yetanotherphd

Most of the objections here and in the article are not inherent problems with frequentist p-values.

First, the reported p-value might be wrong. E.g. basing it on assumptions of normality when the data is non-normal. However modern non-parametric approaches like the bootstrap can avoid this issue.

Second, testing multiple hypotheses. If you test 10 hypotheses then you cannot reject the null (that all 10 null hypotheses hold) simply because one single hypothesis is rejected in isolation. But this is well known, and failing to account for it is an issue with the researcher, not with frequentist statistics. I actually think that the main practical difference between Bayesian and Frequentist statistics is whether accounting for the issue of multiple hypotheses is done formally or informally.

All I see is the assertion that "money isn't real" interspersed with rambling anecdotes.

Great ideas, I look forward to them in your fork of HN.

I don't know if this man's views on sugar are accurate, but things like:

>''Reviews of the body of scientific evidence by expert committees have concluded that consuming sugar as part of a balanced diet does not induce lifestyle diseases such as diabetes and heart disease,'' he says.If you look up Robert Lustig on Wikipedia, nearly two-thirds of the studies cited there to repudiate Lustig's views were funded by Coca-Cola.

really disturb me. I think there is something wrong with are intellectual culture when we give completely undeserved credulity to studies with obvious biases.

I made the switch to OpenCombat, it's based on the same open source software, but without the spammy ads.

Programming used to be hard because of the hyper-optimization needed to get things to run.

Now programming is hard because of the giant scale of existing open source codebases.

It's not just the libraries, it's the toolchains, the build systems, the versioning tools, and that's just the things I've touched myself.

Someone once compared classical mathematics with modern mathematics, with the analogy of open pit mining vs deep shaft mining. I think programming has followed a similar trend. Modern programming involves strategically using existing tools, combining them without making major modifications to any of them. Of course, this is just for the individual programmer working on a discrete task. There is still room to participate in or lead large projects.

You assume that there is some relationship between churn, and total unemployment. I don't see how that would work.

If Uber were convinced that it was terribly immoral to fire someone, they would just put greater effort into making sure they got the best people in the first place.

So your policies favor a society with 5% of the people unemployed 100% of the time, instead of 100% of the people unemployed 5% of the time.

Job security is of questionable social good because it places a nonsensical emphasis on the harm of getting fired, as opposed to the harm of not getting hired in the first place.

It seems that Hawala might be used for import tax evasion:

>Most hawaladars take care of money transfers as a side part of their small business, so often hawaladars pay each other back in non-monetary ways. The most common case is by discounting goods in an export/import business. So in Ibrahim’s case, if the hawaladar he visits in Dubai exports goods to the hawaladar in Alexandria, the Dubai based lender can pay off his debt by discounting the value of his goods.

If the cost of the imported goods is discounted, then proportionally less import tax will be paid.

Is there anything that grasshoppers eat that isn't kosher? Maybe Watson is much smarter than we think.

The Google barge is displacing thousands of cubic meters of water, some of which has been in the bay for decades.

You are clearly taking one side of a debate, whether you admit it or not, cunt.

Porn is wonderful and liberating. Booth babes are degrading and misogynistic.

It really depends on your definition of sexism, which is an ambiguous term.

Suppose it were true that given a woman and man with the same resume, the woman tended to perform worse. It would them be rational to assume that, given two otherwise identical resumes, the one with the female name represented a worse candidate. To act on this information is statistical discrimination. I highly recommend you read the article.

Let me clarify the the alternate explanations for this study:

The researchers are aware that women on average perform worse than men, even given the same resume. As a general principal, this is not ridiculous, e.g. a female boxer will perform worse than a male boxer, even given the same height and weight. You personally might believe that a resume so perfectly captures the qualities of a person, that the person's gender is no longer relevant once you have seen the rest of the resume. But that is just your opinion.

So the professors are discriminating against women, but not for its own sake, but because they believe that statistically, even given the same resume, the woman would on average perform worse. See http://en.wikipedia.org/wiki/Statistical_discrimination_%28e...

This kind of discrimination does not actually make women on average worse off, in the sense that it only penalizes them for their actual inferior performance, not for being women per se.

On the legality, I don't know if it is legal or not. I'm guessing it is illegal but in my opinion those laws are wrong anyway.

Fun fact: the US government has the ability to tell you how much you should be paying in taxes, and to pre-fill your tax returns. However this has been prevented by lobbyists from the tax preparation industry

http://www.techdirt.com/articles/20100124/1836527884.shtml

I asserted that both explanations are possible, which is an obvious fact to me, until it is shown that one of the explanations is wrong.

I didn't notice I was replying to you, not aestra, who implicitly explained the results of the study in the way I described, when they used that study as evidence that "sexism is alive and well". Even though in this particular study, the authors (incorrectly) ignored my alternate explanation, it is in fact often discussed in this context (see http://en.wikipedia.org/wiki/Statistical_discrimination).

And I am sick of your side of the argument swearing at your opponents while constantly playing the victim card. Fuck you.

That is really gross, can you at least add some trigger warnings next time?

I'm giving an alternative explanation for why the female named resumes are rated worse by the professors.

I'm "pulling it from" the same place you pulled your preferred explanation (that female performance conditional on the same resume is the same, and so the worse ratings were due to professors preferring males, even given the same performance, or incorrectly expecting worse performance from the females).

The issue with your interpretation of the study is your selective appeal to evidence.

You would like to provide evidence for the fact that worse outcomes for females are due to discrimination. But the evidence you provided is consistent with both explanations (discrimination vs actually worse performance from females)

It's also possible that the scientists correctly infer that, even conditional on having the same resume, female applicants were overall of a lower quality.

The study doesn't prove whether this disadvantage comes from people discriminating against women merely because they are women, or people correctly identifying that the women on average perform worse, even given the same resumes. It is still possible that given full information about the candidate, (not just the resume), women would not be disadvantaged.

I don't think there is any conflict of interest. The police are only concerned with the criminals who stole the password. Whether the university owes the employees their pay because of the lax security they implemented, is almost certainly a civil matter.

Wild speculation that {women|older people|Black people} are inherently less inclined/capable in a field, is baseless discrimination. Wild speculation that {men|younger people|White people} are inherently less inclined/capable in a field, is stimulating discussion. Just a heads up for when the downvotes come.

I think the only comparison that makes sense is the benefit from the scan.

So if you are certain that the benefit of the scan is, no matter what the particular case, going to be worth much more than a 1/1000 chance of getting cancer, then that is a reason to ignore the risk.

That still makes no sense.

If I want to know whether to do a CT scan, the only relevant fact is the increase in probability (in an absolute sense) of cancer that it causes.

It seems like either you, or the entire field of medicine, is obfuscating this basic fact using some field-specific concepts.

EDIT: It seems like you are referring to relative risk (http://en.wikipedia.org/wiki/Relative_risk). But as I said, there is no reason that relative risk should be considered in this case.

>If you do the math by ICRP formulae, you end up with increase chance of cancer of 1 in 2600 over the next 20 years from a single 7ms CT scan today. This compares favorably with "natural" risk that is 1 in 10 without any extra exposure above background radiation.

But that is a meaningless comparison. The doctor should be comparing this additional risk, to the benefit of the scan.

The "natural" risk of developing cancer is totally irrelevant to the cost-benefit analysis.

In the actual video, the principal doesn't say there are no rules, but that they start off with no rules and create them collaboratively is the need arises. E.g. no high tackles in the game of bullrush

Those are separate matters: one is a matter of law, the other a matter of fact.

Suppose for example, that the police interviewed this man and he confirmed every part of her story. Then I think there would be sufficient evidence of rape.

On the other hand, if he gave a completely different story, maybe there would be insufficient evidence.

The problem with the ADA is their apparently wrong understanding of the law

being "cheaper" is not in itself an advantage. You personally might benefit from having a lower cost of living, for whatever reason, but your employer never sees this. All they see is the value you provide when you are at work. If two people offer the same value, they will offer the same wage, regardless of the cost of living of those individuals. Now the person with the higher cost of living might find this wage too low, and be forced to take a job with more hours/stress in order to achieve the income they require, or to adjust their lifestyle. But none of these things change what a company is willing to pay.

The rest of your post is premised in the idea that firing someone is inherently immoral. It is not something that should be taken lightly, since there are big adjustment costs for both sides, but as I said before, it only moves a person to their next-best option. The action of firing someone shouldn't be viewed as depriving them of a job for life* (which is made up for by a virtuous company providing them with a job for life). The same argument applies to many other cases. A school teacher cannot say "if it weren't for me, these children would have had no education, see how valuable I am" because if it weren't for that teacher, someone else would have done the job.

*Here life = the average time a person spends at a company and the argument remains the same.

Why did they have to smash up the fax machine too? That was just gratuitous.

Bear in mind Snowden has proven his commitment to rigorous honesty. Many people you might think of as decent might think these things, but not admit it, even to themselves.

I don't judge Snowden for saying these things, any more than I would judge a person who lives in a rich White/Jewish area and would never dream of living or going to a poor Muslim/South Asian area. That is to say, I don't judge him at all for saying these things.

>I've only sees "only abstinence is 100% effective" mocked from a policy perspective. It is true that abstinence is 100% effective on a personal level, but teaching it is remarkably ineffective at a population level.

The phrase "only abstinence is 100% effective" is a slogan for teens, not a claim that only abstinence only sex education is 100% effective (which is clearly false).

>There is room to mock it on a personal level, by pointing out that we are willing to engage in far more dangerous activities without 100% guarantees on safety. 'Seatbelts fail, only not driving is 100% effective'.

It depends on how much a person wants to avoid having an abortion or unplanned pregnancy, and how much value they get out of sex.