About: The Normal Distribution: Crash Course Statistics #19
I still don't get it.
I wish this had talked more about how often people mistakenly use the Normal Distribution in cases where the Central Limit Theorem does not apply. The definition does at least highlight that it only applies for an INDEPENDENT and RANDOM variable, but she doesn't touch on this. Even the strawberry example is questionable because the assumption that the weights of the packages as packed by a single distributor are INDEPENDENT of one another and RANDOM is fairly false and somewhat presupposes what the example is getting at -- i.e. whether that distributor had changed how much they fill the boxes. How much they pack is a choice of the distributor that will apply across packages, so the weights aren't really INDEPENDENT, and as the distributor gets to choose the target weight, the value isn't really RANDOM either (though one might reasonably expect the error from the target value to be). The analysis in the video seems to ask whether the weight is possibly arrived at by random perturbations, but that's arguably not the right question if one suspects foul play. The specifics aside, the importance of the values analyzed actually being INDEPENDENT and RANDOM deserves attention. (It may be this is addressed in a later video?)
Overall, the video makes the Normal Distribution sound a little too powerful and easy to lean on. Nate Silver at 538 talks about this a lot and how often this sort of mistake leads to dicey analysis and bad statistics. I highly recommend his book "The Signal and the Noise: Why So Many Predictions Fail--but Some Don't".
The understanding of viewers on this episode is not normally distributed.
We wish to estimate the cholesterol content in duck eggs. How
large a sample should be selected if we can assume that F=15
mg also holds for duck eggs, and we wish our estimate to be
correct within 5 mg with 99% confidence?
This video didn't even show the normal distribution lol
A free video online is way better at explaining stats than my MBA professor.
But why is CLT? why?
I like the Catan reference
how is the probability of rolling a mean of 2 3/36? 2,2 can be rolled 2 different ways, especially when you consider 1,3 and 3,1 two different rolls...
You really make Statistics so real.❤
Nimal😂 nalibog ko atong intro ani
I am following this series but everything she said went over my head...
Way too fast... I give up on that.
Yeah... You lost me in this video
i got headache of this ...how fast ..lots of informs ...as if i came here after getting the concept !! hello i'm not
i need a crash course for this crash course damnnn
this woman is so cringieeee
this becomes a better course when u play it at speed 0.75x
I’m so confused still