The fact that you described what the squiggly line was with the dot above and below @39:50 easily puts you ahead of th emajority of professors in my university. Most wouldn't even pause to clarify that.
I got confused pretty much from the beginning about willingness to take a bet where I gain $4if it rains and loose $1 if it doesn’t. I don’t see how my willingness to take that bet at those amounts translates into by subjective belief about the probability of the event itself (rain). The shift from size of bet to probably that the event leading to a payoff will occur seems confusing to me.
Are you familiar with the concept of expected value? The expected value is the amount of money you win in a bet multiplied by the probability of winning. For example if there was a 50% chance of winning $10 by playing a game the expected value of winning that game would be $5 ($10 multiplied by 1/2). If the expected value of winning is greater than the cost you'll on average make money over multiple bets. Assuming you would only accept a bet that at least doesn't lose money on average, if you're willing to bet either way that implies you believe both choices have the same expected value. It can be concluded that your perceived probability of winning is equal to the odds of the bet.
@@nahometesfay1112 Thanks, I think I see part of the problem. One issue is that calling the Bayesian perspective a "personal", depending on one's perspective and knowledge seems a bit inconsistent with the idea that someone will engage in accurate calculation of what is fair. Another confusing point is that it seems you are using the word "fair" to mean break even. But fair might not mean break even for everyone, so if I think it is fair to win $4 if it rains tomorrow (or lose $1 of it doesn't) does not mean I will think it is fair that I will loose $4 if it rains tomorrow (or win $1 if it doesn't).
Thank you so much for this! I'm a junior Data Scientist looking to develop my prowess in Applied Bayesian Statistics. This is a lifesaver!
The fact that you described what the squiggly line was with the dot above and below @39:50 easily puts you ahead of th emajority of professors in my university. Most wouldn't even pause to clarify that.
🤣🤣🤣🤣🤣🤣🤣🤣😘
Sincerely add the mixture model and hierarchical modeling part thank you
Will this course help me go do Bayesian analysis using R?
I got confused pretty much from the beginning about willingness to take a bet where I gain $4if it rains and loose $1 if it doesn’t. I don’t see how my willingness to take that bet at those amounts translates into by subjective belief about the probability of the event itself (rain). The shift from size of bet to probably that the event leading to a payoff will occur seems confusing to me.
Are you familiar with the concept of expected value? The expected value is the amount of money you win in a bet multiplied by the probability of winning. For example if there was a 50% chance of winning $10 by playing a game the expected value of winning that game would be $5 ($10 multiplied by 1/2). If the expected value of winning is greater than the cost you'll on average make money over multiple bets. Assuming you would only accept a bet that at least doesn't lose money on average, if you're willing to bet either way that implies you believe both choices have the same expected value. It can be concluded that your perceived probability of winning is equal to the odds of the bet.
@@nahometesfay1112 Thanks, I think I see part of the problem. One issue is that calling the Bayesian perspective a "personal", depending on one's perspective and knowledge seems a bit inconsistent with the idea that someone will engage in accurate calculation of what is fair. Another confusing point is that it seems you are using the word "fair" to mean break even. But fair might not mean break even for everyone, so if I think it is fair to win $4 if it rains tomorrow (or lose $1 of it doesn't) does not mean I will think it is fair that I will loose $4 if it rains tomorrow (or win $1 if it doesn't).