashcourse
Thanks to the following Patrons for their generous monthly contributions that help keep Crash Course free for everyone forever:
Mark Brouwer, Justin Zingsheim, Nickie Miskell Jr., Jessica Wode, Eric Prestemon, Kathrin Benoit, Tom Trval, Jason Saslow, Nathan Taylor, Divonne Holmes à Court, Brian Thomas Gossett, Khaled El Shalakany, Indika Siriwardena, Robert Kunz, SR Foxley, Sam Ferguson, Yasenia Cruz, Daniel Baulig, Eric Koslow, Caleb Weeks, Tim Curwick, Evren Türkmenoğlu, Alexander Tamas, D.A. Noe, Shawn Arnold, mark austin, Ruth Perez, Malcolm Callis, Ken Penttinen, Advait Shinde, Cody Carpenter, Annamaria Herrera, William McGraw, Bader AlGhamdi, Vaso, Melissa Briski, Joey Quek, Andrei Krishkevich, Rachel Bright, Alex S, Mayumi Maeda, Kathy & Tim Philip, Montather, Jirat, Eric Kitchen, Moritz Schmidt, Ian Dundore, Chris Peters,, Sandra Aft, Steve Marshall
--
Want to find Crash Course elsewhere on the internet?
Facebook - / youtubecrashcourse
Twitter - / thecrashcourse
Tumblr - / thecrashcourse
Support Crash Course on Patreon: / crashcourse
CC Kids: / crashcoursekids
![The moment we stopped understanding AI [AlexNet]](http://i.ytimg.com/vi/UZDiGooFs54/mqdefault.jpg)
This is by far the best Statistics course i've ever taken! Instructor is great, jokes are funny, and i love how the personality comes out! Great work here, team! Even though my background is in applied mathematics, statistics, and data science ... this course has been the best stats class i've taken!
You have made statistics really fun, especially because you pick up several examples from different fields thus some actual real life applications, that doesn't happen really in classrooms! Which actually should be the way to go about things.
Don't Forget To Be Asking Questions.
And proving these with experiments.
Don't Forget To Be Awesome Quavengena? I should have asked her out :(
is that actually what she means ?
Regularly watching this awesome series. Thank you creators.
I'm not an expert, but from what I know multiple studies don't want to use placebos because of ethical concerns. Instead, the control group is given the old, standard treatment while the experimental group received the experimental treatment. It would have probably been nice if ethical concerns like that would have been addressed in the video. Despite this point of criticism the video was still pretty well made.
Love this series
I love this, maybe an episode of how to run an experiment properly? Cheers
I'm not sure that's a "statistics" problem, though... and this is a series on statistics.
That plant is growing nicely ^_^
Amazing series
Wow, only 40k views? These episodes are great! Or maybe this is all an experiment to see which subjects people are most interested in!
Hi adrien love ur vids u helped me so much in school
Love you Adriene, please make more videos.
I want that T-shirt!
i love this series
we also need to consider sample size and ethics
👍 clearly mentioned
Ich feel you skipt the problem of sampel size. I need a large enough group of people in the experiment. If I take 30 people, splitt them into 3 random groups, chances are these groups are quite dissimilar. This alone might invalidate the experiment.
Why the heck am I paying 600 dollars for my university course again??? I learned more here in an hour than I did all semester at school
Anybody catch the typo “effcts” at 6:08 approximately?! I still love you crash course.
I have a question: when we compare two variables, and we do linear regression, we tend to see a line that can be described as y = mx+b
But I was wondering, do we ever see variables that are connected with an exponential correlation? The reason I ask is because so much of statistics seems to revolve around linear correlations of variables.
Stats is a subject that people generally ignore but it's very important
The Framework!!!!!
Hi Adrien
The cool thing about that shooter/game study is that Mario Kart is still competitive, so it's a pretty good placebo.
Placebo Effcts
Francis Guevara I caught that too, didn’t see your comment till I scrolled down 😆
Richard Wyant Same.
@@rickwyant
I caught that too, didn’t see your comment till I scrolled down 😆
Mrs. Hill, you look great... kindly make your team add more description to the video, so that revision could completed within 15 seconds.
Where do I sign up? I want to be in the control group
What about Triple blinded experiment?
Who are "train people"?
DFTBA-Q. It is taking off.
How do I make best use of this course?
I'll reverse that question next time you see a prescription you got from the doctor for Oxycontin ask yourself how was it tested on how many people could be addicted to this stuff and what's in the chemical makeup to make it so addictive more so than sugar? Stay curious
Hi
It is crazy thinking that our universe is just an experiment of another high being, and when our experiment answer their question, they will just destroy our universe and create another one for another experiment
TYPO ALERT! 6:12 Placebo Effcts? Did you mean Placebo Effects?
Please do a video about Prussia
What exactly is the thought bubble?
that thing with the animators
when it comes to clinical trials, if it ain't double blind, then never mind :-)
the ringing in the background of the definitions makes it hard to focus
EFFCTS - nooooooo a typoooooooooo
Double blind food study: Eat this brick of food (that I don't know what is), and let me take tests. Go fund me... or whatever.
the THOTBUBBLE is really helpful for understanding....
Maze Runner
That cappuccino experiment sounds like an ethical nightmare tbh.
Yup, jacking people's arousal as if it were innocuous is a lot like committing acts of violence in poorly insulated apartments. there are drawbacks to acepting exogenous neurotransmitter analogues - especially one, caffeine - that research has shown reduces g.
DFTBAQ should be a statistician thing now 😂
DFTBAQ I want that shirt
I don't think this video had a Crash Course Intro
Te
I bet she plays WoW
HI!!!!!!!
Someone give this woman a t-shirt
DFTBAQ !!!
Ready Player One anyone?
I watched a Grammarly ad before this video. They spelled Grammarly "grammerly" AND forgot the capital G in the subtitles. Every. Single. Time.
thats because youtube is auto generated Cc
Before 50 views
Don't use a font that uses an inverted W to represent the M.
To be clear: that's not what placebo effects are. Sham treatments don't cause anyone to feel better, though they may bias subjects toward *reporting* that they feel better. You correctly note that the cut may have healed without Neosporin. So if a cut heals with a placebo ointment, "placebo effect" is a catch-all category accounting for natural progression, regression to the mean, effect of treatment on reporting bias, etc.; but the placebo isn't actually responsible for any healing or pain reduction.
Creeper
Awww man
When you’re to gullible 🙌
The Philly sugar tax didn't encourage people to buy less, it encourage people to buy out of the city limits instead, that and it propped up a small black market.
Lmao
100th like here!!
This is the kind of thing I say to people who believe in magic and prayer... they rarely take it well.
Keep trying. They'll realize it eventually. :)
Nick Bostrom didn't make it onto your identity parade of simulation theorists? are you kidding me?
Climate change is dependent on the Grand solar Minimum coming and the current Magnetic weakening and Pole shift happening at the same time more than certain kinds of pollution IMHO. I mean what are the odds the environment will follow the same rules it followed the last great die offs? 100% or 100%?
Haha Elon Musk...
Nick Bostrom deserve credits,(Not Elon Musk)
Airborne (the cold remedy by a teacher) isn't homeopathic. It's a great big dose of vitamin c, and some misc other stuff, considered a supplement instead of a drug... An "alternative remedy". But homeopathic remedes are just placebos with nothing in them. (Unless you think water that never touched a poisonous substance will remember touching it, and use that to make you better, in which case your common cold is not your biggest problem.)
Calling things like airborne homeopathic muddies people's understanding. All homeopathic remedies are alternative remedies, not all alternatives are homeopathic.
"Elon Musk, along with actually intelligent people he read and the repeated from, argue that..."
lol, can we stop quoting people on things they didn't come up with and don't have an understanding of just because they happen to be be wealthy please? There's no reason to treat Musk as if he as a clue what he's talking about outside of perhaps specific parts of engineering.
More scattershot presentation. No discussion of validity or generalizability to frame the methods. This series is a mess.
BORING !!!!!!!!!!!!!
Please do a video about Prussia