Great, this is the way Bayesian statistics should be taught...you have a previous belief about "something", then you get some extra "information" about that "something", so you update your knowledge about that "something" given that "information".... That is the intuition to start to understand bayesian inference.... Loved it great example!
Joshua Emmanuel - you are awesome!! Thank you so much for simplifying this concept. You have blessed me tremendously. I was going crosseyed trying to understand this principle when rearranged mathematically in a way that was more difficult for me to conceptualize. Thank you!
Amazing video. I've watched at least 5 others & didn't understand, but the way you used tables & explained everything both with words & visuals made it so easy to follow. Thanks for the help!
Thanks for the instructions on how to make a decision tree. Honestly, this really helped me in the final stage of my final project.. thankyou so much.. 😇😇
Hello Mr. Joshua. Can you kindly explain the value of information. That is the Market value, cost value and Economic value? This is related to the new infonomics trend.
Joshua,what if the question wrote the other way around.For example "when the consultant's report was positive 65%,the economic was growth".So the (Growth | Positive)= 0.65 and (Decline | Positive ) = 0.35.Am I right?please answer my question cause i am confuse with the question when they change the place of the word "given" which is consider as "when" in this question.
If we never had a consultant, so we have no historical data about their performance. How should we assign the probabilities of negative and positive report?
Hello Joshua... Thnx a lot... Its helpful... But l want to inquire about how to make a decision given data to calculate the posterior probabilities... How do u conclude from the posterior probs concerning a certain problem at hand...
You and a friend are playing toss the coin and the coin are tossed twice. Each of you get a turn to call heads or tails to indicate the manner the coin would land after it has been tossed. You are required to: a. Compute the probability that a head would result on the first toss. b.Compute the probability that a tail would result on the second toss given that the first toss resulted in a head. c. Compute the probability that two tails would result d. Compute the probability that a tail would result on the first toss and a head on the second toss. e. Compute the probability that a tail would result on the first toss and a head on the second toss or a head on the first and a tail on the second toss. Elaborate your answer f. Compute the probability that at least one head would occur on the two tosses. Elaborate your answer
The posterior probabilities normally should add up to 1. If they don't, then check your rounding or increase the number of decimal places you round to. I will suggest rounding intermediate results to 4 decimal places.
Great, this is the way Bayesian statistics should be taught...you have a previous belief about "something", then you get some extra "information" about that "something", so you update your knowledge about that "something" given that "information".... That is the intuition to start to understand bayesian inference.... Loved it great example!
Well said, Andres. 🙏
Best explanation of Bayesian Posteriors I've seen so far!
You are a brilliant explainer! Words can`t express how helpful your video is
🙏 Thannk you!
You have no idea how you just saved my life Joshua. Great help and simplified explanations. Thanks so much.
Omg!! You just save my whole semester in just a 3-minute video! thanks a lot!
Finally a Bayes Classification explanation I can actually understand. Thank you !
I just want to say thanks Joshua. Your material has been of great help. God Bless You
+Moses Sei
You're welcome Moses.
Joshua Emmanuel - you are awesome!! Thank you so much for simplifying this concept. You have blessed me tremendously. I was going crosseyed trying to understand this principle when rearranged mathematically in a way that was more difficult for me to conceptualize. Thank you!
Joshua, Thanks Man ! so much better than university's lectures !
Ohad S
You're welcome Ohad.
Waaay better...❤️Thankyou
I 100% agree!
Amazing video. I've watched at least 5 others & didn't understand, but the way you used tables & explained everything both with words & visuals made it so easy to follow. Thanks for the help!
You really have a gift for teaching! Thank you!
This is one of the best explanations of this topic I've seen. Awesome!
Wow, thankyou so much. I am 4th year engineer and this is going to help so much with my test tomorrow on Decision Theory
It is described as simple, short and nice way to understand the concept clearly. Material and presentations are too good. Thank you for sharing.....
Absolutely love your explanation and the table format was super helpful
Thank you so much!
thanks so much, man. you teach in a way that's so much easy to understand. appreciate it
Awesome! A very simplified presentation of a complex concept.
I subscribed immediately. That was clear!
Thank you so much Joshua Sir. Your explanation on posterior probability saved me.I was able to resolve my issue.
Glad it helped, Lopamudra.
Amazing tutorial! Concise and precise! Thanks for making this video!
Joshu,the man with brain 💥💥💥
Love you brother ❣️❣️❣️❣️
Thank you for your online video presented in clear way.
🙏
Thanks Joshua! You make this material easy to understand and really helpfull.
GBU
Thanks for the instructions on how to make a decision tree. Honestly, this really helped me in the final stage of my final project.. thankyou so much.. 😇😇
hey Joshua, thank you so much for this Video mate! due to this video i will be able to score high in my exam. more power to you!!!
Thank you for the excellent concise lecture. I am wondering how I should conclude or interpret the analysis?
Thank you so much for the video Joshua! My stats teacher is a complete bozzo so thanks for saving my grade
You explained in 4 minutes what hours of lectures couldn't
This was very well explained, thank you !
You explained in very simple manner
Fabulous 🎉🎉
This video was amazing!!! Thank you so much!
These are great videos. Thank you so much!!
Please do a Bayes Theorem Video! Love your content!
thank you so much!! it helps me lot for tomorrow exam!!
OMG 😍😍🙏🏾🙏🏾Thank you so much Joshua. Please, can you show us how we draw the decision tree after determining the posterior probabilities?
See if this helps:
th-cam.com/video/FUY07dvaUuE/w-d-xo.html
I watched this video but I am not able to apply it to my exercise. I have many qustions. can you help me?
Thank you!! You really made it easy to understand :)
Hello Mr. Joshua. Can you kindly explain the value of information. That is the Market value, cost value and Economic value? This is related to the new infonomics trend.
Wow thanks for this clear video!!
very good presentation, thank you so much :)
Excellent material big thanks
Great video and helpfull
Thank you so much, I could understand the concept!!!
Excellent. Can you please explain the interpretation of the posteriori to a decision.
posteriori refers to "later" or "after"
In essence, the additional information obtained after the decision is made.
lmfao i made the exact same mistake you mentioned by trying to do this before you explained it all hahah love this video
Love the stuff. Super helpful for reviewing for a big stats exam comin up!
Helpful one.
Joshua,what if the question wrote the other way around.For example "when the consultant's report was positive 65%,the economic was growth".So the (Growth | Positive)= 0.65 and (Decline | Positive ) = 0.35.Am I right?please answer my question cause i am confuse with the question when they change the place of the word "given" which is consider as "when" in this question.
Correct. You can replace "when" with "given".
If we never had a consultant, so we have no historical data about their performance. How should we assign the probabilities of negative and positive report?
Unfortunately, we cannot assign those probabilities unless provided. We will just stick with the prior probabilities in making the decision.
Joshua excellent videos, by any chance do you have a video about Decision Making under risk , sensitivity analysis ?
Sorry, I have nothing on Sensitivity in Decision Analysis.
Awesome question, have you found any answers since 1 year?
Simplified teaching.
Hello Joshua... Thnx a lot... Its helpful... But l want to inquire about how to make a decision given data to calculate the posterior probabilities... How do u conclude from the posterior probs concerning a certain problem at hand...
You and a friend are playing toss the coin and the coin are tossed twice. Each of you get a turn to call heads or tails to indicate the manner the coin would land after it has been tossed. You are required to:
a. Compute the probability that a head would result on the first toss.
b.Compute the probability that a tail would result on the second toss given that the first toss resulted in a head.
c. Compute the probability that two tails would result
d. Compute the probability that a tail would result on the first toss and a head on the second toss.
e. Compute the probability that a tail would result on the first toss and a head on the second toss or a head on the first and a tail on the second toss. Elaborate your answer
f. Compute the probability that at least one head would occur on the two tosses. Elaborate your answer
Khanyisani Mlaba
Check out the solutions here: th-cam.com/video/6HppFWelx64/w-d-xo.html
final exams twos day later... thank you for saving my life
thank you so much for this!!
Thank you!
Thanks again! you saved me
Thank you so much!!
I have a couple 2 examples about decision making with probability, could you please solve it for me, Thank you
thank you your the best
Hello @Joshua, Do you do coaching?
Sure. Please see About section of this channel for contact info.
Thank you so much
thanks a lot ....
Thank you!!
Is conditional probabilities should equal to 1 or it can more or less?
It can be more or less.
thanks man
tanks so much sır.
ı rlly apprecıate for dıs vıdeos
Is this the same as calculating Bayes Probability or am i missing something
Yes, it is the same...just in table format.
Is it necessary to get 1 or it's okay to get .99?
The posterior probabilities normally should add up to 1. If they don't, then check your rounding or increase the number of decimal places you round to. I will suggest rounding intermediate results to 4 decimal places.
Why don't the conditional probabilities add up to 1?
Conditional probabilities don't add up to 1 because they are not complementary.
Prior probability. Conditional
P(E1)=0.10. 0.4
P(E2)=0.70. 0.7
P(E3)=0.20. 0.5
How this will be calculated is not happening to me.
How many conditions do you have?
thank man
Why is this example so easy compared to my professor's exam questions. His questions can not be solved at all.
Can the marginal probability not equal to 1?
The sum of the marginal probabilities must equal 1.
how ca i get it
I lovvvvve youu
What is your email?
thank you!