Think Bayes - Bayesian Statistics Made Simple • Hacker News Board

Re: Think Bayes - Bayesian Statistics Made Simple

#41

Post by trhtrsh » Thu, Oct 11, 2012, 5:50 AM UTC

hessenwolf wrote: post #19

Bayesian is cool because you can make arbitrarily complex models, and when you have the parameters estimated it is really easy to calculate all the cool things you want to. Bayesian is not cool because estimating the parameters takes bloody ages on a supercomputer, unless you spend ages being really careful to specify your model. Frequentist statistics is cool because it is a massive big bag of tricks to estimate all…

Bayesian statistics gives you a subjective answer to your question. (conditioned on the prior you choose)

Frequestist statistics gives you an objective answer to a question that has the same words as the one you asked, but arranged differently.

Re: Think Bayes - Bayesian Statistics Made Simple

#42

Post by Datonomics » Thu, Oct 11, 2012, 6:20 AM UTC

danso wrote: post #25

ph0rcyas wrote: post #18

Earlier quoted context omitted.

Agree. It is unbelievable - one has to study it to believe it.

Going to Amazon right now... * edit: Doh, no Kindle version. I don't mind paying $90+ for a good book though, just like it to be electronic: http://www.amazon.com/Probability-Theory-The-Logic-Science/d...

http://www.naturalthinker.net/trl/texts/Science/Jaynes,%20E....

Re: Think Bayes - Bayesian Statistics Made Simple

#43

Post by hessenwolf » Thu, Oct 11, 2012, 9:11 AM UTC

pmjordan wrote: post #20

So this is all very well and good, I've had about 5 intros to Bayesian Statistics. But those are a fair bit away from actually applying that knowledge in practice in software. Let's say we have N different kinds of events with unknown probabilities and unknown dependence or independence between them. The naive approach to gathering data on the probability of event n occurring following an occurrence of event m would…

Sounds like you need a Bayesian network - the junction tree algorithm.

You can send the cheque in the mail. ;)

Re: Think Bayes - Bayesian Statistics Made Simple

#44

Post by AllenDowney » Thu, Oct 11, 2012, 12:36 PM UTC

markus2012 wrote: post #38

AllenDowney wrote: post #23

Earlier quoted context omitted.

I am coming around to the conclusion that this example is more trouble than it's worth. I think it's kind of fun, but it does seem to annoy people. This kind of feedback is exactly why I like to post drafts early. Expect this example to magically disappear very soon :)

Underneath Figure 4.2: I want to addresss on possible source should be I want to addresss one possible source (on -> one) Peace.

Fixed. Thanks!

Re: Think Bayes - Bayesian Statistics Made Simple

#45

Post by jcrubino » Sun, Oct 14, 2012, 12:41 PM UTC

I think you and Prof Scott Page could make a great team combining your think series with his model thinking class content.

Re: Think Bayes - Bayesian Statistics Made Simple

#46

Post by jcrubino » Sun, Oct 14, 2012, 12:42 PM UTC

jcrubino wrote: post #45

I think you and Prof Scott Page could make a great team combining your think series with his model thinking class content.

U Mich. Prof Scott E. Page http://masi.cscs.lsa.umich.edu/~spage/

Re: Think Bayes - Bayesian Statistics Made Simple

#47

Post by jeffjo » Sat, Oct 20, 2012, 1:57 AM UTC

nowarninglabel wrote: post #10

So, I'm going to counter here and say I don't find this to be a good intro. I started reading and had not heard of the "Girl named Florida" problem and then went to the linked to blog post http://allendowney.blogspot.com/2011/11/girl-named-florida-s... The way he explains it I found to be confusing and counter-intuitive. I've taken basic stats in college, and learned some of the associated problems, though not this o…

Yes, these sorts of problems can be confusing. But the confusion is propagated by educators who refuse to recognize that what they asked is not what they intended to ask, and so they provide inconsistent answers.

Say you are on a game show, and pick Door #1. The host opens door #3 to show that it does not have the prize, and offers to let you switch to door #2. Should you? Most people will initially reason that door #3 is prize-less 2/3 of the time, evenly split between cases where the prize is behind door #1 and door #2. So it would be pointless to switch. But that is wrong. Few educators will explain why by solving the problem rigorously. They will use an analogy like pointing out how the original choice is right only 1/3 of the time, and since the host can always open a prize-less door, that can’t change.

People don’t believe these educators because their 1/2 answer is indeed more rigorous than the analogy. It just makes a mistake. The probabilities to use are not the probabilities that the cases exist, but the probabilities that the observed result would occur. The existence probabilities are the same, but the probability of the observed result when the initial door was correct is half of what it is when the initial choice was incorrect.

Re: Think Bayes - Bayesian Statistics Made Simple

#48

Post by jeffjo » Sat, Oct 20, 2012, 2:01 AM UTC

nowarninglabel wrote: post #10

So, I'm going to counter here and say I don't find this to be a good intro. I started reading and had not heard of the "Girl named Florida" problem and then went to the linked to blog post http://allendowney.blogspot.com/2011/11/girl-named-florida-s... The way he explains it I found to be confusing and counter-intuitive. I've taken basic stats in college, and learned some of the associated problems, though not this o…

Oops, I only cut-and-pasted half of what I wanted. This comes after my other reply.

Yes, these sorts of problems can be confusing. But the confusion is propagated by educators who refuse to recognize that what they asked is not what they intended to ask, and so they provide inconsistent answers.

Say you are on a game show, and pick Door #1. The host opens door #3 to show that it does not have the prize, and offers to let you switch to door #2. Should you? Most people will initially reason that door #3 is prize-less 2/3 of the time, evenly split between cases where the prize is behind door #1 and door #2. So it would be pointless to switch. But that is wrong. Few educators will explain why by solving the problem rigorously. They will use an analogy like pointing out how the original choice is right only 1/3 of the time, and since the host can always open a prize-less door, that can’t change.

People don’t believe these educators because their 1/2 answer is indeed more rigorous than the analogy. It just makes a mistake. The probabilities to use are not the probabilities that the cases exist, but the probabilities that the observed result would occur. The existence probabilities are the same, but the probability of the observed result when the initial door was correct is half of what it is when the initial choice was incorrect.