An Introduction to Discrete Random Variables and Discrete Probability Distributions
HTML-код
- Опубликовано: 3 июл 2014
- An introduction to discrete random variables and discrete probability distributions. A few examples of discrete and continuous random variables are discussed.
This is an updated and revised version of an earlier video. Those looking for my original Intro to Discrete Random Variables video can find it at: • Introduction to Discre...
Wow this was one of the most clear and concise math/stats videos I have ever watched. Thank you so much.
You are very welcome Daniel. Thanks for the compliment!
I'm sure I speak for everyone here when I say these videos are amazing. You make complex concepts easy to understand. THANK YOU!
You are very welcome. I'm glad to hear that you find my videos helpful, and thanks for the compliment!
I started studying about data science and came here whenever I had to revisit my concepts in statistics. One of the best and concise
This is probably the best introduction to statistics I have watched on RUclips. The concept is explained in a wonderfully simple and crisp manner, with great examples. The speed of delivering the concept was perfect and it is presented in such a clean and un-fussy manner! Thank you so much for your video series; it makes studying statistics so much easier!
You can tell how well this guy understands this subject by how well he explains it. Brilliant!
One of the best understandable videos about discrete probability distributions. Many thanks, I really appreciate it
***** You are very welcome!
It couldn't be better than this, crystal clear.
Thank you for the crystal clear explanation.
Your way of explaining is so perfect! Thank you so much
I took so many stat classes at some point even tutor others, but never come a cross some one who can clearly explain this counter intuitive subject. Indeed, knowing a subject and teaching others is too different things. Thank you sir for sharing your knowledge to the world. As some one who love to learn and teach others , I am very grateful to find your videos.
Watching this video is the best way to refresh my knowledge on this topic. Thank you!
Your videos are currently saving my life in stats class - THANK YOU
Thanks so much for all your videos. You've been a big help for me in my Prob and Stats class!
i think all professors teaching probability should watch your lectures..i magically understood all concepts..just amazing
it's so funny I had a lot of professors during my math studies and none of them taught me statistics as good as you did. thanks :)
Thank you for the great course. You have a talent of explaining.
You are very welcome!
Thank you so much. It made me more clear with what I learned in my statistics classes. I will go through your other videos. Many thanks.
My classmate showed me your channel. Thank you so much for the videos! Theyre so useful!
Your videos are the best. You have no idea how much help they have been.
I'm glad to be of help!
Really grateful for these videos, thank you!
I got a 95/100 on my last exam because of your explanations and I would like to say thank you for explaining all the concepts so well.
best video of statistics I have seen so far
YOU ARE AWESOME! SO GLAD I FOUND YOUR CHANNEL!
My whole respect sir,
it couldn't be more clear than that ....
thanks so much for this piece of art. pleas keep up...
Very helpful explanation, thank you.
You are a cool teacher. I hope I become as good as you someday. You are very clear in explaining. Thanks! I need this for my exam this Saturday. :D
thank you so much. This video really helps me a lot. I really hope my professor can be like you.
+Guoz Hee You are very welcome!
+jbstatistics love! love! love!
Best Of Luck Forever
For Sharing Such a Deep Knowledge in such a simple way.
Well Done Sir
You are seriously my savior, my knight in shining armor. The one true probability & statistics messiah. My professor has an extreme accent, and I can barely understand a word that comes out of his mouth. Your videos on discrete probability distributions are pretty much the only reason I aced my test on Friday. Truly, from the bottom of my heart, thank you.
You are very welcome! Thanks so much for the very kind words. I'm very glad I could be of help.
too sad only about 150K views, I think it deserves 1 million at least. thx for your explanation!
You're one of the best teachers I've come across in my entire life.
What an explanation. Killed it.
I mean I don't know how to thank you for making such amazing videos.
Thanks alot! Tomorrow is my exam..and I couldn't have understood this entire thing in one whole week which you made me understand in couple of hours. ❤️❤️
Thanks for the kind words! I hope your exam went very well!
You will go to heaven, for making this videos
thanks!!!!!
Great Explanation ❤
Hello sir my great vanakkam to you.. am from chennai Tamil Nadu.. Ur videos Everything am always watching .. u r such a great person .. am more impressed Ur teaching sir..
I am also from Tamil nadu bro ,seeing this comment after 3 years☺️
oh my goodness thank you SO much! you're a god send!
he is so good....thank you
Thank you so much for making this video!
You are very welcome!
Thank you so much for this video!!!!
dude. if i learned everything with this level of clarity...
perfect explaination !
Beautiful Explanation. Thankyou for this
You are very welcome!
Great video! Thank you.
thank you!!! the videos are amazing!!!
You are very welcome! Thanks for the very nice compliment!
Give a chair of statistics and probability at MIT to this man !
Thanks sir. You are great
thank's a lot for your effort's professor Jeremy Balka's
Thank you very much! Very clear and concise :D
+Amiel Dionisio You are very welcome Amiel!
+jbstatistics you've only replied to the people praising you saying that you're an excellent teacher. But it was very unclear for and many others where the 0.6 figure came from and you've ignored all of them.
+Matthew Oancea I often do take time to offer points of clarification on my videos, but I make no promises about answering every question that I'm asked. Writing a reply of "Thanks for the compliment!" takes perhaps 10 seconds, whereas replying to a request for clarification often takes some time.
In the example you are referring to, it's stated that "Approximately 60% of full-term newborn babies develop jaundice." I then state that the probability a randomly selected full-term newborn develops jaundice is 0.6. So the 0.6 is, essentially, given in the question.
Really very effective explanation awesome
Thanks for the kind words!
Thank you jb, very cool
actually u r excellent i'm from Egypt and i did not find any difficulities to understand this lesson ^_^
The best lecture videos
Thanks again!
Thank you so much
Dislikes for this video come from uni's professors
Excellent!!!!
Great video - thanks v much
You are very welcome!
best of the best !
Great set of videos. Thank you! Good karma coming your way (depending on the probability that it is real and you believe in it :))
thank you so much!
I have been checking out other online courses to brush up my statistics skills. So far I find your videos are the best because they are easy to understand and the content are also advanced enough to me. However, some times in your videos you mentioned something like "this will be discussed in another video", but it is not clear how to find that video, for example: showing binomial formula at 13:10. And in general, I would like to see your videos about how to constructs probability mass functions for all well-known distributions (i.e. normal, binomial, negative binomial, Poisson, etc.). I feel that they all can be build based on basic probability rules, but I haven't found reading or worked out myself. Two other very interesting aspects: How distributions are related and how one can argue that the data follows a particular distribution. Could you make some videos about these?
An update: I went to your website: www.jbstatistics.com/ . Relationship of video is well structured there. So I may be able to tackle the first problem (looking for related videos), but still very much interested in other things:
" I would like to see your videos about how to constructs probability mass functions for all well-known distributions (i.e. normal, binomial, negative binomial, Poisson, etc.). I feel that they all can be build based on basic probability rules, but I haven't found reading or worked out myself. Two other very interesting aspects: How distributions are related and how one can argue that the data follows a particular distribution."
you're so awesome!
Thanks!
Thanks!
It was very helpful. Thanks, man!!!! By HASAN
You are very welcome!
Thanks
Q on bivariate probability distribution
And on distribution of sums and quotient
Love this~
Thanks!
YOU are too good....
Thanks!
Super video
how did you get .4 when you multiplied .6
great work thnk you
+Fikri Saoudi You are very welcome!
thanks bro
Perfect 👌👌👌👌😍
Thank you sir
You are very welcome!
What enables you to multiply probabilities like that in the baby example? Is it because the events J and N are independent? Is it a consequence of conditional probability?
I state in the video "If we are sampling randomly and independently..." In other words, the events "the first baby has jaundice" and "the second baby has jaundice" are assumed to be independent. Whether that assumption is true would depend on the nature of the sampling.
can we convert set of data into uniform distribution
8:40 ,why are we having two 0.24s instead of one .anyone please explain
Tq so much sir😊
You are very welcome!
next time while writing the description plz mention the duration of the playlist of each...
Because the accuracy is governed by our measurement device, doesn't that make everything a discrete variable? e.g. if I'm measuring height, I may do so to the nearest cm or 0.5 cm, which then gives a countable finite number of possible values.
great intro, lets move on!
THANK YOUUUUUUUUUUU
You are very welcome!
THANK YOU! Many hours I spend wanting to biotch slap my teacher and yell "Get to the point! Keep it simple!" I've learned more here in 15 minutes than in hours of class. The only improvement I would suggests is some personality in your voice... kinda drone-ish.
how did you get .6
Isn't the plot at 10:55 a bar plot rather than a histogram?
9:45 "Dont worry, in MOST cases its not a MAJOR cause of confusion". Which means, usually, its at least a MINOR cause of confusion :p I definitely know it confuses me.
Can we say that each formula (such as the binomial, poisson etc...) is a Probability Mass Function?
Yes, the formula that yields the probabilities for a discrete probability distribution is called the probability mass function.
could you please explain how we got 0.6 for the probability of their occurring??
It was given in the problem. "Approximately 60% of full-term newborn babies develop jaundice" at 6:24.
how did he get 0.6 for the probability of JJ?
How did you get .4 when calculating the probability ?
The probability a randomly selected baby develops jaundice is 0.6 (as given in the problem statement). The probability a randomly selected baby does not develop jaundice is 1-0.6=0.4.
how was 0.6 obtained for the example of babies with jaundice?
Because 60% of newborn babies developed jaundice, 0.6 was given.
Martian: you are right. During the course of the explanation, the 60% was somehow forgotten - which shouldn't have happened. Thank you for the answer.
@@TheTomboy345 thank you, i know it was 3 years ago but i was just wondering this and paused to go in the comments section.
@@senpai1928 You're welcome. :)
Even though height in the real world is continuous, whenever we actually model it wouldn't it be discrete since we can't measure height to infinite decimal places? Is what you're saying that there's a point at which if you have enough discrete datapoints, you can treat it as continuous?
I'm saying height, in its nature, is continuous.
Absolutely anything that is truly continuous is subject to some sort of discretization based on the practical realities of the measuring device or method. Time, height, weight, etc. But yes, if we're not limiting ourself to a smallish number of possible values, it's usually reasonable to treat them as continuous. Sometimes how to treat a variable can be debatable, e.g. if we're taking medical measurements roughly each week, should we think of the # of weeks until occurrence of XXXX as discrete or continuous? Sometimes it's not obvious.
@@jbstatistics Thanks, that makes a lot of sense. Your videos have been very helpful during my stats course at waterloo :)
3:40 since this is infinite, this should be continuous right?
No, that's not the distinction between discrete and continuous. I included that intentionally, as an example of a discrete random variable that can take on an infinite number of possible values.
at. 13.37, is that a binomial distribution? If it is where does the 2 come from? Thanks!
Yes, that's a binomial distribution with n = 2 and p = 0.6. (I don't discuss that in this video, as this video comes before a discussion of the binomial.) I'm not sure what you mean by "where does the 2 come from?", as it's just a simple example I picked with n = 2 and p = 0.6.
@@jbstatistics Ok ok, I just thought that 0.6 comes from the fact that 60% of newborn babies developed jaundice whereas the number n should be the total number of the cases, right?
@@nm800 Whoops! Yes, that's definitely the case. I just took a quick look last time, and didn't notice that I had a motivating example. I should have known better, as I almost always use a motivating example :)
@@jbstatistics thank you very much. You're very kind. I like a lot your videos and I'm going to ask you a lot of things... sorry 😅
@@nm800 You're welcome to ask, but I won't always answer :) If people ask for a clarification about a video concept, then I usually try.
please i want a lesson about expectation of a random variable
It's next up in the playlist: ruclips.net/video/Vyk8HQOckIE/видео.html
How do we get a probability of 0.6 for the kid getting jaundice?
Hi, how did you deduce probability of 0.6 and 0.6 for both babies having jaundice? A little unclear there
"Approximately 60% of full-term newborn babies develop jaundice."
I don't understand where the probability of 0.6 came from?
+Aalok Kafle on the previous slide it gives a stat of 60% of newborns developing jaundice.
so that is used to calculate the probability but none of the probabilities actually equal 0.6
What programming language do you use?
The background is a Latex/Beamer presentation. I annotate using Skim and a Wacom Bamboo tablet. Screen capture and editing is done in Screenflow. Any statistical analysis or plots are done in R.
Can you suggest me some sources where I can learn these languages? I have enrolled to a course for R on Edx, where can I learn more?
I don't get how you got the probabilities e.g. the 0.6 and 0.4
It's given in the example. Approximately 60% of full-term newborns develop jaundice.
Might sound silly to a wizard like you but wanted to know why you list JN and NJ both as outcomes. Shouldn't they be the same thing. PLEASE HELP OUT SIR
That's a reasonable question, and we all sometimes get trapped or confused on whether we need to pay attention to order or not. First note that I do eventually pool those together, as they are both the event that X = 1. But in the *calculation of probabilities* it's important to note that they are not the same occurrence. X=0 (JJ) can happen in only one way: The first baby selected must have jaundice, and the second must have jaundice. X=2 (NN) can happen in only one way: The first baby selected must not have jaundice, and the second must not have jaundice. But X = 1 can happen in two ways: The fist has jaundice and the second doesn't, or the first doesn't and the second does. Each of these has the same probability of occurring, and when we group them together into the event that X = 1, we need to account for that.
If we look at the slightly simpler analog of flipping a balanced coin twice, if we ignored the ordering of the two possibilities that get us heads a single time (HT and TH), then we'd think we had 3 equally likely outcomes: Heads no times, 1 time, and 2 times. If these 3 were equally likely, then they'd all have a probability of 1/3. We know that can't possibly be the case, since the probability of getting heads both times must be 1/2*1/2 = 1/4. Our mistake would have been assuming that getting heads 0, 1, and 2 times were equally likely, when in reality getting HH, HT, TH, TT are the 4 equally likely outcomes.
Please can you translate to arabic
Because I have problem with English
Who were the down votes from? Flat earthers that can't math?