A coin is tossed 100 times independently. 50 heads are obtained. Let p denote P(H) It is given that p \in \{1/4, 3/4\} Then MLE of pis: (A) 1/4 (B) 1/2 (C) Does not exist (D) Both (A) and (B)
7:15 Can somebody please explain in layman terms how the probabilities of 1/2, 1/3 & 2/3 were reached for the heads flip (given 61 heads for 100 flips) even ratio of heads & tails is 60:40 which would be 3/2 NOT 2/3.
Suppose you have a weighted(biased) coin with a probability of heads 2/3 and tails 1/3. Now, If you flip it 3 times, it is still possible to get tails 2 out of 3 times, Right? Similarly if you flip a fair coin 3 times with probability of heads 1/2, you can still get 3 tails. Basically, There can be a difference between observed favourable events and calculated probability of favourable events, Which is whats happening here. Probabilities of 1/2, 1/3 and 2/3 are arbitrary and they are different from the observed counts of heads.
those who are tried and looking for MLE , Just watch believe me this is the best for MLE
One of the best mathematics teacher i have found on yt
Thank you soooo much ... You didn't know in which time this video help me ... God Bless you
Its my pleasure .... Happy learning.
You are a saviour
'this is in pounds' just saved him from half the human population lol
Thanks
real
This channel save my Career
Thank you sir for the amazing lecture.
very good and satisfactory explanation. Thank you
Thanks, u got my concept cleared 🙌
Great!... keep watching and sharing
Thank you so much sir for this amazing explanation 🙏
Thanku so much sir ❤️
Your content is amazing to clear concept
Explained it so nicely. Keep up the good work!
Thanks. Keep watching and sharing with others
Best explanation...
A coin is tossed 100 times independently. 50 heads are obtained. Let p denote P(H) It is given that p \in \{1/4, 3/4\} Then MLE of pis:
(A) 1/4
(B) 1/2
(C) Does not exist
(D) Both (A) and (B)
Both (A) & (B) will have same value. {100\choose50}({\frac{3}{16}})^{50}
Wow wow wow very nice explanation sir thank you so much 🤩
I am very thankful for your video
it explained so easy to understand and was perfect😍😍
Can u share the slide ? It will be helpful for us
Grateful for your efforts 🙏🙏🙏
Thnk u so much sir ..
Wow!!!
Thank you so much, sir, explained it in a very-very easy way
Quality Content ❤️
thanks dear..... Keep watching and sharing with others
truly amazing
amazing sir
Thank you so much 💝
just awesome
Sir may I get the pdf of this lecture?
THANK YOU
My pleasure... Keep sharing with other students too so that they will also learn with easiest manner... Happy learning...
Excellent
Many thanks
You helped me a lot sir!! Thank you sir
My pleasure always....
Thankuuu
Tx a lot
sir please explain those examples also in which we use order statistics
Yes, we will discuss surely in the next couple of videos on MLE
@@DrHarishGarg thanks sir
Nice I was student of thaper
9:50 why we haven't taken log in this example?
much better
Sir, can you give me example for biased MLE's
Sir plz make video on mean square error
Thanks .
My pleasure. ...keep sharing
Great love you Sir❤❤❤❤
Hi Dr. Harish can you just help me out in a research work
Is this concept from machine learning?
It is from Statistics but widely used in machine learning.
Sir i need cramer huzurbazar theorem sir
❤
7:15 Can somebody please explain in layman terms how the probabilities of 1/2, 1/3 & 2/3 were reached for the heads flip (given 61 heads for 100 flips) even ratio of heads & tails is 60:40 which would be 3/2 NOT 2/3.
Suppose you have a weighted(biased) coin with a probability of heads 2/3 and tails 1/3. Now, If you flip it 3 times, it is still possible to get tails 2 out of 3 times, Right? Similarly if you flip a fair coin 3 times with probability of heads 1/2, you can still get 3 tails. Basically, There can be a difference between observed favourable events and calculated probability of favourable events, Which is whats happening here. Probabilities of 1/2, 1/3 and 2/3 are arbitrary and they are different from the observed counts of heads.
@@parind-e-hind7311 Thanks a lot
At 7:16 i heard a voice like the wild fox 🦊 Anyone have noticed it ????
Can you write the likelihood function in the conditional form? As you have discussed in 5.45min..
Many thanks....
Join my telegram link of Probability and Statistics
t.me/gargProbability
❤❤☺☺
You are a saviour