👋🏼 Hello There! In this video we answer these questions: what is the difference between sample and population in statistics? What is sample mean vs population mean and more with examples. If you like to support us, you can Donate (bit.ly/2CWxnP2), Share our Videos, Leave us a Comment and Give us a Like 👍🏼! Either way We Thank You!
At minute 3:00 I think that there is an error, to model binary events we use the Bernoulli distribution. The Binomial distribution is for the number of success in a serie of iid Bernoulli trials
I love you from somewhere that you do not know. I respect you from somewhere that you do not know. Because you show me your wisdom somewhere I do not know.
Pretty sure that the binomial distribution isn't the model that you should use at 3:30. The binomial distribution models the number of people x who have the disease given a population n and probability p. Your x seems to be a category of Yes or No.
Hi, I am following this intro statistics series and I am having just a small doubt , In this lecture you said (4:15) :- By X = Binomial(n,p) we will try to know how likely it is that 12% people of a randomly selected sample of 100 people will have disease given that our 10% population has disease. But how can we solve this using binomial(n,p), for example , : Lets we have population of 1000 with 1% i.e. 10 people having disease, now we sample 100 people randomly then probability of 50 people in sample having disease will be (100 choose 50) * (.01)^50 * (.99)^50 by binomial. But in reality its probability should be 0 as it is not possible as in total population, only 10 people have disease. Please tell me what concept I am missing.
Your example violates assumptions of the binomial. The first being that p is constant (ie) for each trial/persons selected, there is a p (1%) in your example of the person having the disease. In the example you created, p changes depending on each individual selected. It also violates the independent trials assumption...that each trial/person is independent of others. In your example, selecting a diseased individual reduces the probability of selecting diseased individuals in the future as there is no one less. These assumptions hold for a large population, eg 1 million people with 1% diseased. Your example had such a small population and a very large sample from there, that the independence assumption and hence constant p assumption are not met. But for a large population as I described, it will be met (or the change in p with each selection will be so small and negligible that you can assume p is constant
at the moment we dont have videos covering module 1 content. for my course, the module 1 material (and part of the module 2 material) are preceding material for the course, and we begin from the middle of module 2. in the future, we hope to build out videos for the module 1 and 2 material, but they are behind a few other topics in our queue
👋🏼 Hello There! In this video we answer these questions: what is the difference between sample and population in statistics? What is sample mean vs population mean and more with examples. If you like to support us, you can Donate (bit.ly/2CWxnP2), Share our Videos, Leave us a Comment and Give us a Like 👍🏼! Either way We Thank You!
At minute 3:00 I think that there is an error, to model binary events we use the Bernoulli distribution. The Binomial distribution is for the number of success in a serie of iid Bernoulli trials
Excellent explanation Sir!! I'm here from UOPeople and definitely glad that they chose you!
I love you from somewhere that you do not know. I respect you from somewhere that you do not know. Because you show me your wisdom somewhere I do not know.
Sir you made statistics very easy for me, very usefull course, Even in paid courses we cannot see such kind of explanation,
you are a life saver... love your classes
Pretty sure that the binomial distribution isn't the model that you should use at 3:30. The binomial distribution models the number of people x who have the disease given a population n and probability p. Your x seems to be a category of Yes or No.
Hello Marin. Thank you very much for your videos. You helped me a lot with this complicated subject. Regards,
clear cut explanation thanks
Amazing lecture... thanks a ton sir..it helped me a lot 😊😊
you're welcome, glad we could help :)
Are there videos of Module 1 and Module 2? Do share those.
The lesson is awesome.
Thank you
Thank you for sharing your knowledge.
You’re welcome, glad we could help :)
Why we are subtracting 1 from sd and not in mean
our little guy loves statistics T-T
How can you Use R to calculate the standard deviation of a log 2 base value?
If the values (let’s say in x) are already on log2 scale, then just use sd(x). If x is not, then use sd(log2(x))
Thanks sir ji
Hi, I am following this intro statistics series and I am having just a small doubt ,
In this lecture you said (4:15) :- By X = Binomial(n,p) we will try to know how likely it is that 12% people of a randomly selected sample of 100 people will have disease given that our 10% population has disease.
But how can we solve this using binomial(n,p), for example , : Lets we have population of 1000 with 1% i.e. 10 people having disease, now we sample 100 people randomly then probability of 50 people in sample having disease will be (100 choose 50) * (.01)^50 * (.99)^50 by binomial.
But in reality its probability should be 0 as it is not possible as in total population, only 10 people have disease.
Please tell me what concept I am missing.
Your example violates assumptions of the binomial. The first being that p is constant (ie) for each trial/persons selected, there is a p (1%) in your example of the person having the disease. In the example you created, p changes depending on each individual selected. It also violates the independent trials assumption...that each trial/person is independent of others. In your example, selecting a diseased individual reduces the probability of selecting diseased individuals in the future as there is no one less.
These assumptions hold for a large population, eg 1 million people with 1% diseased. Your example had such a small population and a very large sample from there, that the independence assumption and hence constant p assumption are not met. But for a large population as I described, it will be met (or the change in p with each selection will be so small and negligible that you can assume p is constant
@@marinstatlectures Everything is clear now, Thank you.
when you say "in module 1 we learned all about summarizing...", where are those module 1 videos?
at the moment we dont have videos covering module 1 content. for my course, the module 1 material (and part of the module 2 material) are preceding material for the course, and we begin from the middle of module 2. in the future, we hope to build out videos for the module 1 and 2 material, but they are behind a few other topics in our queue
Go back to the first couple of lesson to learn about plots
Great video! Thanks a ton. Out of curiosity are you writing backwards the whole time or is there a trick I am missing.
The video is flipped (mirrored)
OMG…. It seems a lot things said but in fact nothing