## Archive for the ‘Rants’ Category

### Oh no...

Thursday, February 17th, 2011

Is blogs really science journalism? Maybe not, but the science news I get, I mainly get from great blogs, so even if it isn't "proper" science journalism, I think I can say that it is where at least some scientists get their news.

So it is a bit strange when a press officer doesn't want to talk to bloggers.

I know that I would absolutely love to have my research mentioned by Ed Young -- I've been reading his Not Exactly Rocket Science for years -- so if a press officer at AU didn't give him all the information he wanted, I'd be rather miffed.

### P-values again again

Friday, February 4th, 2011

For no apparent good reason, I read an old post on p-values and re-read this comment:

John Larkin Says:

Hi.sorry. I have trouble with the “if you repeat experiment lots of times…p value…uniformly distributed between 0 and 1″.
Is that true? If you do it lots of times do you get as many grouped around 0.0-0.01 as around 0.49-0.50?
It may be because I’m thinking of “experiments” (e.g. height of groups)…vs some statistical scenario whish uses the word stochastic – which clearly puts me in trouble.
I don’t think of pvalue as direct measure of likelihood of nul hypothesis. But if you compared two big samples (huge!) from two big groups twice (say, of height) and each experiment gave you a p-value of 0.99….I just get the feeling that these two groups might be very similar/same population…..
Cheers
JL

Thomas Mailund Says:

John: Yes, p-values are uniformly distributed (under the null distribution) so you do expect to observe as many in the interval 0.0-0.01 as in 0.49-0.5.

You cannot consider a p-value of 0.99 as any kind of measure of similarity. It just doesn’t work that way.

The reason we are interested in low p-values is because if we sample from a mixture of the null distribution and the alternative distribution, then we expect more of the alternatives in the low end of p-values than we expect from the null.

Hope that helps.

Now that I think about it, this isn't strictly true.

I still hold that p-values are uniformly distributed under the null model. So under the null model, you cannot conclude that a high p-value indicates strong support for the null model whereas low p-values support the alternative model. It doesn't work like that.

But of course, the null model can be wrong in more than one way, and not all will show up as low p-values.

If your null model tells you that there should be a certain variance, and you see less, then you will probably see an excess of high p-values. The observations are more similar than they should be (under the null model).

You won't see the problem as too many low p-values, but as too many high values.

If the p-values are not uniformly distributed, your null model is wrong. It can be wrong in so many ways that it really doesn't matter why it is wrong. It is just wrong.

Hope that makes sense.

### Oh the absurdities

Friday, February 4th, 2011

Not only did she commit scientific fraud, she even lied about her mother's and sister's death in a car accident (and later had them on the guest list for an award ceremony).

They were dead but got better? Some amazing doctors, I assume?

The mind boggles about how she could think that she would get away with this...

Update: More herehere and here.

In English:

Something is rotten in the Denmark...

### You give science a bad name!

Thursday, February 3rd, 2011

I wasn't going to comment on this, but it is getting ridiculous now.

There's a case of scientific fraud going on at Copenhagen University, that isn't just your "typical" fraud case, but is reaching the absurd.

Recent coverage (in Danish) here, here and here.

It is one of the poster scientists from Copenhagen U that is not only on trial for scientific fraud, but it has reach the level of legal actions against her for falsifying documents. She was reported to the police for this recently. It has even reached the ministerial office. This is just crazy!

This is someone who got the "elite scientist" award a few years back. I got the junior version in 2008, but I am feeling a bit ashamed of this now.

In an independent case -- and for legal reasons, due to closed doors policies at court we have to assume it is an independent case although everything points towards the same scientist -- a research at Copenhagen U tried framing a student for the fraud. Not just scientific but financial.

I find it hard to grasp how someone who has been known to have dodgy results -- and this is an old case -- was used as the poster child by the university, but even more I find it hard to grasp how scientific fraud can be taken this far.

I can sort of see how the cut-throat competition in a field where there are so few tenure positions per scientist can lead to desperation. I can see how someone who really believes in a hypothesis can doctor some experiments by avoiding the evidence against and promote the evidence for the desired result.

Not accept, but partly understand. Assuming that they believe that further studies will eventually prove the hypothesis.

But once you start sliding down that slippery slope, eventually you must know that you will be caught. We are in a field where everything is tested again and again.  You will eventually be confronted with dodgy results.

How can anyone believe that they will get away with it? That, I don't get.

What I consider the strongest point of science is that the whole system is based on figuring out the truth. We have a system designed for that specific purpose, and it is amazingly powerful. If a theory is wrong, we will eventually find out. Then we will start to question why we thought otherwise earlier, and if it is because of dodgy science, we will figure that out.

Trying to cheat in science is silly. The whole system is designed to figure that out, and I feel angry that someone will even try!

Not only that. I get angry thinking about the time and money spend trying to validate results that are just based on bogus.

There is a reason we consider scientific fraud the highest sin a researcher can commit.

### God I hate spammers

Friday, July 2nd, 2010

I hate spammers.  I really, really hate spammers!  I think they should be shot on sight.  No trial, just instant execution.

I haven't been around the blog for a while because of RSI, and while I've been away, Akismet seems to have let 20,000 spams through.  I usually get a few thousand spams a month, but I guess the spammers smelled blood once some of their comments came through, and within the last couple of weeks, yeah, I've been spammed twenty thousand times.

I'm really in the mood to track some of those spammers down and club them to death.

Especially since it is going to take me ages to get rid of the spam again.  I've tried to get Akismet to recheck all the comments, but I can only make it check the pending comments and those 20k spams are, for some reason, not checked.  So I have to delete them manually.

I can delete around 100 at a time, more than that and I get an error from WordPress.  And it is not exactly fast deleting 100 comments, so I am not looking forward to doing it 200 times.

I really, really, really hate spammers