News for hackers. Stuff that matters.
Re:Statistical Mistakes and How to Avoid Them by lisper on Wednesday November 23, 2016 @09:16PM (#13027485)
That cartoon is actually a pretty good illustration of why frequentists are wrong.
Re:Statistical Mistakes and How to Avoid Them by qwrusz on Thursday November 24, 2016 @12:26AM (#13028377)
Do you mean probably wrong?

Either way I disagree. Both approaches have pros and cons depending on the type of analysis.

At the very least, just the presence of competing approaches in the field has pushed statisticians to have more rigour and do way more double checking than they might have, out of fear the other side actively looking to poke holes. It's easy to lie with statistics and the only people who can call statisticians out on their BS is other statisticians...Need more of this.

Re:Statistical Mistakes and How to Avoid Them by lisper on Thursday November 24, 2016 @12:58AM (#13028502)
> Do you mean probably wrong?

Nope.

> Both approaches have pros and cons

What are the pros of the frequentist approach?

Re:Statistical Mistakes and How to Avoid Them by rspeer on Thursday November 24, 2016 @02:57AM (#13028944)
You can justify that you did everything "by the book" and you don't have to make up priors.

Now. You might read this as me saying that Bayesian statistics is all made up, and that's not what I'm saying. I'm saying that if you go Bayesian all the way, and your result is even remotely controversial, someone could easily challenge you by saying "this result would have been different with different priors, and why won't they just come out and say p < 0.01? What are they hiding?"

When you do frequentist statistics, the equivalent of priors were, instead, made up for you by long scientific tradition. They're not very good priors, as the relevant xkcd illustrates. But at least it's not you making them up.

In a more complex model, there's also the thing where you can't calculate the result exactly, you have to approximate it with Markov Chain Monte Carlo or something, leading to another way to doubt your results (did the MCMC converge correctly?)

So instead you do frequentist statistics. You use your favorite stats package and it spits out a nice comforting p-value that will satisfy the reviewers. You have tons of guidance about how to do things. It's not a great thing, but it is a definite advantage of using frequentist statistics.

Re:Statistical Mistakes and How to Avoid Them by lisper on Thursday November 24, 2016 @05:07AM (#13029451)
In other words: the advantage of frequentism is that it gives you better plausible deniability when you get the wrong answer. Did I get that right?
Re:Statistical Mistakes and How to Avoid Them by rspeer on Thursday November 24, 2016 @11:09AM (#13030984)
No, and I don't know where you're getting your certainty that the answer is wrong from.

How about this: find me a published scientific paper with only Bayesian results in it, no frequentist statistics at all. Argue for its superiority all you want, but I don't think anyone does it. It would be seen as a stunt.

Re:Statistical Mistakes and How to Avoid Them by lisper on Thursday November 24, 2016 @04:57PM (#13033033)
Don't know about a paper, but here's a book:

https://www.amazon.com/Proving-History-Bayess-Theorem-Histor...

Re:Statistical Mistakes and How to Avoid Them by jcahill on Friday November 25, 2016 @07:17AM (#13036184)
> find me a published scientific paper with only Bayesian results in it

Trivial¹, surely?

> [B]ut I don't think anyone does it. It would be seen as a stunt.

What did you mean by "scientific"?

You'd have to hunt for a narrow reading s.t. the above holds — extant counterexamples aren't limited to any one branch.

Check it out² for yourself.

Further: cogsci's bayesian adoption is rapidly accelerating.

The replication crisis is brutalizing huge swathes of psych:

• loss of confidence in NHST is becoming near-total for many

• journals are purging in turn — e.g. BASP's p-value ban³⁴

• others are overhauling stats-in-psych entirely

J Math Psych alone has two recent special issues⁵⁶ on this.

I mean:

> no frequentist stats at all

isn't even a strawman lately, let alone an absurdity.

In some fields, it's a battle-cry.

All that being said… re:

> Argue for its superiority all you want

I wouldn't even go that far. Don't give em that.

Probability interpretation fundies

• are all wrong,

• narrow minds and waste lifespans with the cultism, and

• should at least learn of the other interpretations.

Pitching probability as a 1v1 isn't merely wrong-prime⁷ — it's doublepluswrong″⁸.

It's pseudofundamentalism: fundies uphold foundations.

Flamewars predicated on ignorance of the same gotta go, no matter how fashionable they may be.

____________________________________________________________

[1] http://enwp.org/bayesian_game

[2] http://google.com/scholar?q=fully+bayesian

[3] http://doi.org/4z8 | BASP 37

[4] http://doi.org/34p | Nature re: BASP

[5] http://doi.org/btqx | J Math Psych 72

[6] http://doi.org/btqz | J Math Psych 74

[7] http://enwp.org/all_models_are_wrong

[8] http://enwp.org/not_even_wrong

Re:Statistical Mistakes and How to Avoid Them by throw_away_777 on Thursday November 24, 2016 @08:12AM (#13030128)
The main advantage of the frequentist approach is that you can do the calculations much more easily. Bayesian statistics is great, but often the calculations are much more difficult because of your distribution of priors. You can make up simplified priors to ease the calculations, but then you run into some of the same problems as frequentist statistics.

Here is a simple example: lets say you flip a coin 10 times and get 8 heads, what is the probability that the coin is not fair? In frequentist statistics you only have to calculate the likelihood of the results for a null hypothesis, and then you use a p-value. While this approach is flawed, at least you can quickly do the calculation and get an approximate answer. In Bayesian statistics you have to specify the prior distribution, and calculate the likelihood of your results under every possible hypothesis. Correctly specifying this prior distribution and calculating the results is quite challenging - especially if you want to use a realistic prior (not just uniform). This is a pretty simple example, you can imagine how much more challenging this becomes in real-world problems. On the other hand, it is true that the frequentist approach doesn't really answer the question asked, so it is misleading (especially if you choose a p-value that isn't specific to the problem). If you choose p-values based on prior knowledge, than the differences between frequentist and bayesian are less extreme.

Re:Statistical Mistakes and How to Avoid Them by lisper on Thursday November 24, 2016 @09:42AM (#13030520)
A man was walking down a city street when he saw another man wandering around a lamp post looking at the sidewalk. "What are you doing?" the first man asked. "Looking for my keys," said the second man. "Oh, did you lose them around here?" asked the first man. "No," the second man replied, "but the light is better here."
Re:Statistical Mistakes and How to Avoid Them by throw_away_777 on Thursday November 24, 2016 @03:19PM (#13032515)
Often times getting close to an answer that is approximately correct is better than trying to find the perfect solution. Most real world problems, especially in analyzing data, don't have perfect answers. For example approximations are made all the time in physics, because without these approximations the calculations can't be done. Knowing when to make approximations and what approximations to make is an essential skill for analyzing data.
Re:Statistical Mistakes and How to Avoid Them by ska on Thursday November 24, 2016 @09:26AM (#13030443)
> Bayesian statistics is great, but often the calculations are much more difficult because of your distribution of priors.

This is often a feature, forcing you to actually look at the complexity head on before you sweep it under a rug.

Re:Statistical Mistakes and How to Avoid Them by danieltillett on Thursday November 24, 2016 @01:49AM (#13028685)
Simple maths that can be done without a computer. Useful in the past - not so useful today.
Re:Statistical Mistakes and How to Avoid Them by jcahill on Thursday November 24, 2016 @04:59AM (#13029417)
All models are wrong. That much is entailed by 'models'.

There is no Zuul.