Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Statisticians Uncover the Mathematics of a Serial Killer

Unknown Lamer posted more than 2 years ago | from the something-about-murders-and-statistics dept.

Math 164

Hugh Pickens writes writes "Andrei Chikatilo, 'The Butcher of Rostov,' was one of the most prolific serial killers in modern history committing at least 52 murders between 1978 and 1990 before he was caught, tried, and executed. The pattern of his murders, though, was irregular with long periods of no activity, interrupted by several murders within a short period of time. Hoping to gain insight into serial killings to prevent similar murders, Mikhail Simkin and Vwani Roychowdhury at UCLA built a mathematical model of the time pattern of the activity of Chikatilo and found the distribution of the intervals between murders follows a power law with the exponent of 1.4. The basis of their analysis is the hypothesis that 'similar to epileptic seizures, the psychotic affects, causing a serial killer to commit murder, arise from simultaneous firing of large number of neurons in the brain.' In modeling the behavior the authors didn't find that 'the killer commits murder right at the moment when neural excitation reaches a certain threshold. He needs time to plan and prepare his crime' so they built delay into their model. The killings eventually have a sedative effect, pushing the neuronal activity below the 'killing threshold' – which is why there are large intervals of time between groups of murders. 'There is at least qualitative agreement between theory and observation [PDF],' conclude the authors. 'Stats can't tell you who the perp is, but they're getting better and better at figuring out where and when the next crime might happen,' writes criminal lawyer Nathaniel Burney adding that 'catching a serial killer by focusing resources based on when and where he's likely to strike next is a hell of a lot better than relying on the junk science of behavioral profiling.'"

cancel ×

164 comments

Sorry! There are no comments related to the filter you selected.

The cure for the itch... (0)

Anonymous Coward | more than 2 years ago | (#38722222)

...Is a few bodies of specific height, weight, and coloration.

Yeah I saw that on... (1, Funny)

teeloo (766817) | more than 2 years ago | (#38722238)

Numb3rs already. Yawn.

Re:Yeah I saw that on... (4, Insightful)

Zontar The Mindless (9002) | more than 2 years ago | (#38722258)

Numb3rs already. Yawn.

Dear teeloo,

Many of us reside outside the US and/or have lives.

Sincerely,

The rest of /.

Re:Yeah I saw that on... (1, Redundant)

dredwerker (757816) | more than 2 years ago | (#38722288)

Many of us have torrents and like Us crime dramas without ads.:) (probably)

Re:Yeah I saw that on... (2)

sjudd (162227) | more than 2 years ago | (#38722372)

Many of us have torrents and like Us crime dramas without ads.:) (probably)

dumbers hardly fits into that category

Re:Yeah I saw that on... (1)

johnsnails (1715452) | more than 2 years ago | (#38722776)

Do you really not like Numb3rs? Or is this some elites BS? I for one think its a great show. How would you make it better? Assuming you think its possible to have a show with some Savant like mathematician who solves crime? Do you like BBT out of curiosity?

BBT is horrible (0)

Anonymous Coward | more than 2 years ago | (#38723090)

The laugh track completely kills it.
It seems to aim for somewhat intelligent jokes and at the same time insults its audience by telling it when to laugh.

Re:BBT is horrible (1)

imakemusic (1164993) | more than 2 years ago | (#38723718)

No, no, it's the jokes that kill it. Try watching it without the laugh track (there are clips on youtube) - it's just not funny.

Re:Yeah I saw that on... (2, Insightful)

neokushan (932374) | more than 2 years ago | (#38722532)

Many of us have better taste in TV.

Re:Yeah I saw that on... (3, Interesting)

tehcyder (746570) | more than 2 years ago | (#38722574)

Many of us have torrents and like Us crime dramas without ads.:) (probably)

Buy Sky+ then. Oh, sorry, I forgot this is slashdot so we're entitled to anything we can get our hands on and believe that films and TV shows magically get made at no cost.

Yeah, blah blah "Intellectual property" doesn't really exist, it's only copying not stealing, whatever.

Re:Yeah I saw that on... (5, Interesting)

pla (258480) | more than 2 years ago | (#38723016)

Yeah, blah blah "Intellectual property" doesn't really exist, it's only copying not stealing, whatever.

Unfortunate that you got modded troll, because you make a good point.

I have to ask, though - At what point do you consider time and/or format shifting as "piracy", for ethical purposes?

If I watch live TV, no piracy, ostensibly because we see the ads that "pay" for it. But I can (and back before TiVo, most people did) use commercials as food/bathroom breaks, or just flip channels during them, so even in the bad-ol'-days, no one really watched them.

If I buy the season on DVD, no piracy, because I've actually directly paid for the content.

If I download the same show from a torrent, most of us would agree that violates the spirit of copyright, even if we don't particularly care and do it anyway.

If I rent the DVD and rip it, I think most would consider that piracy.

And of course, we have the DVR, where I can time and format shift it to watch wherever and whenever I want, which IMO most people have come to accept as not piracy.

But - How does ripping or torrenting differ from the DVR case, either functionally or in terms of compensation? Whether I "rip" a show from broadcast TV or rip it from a DVD, it makes absolutely no difference to the producer. Whether I download it from a torrent or "download" it from my TiVo To Go, it makes absolutely no difference to the producer. Whether I watch it live and promise to completely ignore the commercials, or watch a torrented 4th-hand fansubbed unlocked-PSP version, it makes absolutely no difference to the producer.

Basically, once the producer has "given it away" by broadcasting it to the world, how can any use of that content really fall into the same box as "stealing"?

Re:Yeah I saw that on... (1)

Marcx77 (1193559) | more than 2 years ago | (#38723098)

Your argument goes astray when you say that it makes no difference to the producer whether you watch something without ads through TiVo and the like, or by torrenting something. It makes a difference in the sense that built into the price of broadcast tv (i.e.: free) is the assumption that a certain portion of viewers will find the ads so annoying that they'll get it on DVD. From a producer's point of view, the choice isn't between watching it on TV (while skipping the ads) and watching a torrented episode (without ads); the choice is between watching it on TV and buying it on DVD. An often heard counterargument to the above is that the people who download wouldn't have bought in the first place. I can at least anecdotally disprove that by saying that since I got a media box with Sickbeard I haven't bought any series on DVD, which previously I did (albeit incidentally). And even though downloading (without uploading) is legal in my country, it's not something I feel particularly good about.

Re:Yeah I saw that on... (1)

AJH16 (940784) | more than 2 years ago | (#38723800)

This is more a statement of the apparent ineffectiveness of advertising. The fact is that the majority of advertising is largely ignored, but they are simply looking for brief impressions that yield small returns, but are also very cheap per impression. If you are skipping it with your DVR, you'll probably still catch the beginning and end of each commercial break and at least have a small impression. For marketers, even that small impression being mixed in is still worth paying for. Maybe you aren't seeing as much as other viewers are, but it also would drive up the value of the first and last commercial spot in a break.

You can debate the effectiveness all you want, but the fact is still that there are marketers willing to compensate the content creator for you to DVR the program and skip their adds. If you could get someone to compensate them for torrenting it, without giving you meaningful ads, then you would have a similarly good deal. Something like Hulu is really kind of similar to this idea, but they stream it so as to be able to charge advertisers by impression.

Re:Yeah I saw that on... (1)

JasterBobaMereel (1102861) | more than 2 years ago | (#38723832)

For no other reason than that the government says it does ...

This is the problem with copyright (and Patents) they make no sense with modern technology, either you ban what everyone would agree is normal legal use, or all copying is valid and legal ...

It's like putting a film on a huge screen in a public place then trying to sell ticket to people to watch it ... ?

Re:Yeah I saw that on... (1)

hairyfeet (841228) | more than 2 years ago | (#38723860)

I say as far as TV there shouldn't be a way to even label it AS piracy if they are showing it OTA. After all if you can get it for absolutely free why should they give a crap if I don't have the time to watch it at say Wed at 8PM? If they would just let us watch when we have the time I wouldn't need to fricking format shift would I? It also ignores the fact that seeing a show, be it OTA or BT can get a person interested enough to buy. I have the almost complete Whedon collection* which probably cost close to $1000 along with a couple of sideshow collectible figures from Buffy that my late sister got me as bookends simply because I was able to download a couple of episodes of BtVS off of eMule. When Buffy was on the air there wasn't a station in this area with a strong enough signal to actually watch it and frankly if I hadn't downloading a couple of episodes and got hooked on the writing I would have NEVER bought it based on the description. I mean a show based on a bad movie with the guy from the Taster's Choice commercials and a soap actress as stars? Doesn't sound even a tiny bit appealing to me, but after seeing a few episodes i got hooked on the witty dialog and ended up getting the complete box set along with the Angel and Firefly set so that's a $1000 they would have never gotten otherwise.

As for TFA frankly I don't see how anyone can predict batshit. With serial killers we've seen everything in this country from a sexual sadist clown (Gacy) to one that was killing the same girl over again (Bundy) to a guy that thought the neighbor's dog was giving him orders (Son of Sam) to a nutbar collecting slaves for the afterlife (Zodiac). If its one thing we've learned about these freaks its that like a virus there is always some new mutation and there is as many reasons for them doing it as there are stars in the sky. I have to wonder how much of these "patterns" are simply trying to find meaning where none exists? it seems we humans really don't like things that are unpredictable and out of control and that pretty much describes serial killers.

(*didn't get Dollhouse, never cared for it)

Re:Yeah I saw that on... (1)

johnsnails (1715452) | more than 2 years ago | (#38722768)

ditto

Re:Yeah I saw that on... (0)

Anonymous Coward | more than 2 years ago | (#38723008)

Maybe if you ask nicely someone can explain numb3rs to you.

Re:Yeah I saw that on... (0)

flyneye (84093) | more than 2 years ago | (#38723220)

What would really be of interest would be to take these numbers, compare and contrast to corrupt politicians, police, doctors with high failure rates, pedo-priests and other ne'er-do-wells.
      Where are the scientists interested in ADVANCING the work of others? Does everything really need to take so damned long? Am I the only one who has to come up with these ideas? Is the beer cold yet? Gimme...

Re:Yeah I saw that on... (1)

gstoddart (321705) | more than 2 years ago | (#38723834)

Numb3rs already. Yawn.

And, of course, the thing to remember about Numb3rs is they didn't really have a genius mathematician who solved all of these problems. Much of the math was solid-sounding, but generally they weren't afraid to use math like Star Trek used tachyons and just make stuff up.

So, the fact that real statisticians identified this is in no way lessened by anything you saw in Numb3rs.

Also, Superman doesn't really live in New York City, and Jack Bauer isn't a real guy. Oh, and there is no Santa Claus or Easter Bunny or Tooth Fairy.

Sorry to disappoint, but you're talking about fiction on TV.

Great. So now all we need... (4, Insightful)

Tastecicles (1153671) | more than 2 years ago | (#38722252)

...is another series of murders to consolidate the theory.

Any takers?

Re:Great. So now all we need... (2)

Anonymous Coward | more than 2 years ago | (#38722402)

Okay. I'll do it. It'll only be four people, though, is that enough? I hope so.

Re:Great. So now all we need... (4, Funny)

dintech (998802) | more than 2 years ago | (#38722616)

I wonder if it also correlates to how often you post on Slashdot. We don't know who you are AC, but we know when you'll strike next.

Re:Great. So now all we need... (1)

Anonymous Coward | more than 2 years ago | (#38722440)

Exactly. You can fit anything to a given set of data to show some sort of correlation. It seems to me they simply played with their model until it fit the data in a reasonable way, and now needs to show that it can also predict the behaviors of other serial killers who have a similar condition. Does this model fit any other killer's pattern? Does it fit any other epileptic behaviors? Kind of a weird study, granted I haven't actually read the actual paper.

Re:Great. So now all we need... (2)

slartibartfastatp (613727) | more than 2 years ago | (#38722686)

Exactly. You can fit anything to a given set of data to show some sort of correlation

Sounds like science to me.

Re:Great. So now all we need... (1)

lightknight (213164) | more than 2 years ago | (#38722818)

We call that 'soft science,' as opposed to the 'hard science' variety.

Guess which one scientists have in mind when they are talking about "understanding things?"

And for a bonus point, guess which one politicians use when trying to craft a new law?

Re:Great. So now all we need... (0)

Anonymous Coward | more than 2 years ago | (#38722972)

Sounds like junk science to me.

Fixed that for you. The mathematical model looks exciting, but...

n = 1

No matching control (Difficult, but there are plenty of options for developing a convincing one). No significance.

It won't just take one other instance to prove this hypothesis; it will take several. That's not saying it can't or won't be done. I'll be excited if they produce a solid paper from further experiments/ observations.

Re:Great. So now all we need... (0)

Anonymous Coward | more than 2 years ago | (#38722862)

actually it's enough for them to develop the theory with only the subset of the data available. Then, when it's all nice and ready and fit for public consumption, as a final sanity check they can check if it works on the final bit of stashed, unanalyzed data. Of course, you can only do this once.

Re:Great. So now all we need... (4, Interesting)

Hentes (2461350) | more than 2 years ago | (#38723328)

Exactly. This whole hypothesis is based on one data point alone. There were more than one serial killers, why did they try their hypothesis on just this one? Or was he the only one who fit in the equation?

Sounds like the dude... (0)

niftydude (1745144) | more than 2 years ago | (#38722272)

just needed to get laid often enough so that his neuronal activity stays below the 'killing threshold'.

Sleeping with serial killers saves lives!

Re:Sounds like the dude... (5, Funny)

Ben_R_R (1177533) | more than 2 years ago | (#38722284)

Getting laid prevents serial killers? Suddenly I feel a lot less safe around here...

Re:Sounds like the dude... (1)

Tastecicles (1153671) | more than 2 years ago | (#38722422)

Suddenly Senior High doesn't sound like such a safe place...

Re:Sounds like the dude... (5, Funny)

ArsenneLupin (766289) | more than 2 years ago | (#38722286)

Sleeping with serial killers saves lives!

... but not necessarily yours...

Re:Sounds like the dude... (1)

turing_m (1030530) | more than 2 years ago | (#38722392)

I know you're trying for the funny but a lot of them are married or have girlfriends.

Re:Sounds like the dude... (2)

mikael_j (106439) | more than 2 years ago | (#38722408)

True, but from what I've read about the topic (hey, serial killers are fascinating in their own morbid way) there are also plenty of them that seem to have turned to true crazy after spending many years as unwilling social outcasts.

So to a small degree the parent poster may be sort of right, there might now somewhere out there be some guy who just happened to finally get laid and thanks to that he never snapped completely...

Re:Sounds like the dude... (1)

tehcyder (746570) | more than 2 years ago | (#38722592)

So to a small degree the parent poster may be sort of right, there might now somewhere out there be some guy who just happened to finally get laid and thanks to that he never snapped completely...

As I would assume everyone on slashdot knows, you can get broadly the same physical release from masturbation as actually having sex. The profound psychological issues associated with being a serial killer won't suddenly vanish just because you get to come inside a woman instead of a tissue.

Re:Sounds like the dude... (0)

Anonymous Coward | more than 2 years ago | (#38722644)

you can get broadly the same physical release from masturbation as actually having sex

Shouldn't that be: you can get broadly the same physical release from sex as you can have from masturbation?

Re:Sounds like the dude... (1)

Captain Hook (923766) | more than 2 years ago | (#38722934)

Thats what I was thinking, sex is more than just physical, it's also about a connection with another living being.

Of course that connection can be good or bad, or even indifferent but it's still a connection.

Re:Sounds like the dude... (4, Insightful)

niftydude (1745144) | more than 2 years ago | (#38722420)

Being married/having girlfriends does not imply getting laid. They can quite often be mutually exclusive sets. Some men are driven to drink, use drugs, post on slashdot in such situations. Others may be driven to commit homicide.

Re:Sounds like the dude... (2)

slackware 3.6 (2524328) | more than 2 years ago | (#38722508)

I'd rather post on /. than kill someone but than again the internet has never been down for more than a day. :) So who knows? Maybe /. is the glue that binds the serial killer community together. Me I like to drink and then post on /. and then get modded into oblivion for being a troll which makes me want to be a serial killer. And since the keyboard is mightier than the sword beware. I have a keyboard and I'm not afraid to use it.

Re:Sounds like the dude... (1)

Whiteox (919863) | more than 2 years ago | (#38722646)

There must be a minimal set of shared characteristics that join all /. posters together.
I wonder what they are?

Re:Sounds like the dude... (2)

azalin (67640) | more than 2 years ago | (#38722864)

whatever it is, it's probably sticky and hip people wouldn't like to be seen near it

Re:Sounds like the dude... (4, Funny)

user32.ExitWindowsEx (250475) | more than 2 years ago | (#38722882)

And since the keyboard is mightier than the sword beware. I have a keyboard and I'm not afraid to use it.

You own an IBM Model M keyboard?

Re:Sounds like the dude... (2)

jd2112 (1535857) | more than 2 years ago | (#38723116)

And since the keyboard is mightier than the sword beware. I have a keyboard and I'm not afraid to use it.

You own an IBM Model M keyboard?

A Model M is dangerous only if you have better upper body strength than the typical slashdotter.

Re:Sounds like the dude... (4, Funny)

Gordonjcp (186804) | more than 2 years ago | (#38723136)

Some men are driven to drink, use drugs, post on slashdot in such situations. Others may be driven to commit homicide.

Some write Byzantine filesystems. Some do both.

Re:Sounds like the dude... (1)

slackware 3.6 (2524328) | more than 2 years ago | (#38722480)

Exactly it's the wife's fault she drove me to it. Seriously though I jest.

Re:Sounds like the dude... (5, Interesting)

antifoidulus (807088) | more than 2 years ago | (#38722472)

Um, did you read anything on this guy? He couldn't get it up apparently, and that is what supposedly sent him into a rage. Dude was married, so ostensibly he had access to a woman, but if he couldn't get it up he couldn't get it up.....Not to mention you have killers like Ted Bundy who are incredibly charming(Bundy had something like 3 girlfriends at a time at some points in his life, dude even had women fawning over him AFTER they had learned he was a serial killer), but kill anyway......

Re:Sounds like the dude... (1)

renoX (11677) | more than 2 years ago | (#38723840)

> even had women fawning over him AFTER they had learned he was a serial killer

That's not an indication of charm, as the "there's no bad publicity" goes, it 's quite likely that some guys have more success with woman after it is revealed that they are serial killers..

Re:Sounds like the dude... (1)

tehcyder (746570) | more than 2 years ago | (#38722584)

And how precisely do you know that getting laid decreases neuronal activity?

Re:Sounds like the dude... (1)

MrHanky (141717) | more than 2 years ago | (#38722782)

Lack of knowledge about the killer's neural activity is what he has in common with the researchers. So hush, we're doing science here. Science in the dark.

Re:Sounds like the dude... (1)

Hentes (2461350) | more than 2 years ago | (#38723346)

Tell that to Jack the Ripper.

so it was the mathamatician (2)

spokenoise (2140056) | more than 2 years ago | (#38722298)

in the library with the pencil

Re:so it was the mathamatician (1)

spokenoise (2140056) | more than 2 years ago | (#38722302)

mathematician even!

They have 1 data point (5, Insightful)

Anonymous Coward | more than 2 years ago | (#38722300)

Aren't they jumping the gun a bit?

Re:They have 1 data point (0)

Anonymous Coward | more than 2 years ago | (#38723720)

Good sir, allow me to nitpick.

They have more than one data point. What they have is one data set.

Thank you and good day.

I've been in Rostov (0)

Anonymous Coward | more than 2 years ago | (#38722334)

and this shows why mathematical formulas are hard for this sort of thing. Does the formula take into consideration that living in a dead boring town with nothing except churches and no jobs or money might've given this nut little else to do? Maybe if this parasite was born in a big city he would've been more busy with work and murdered less frequently due to being preoccupied with other things?

Re:I've been in Rostov (1)

slackware 3.6 (2524328) | more than 2 years ago | (#38722518)

Did someone ever account for the church/serial killer ratio? AC has a point.

Re:I've been in Rostov (1)

antifoidulus (807088) | more than 2 years ago | (#38722732)

Well it did give him plenty of victims, the dude, like most other serial killers he didn't select his victims "randomly", he mostly chose victims who he could get easy access to and whom very few people would miss if she "disappeared", i.e. runaways and prostitutes. In the more desolate areas of the (rich) world, these people can usually be found in spades....

Be ready! (1)

Anonymous Coward | more than 2 years ago | (#38722338)

Minority Report is gonna be real!
Not soon but it WILL be!

What if... just... what if... (0, Interesting)

Anonymous Coward | more than 2 years ago | (#38722358)

different people are... different?

always some correlation to a single set of data (5, Insightful)

Chrisq (894406) | more than 2 years ago | (#38722360)

If you look hard enough you can always find some function that correlates to a single set of data. Like the analogy in a beautiful mind [imdb.com] , you can find any pattern or picture in the stars if you look hard enough.

Re:always some correlation to a single set of data (1)

Improv (2467) | more than 2 years ago | (#38722394)

The question in science has always been, "does it have predictive power?"

Re:always some correlation to a single set of data (1)

mhelander (1307061) | more than 2 years ago | (#38722828)

It can if you reapply the trick of staring hard enough at the experiment output until you see the desired result.

Re:always some correlation to a single set of data (5, Insightful)

NoMaster (142776) | more than 2 years ago | (#38722428)

True. The power law, though, is a particularly dangerous and entrancing trap to fall in to. Almost everything in nature - from pure randomness to highly structured effects - can be fitted to a power law. You often don't even need to do any transformation of the data - simply choosing the wrong set of dependent and independent variables to examine can do it.

My favourite goto whenever this subject comes up is the essay "So You Think You Have a Power Law - Well Isn't That Special?" [umich.edu]

That said, I haven't read the current paper. They might have been very careful to avoid the common traps. I won't know until I spend some time tomorrow reading it.

Re:always some correlation to a single set of data (1)

u38cg (607297) | more than 2 years ago | (#38722522)

Agreed. I'd be very surprised if the data doesn't point just as strongly to an exponential distribution. Phrases like "the psychotic affects, causing a serial killer to commit murder, arise from simultaneous firing of large number of neurons in the brain" sound a little bit hand-wavey to me.

Re:always some correlation to a single set of data (1)

tgv (254536) | more than 2 years ago | (#38723026)

A bit hand-wavey? You're being kind. Large groups of neurons collaborating to trigger a single event have been proposed to model precise timing, e.g. in movement, and locking behavior has been observed for speeds in the order of 100Hz to 5Hz, but synchronization over such a long period of time? And large groups? You would think that would be totally impossible. It sounds like
1. We don't know how a large group of neurons behave over long periods
2. We don't know what triggers a serial killer
3. ?
4. Publication!

Re:always some correlation to a single set of data (1)

vikingpower (768921) | more than 2 years ago | (#38722542)

That is what I am going to do, too - along with the umich.edu paper. I recently "found" a power law in some load- and performance testing data; I am suddenly growing suspicious of my own interpretation, which is always a Good Thing.

Re:always some correlation to a single set of data (1)

pz (113803) | more than 2 years ago | (#38723266)

Whether the distribution is precisely power law or exponential really doesn't really matter that much. With only 52 data points and anything more than trivial noise in the data, every model is going to be an approximation, right?

The bit of profound observation in the paper is surely that there is an aperiodic temporal pattern, and therefore a skewed distribution, that can be modelled with some accuracy. For one killer. And we all know, or should know, the dangers of generalizing from a single example.

junk science (0)

Anonymous Coward | more than 2 years ago | (#38722406)

catching a serial killer by focusing resources based on when and where he's likely to strike next is a hell of a lot better than relying on the junk science of behavioral profiling.

I am so disappointed. This took all the fun out of "Silence of the Lambs" and a succession of TV shows

Too little data, and not useful for prediction (3, Informative)

mugurel (1424497) | more than 2 years ago | (#38722410)

The 'murder probability' comes from a probability density function spanning three years, and is estimated from 53 data points, all from the same subject. That is hardly reliable.

And if we take the sparsity of the data for granted, what is the conclusion? That the less frequently the murderer acts, the less likely he is to act, and vice versa. It is a descriptive model, you can not predict the time of the next murder with it.

Re:Too little data, and not useful for prediction (1)

azalin (67640) | more than 2 years ago | (#38722904)

What a fitting fortune cookie: Williams and Holland's Law: If enough data is collected, anything may be proven by statistical methods.

Power law not usefully predictive in this case (4, Insightful)

Chuckstar (799005) | more than 2 years ago | (#38722424)

I think the importance of what they found is overstated. The fact that a murderer's patterns fit a power law is not particularly helpful in really pinning down the time of the next murder. "The expected time of the next murder is a distribution of odds along this curve" is not particularly useful in trying to stop a single crime. Power laws are more useful predictors when applied across populations.

While unlikely to ever be predictive, this result is more interesting from a more academic perspective. It could help illuminate what might be going on in the brain of a serial murderer. Learning how damaged brains function (or fail to function) has long been a means of studying how non-damaged brains may work.

So this might provide some insight into how a compulsive thought builds up in the brain, but it's unlikely to ever allow a profiler to say "stake out this intersection on this night".

Mathematical model of End of Earth. (2)

sempir (1916194) | more than 2 years ago | (#38722474)

I have one, however will not publish till final proof. I like to be accurate about these things.

Re:Power law not usefully predictive in this case (1)

rohan972 (880586) | more than 2 years ago | (#38722812)

"The expected time of the next murder is a distribution of odds along this curve" is not particularly useful in trying to stop a single crime.
[snip]
...it's unlikely to ever allow a profiler to say "stake out this intersection on this night".

Probably not but combined with other information, such as victim profile, MO, knowing a likely area within a couple of suburbs and a time within a couple of months could well be enough for police run undercover operations. I'm sure it would be harder than just dropping down to the corner and picking the murderer up but the police know there will be more work involved than that, I'm sure.

Re:Power law not usefully predictive in this case (1)

brucmack (572780) | more than 2 years ago | (#38723318)

That is true, but it could potentially be useful in linking murders to the same killer, in cases where the link otherwise might not have been made.

This really isn't new to The Police (2)

Plammox (717738) | more than 2 years ago | (#38722476)

Just watch this this. [youtube.com]

"junk science" of behavioral profiling (5, Insightful)

turing_m (1030530) | more than 2 years ago | (#38722500)

For behavioral profiling being a "junk science" they've had a lot of successes, and more success than this idea will ever yield (especially since it's so easily reverse engineerable, not to mention vague in its predictions). And the criticism coming from a criminal lawyer - well, I think the lady doth protest too much.

The basic idea of profiling is to narrow a large search down into a smaller one. The basis of the idea that by studying known offenders and finding commonalities between them, you'll have a clue as to the sort of person a perpetrator will be given an arbitrary new crime. Now that enough information about profiling is out there, offenders can and do reverse engineer the profiling process to make it tougher for them to get caught (assuming they are smart enough to do so - many are not that smart). However, at the very least there will be certain things that they are compelled to do otherwise the crime is simply not interesting for them to do. And certain things they have to do to carry out their crimes which will give a clue as to who they are.

The way I look at it, the people who study these particular criminals and offer advice for catching them are analogous to specialist doctors. For example, if you are trying to diagnose and treat some specialist skin condition that is very rare, you will have better results with a referral to a dermatologist than having the GP struggle and try to treat it as best he can.

Re:"junk science" of behavioral profiling (5, Insightful)

nyctopterus (717502) | more than 2 years ago | (#38722718)

Actually, profiling has been seriously challenged, there's a nice New Yorker article [newyorker.com] about it, and several scholarly papers [anu.edu.au] , Alison L and Rainbow L. eds (2011) 'Professionalizing Offender Profiling: Forensic and Investigative Psychology in Practice'. Routledge, London. The charge is that profiling is similar to astrology, make vague claims that could match a variety of scenarios, and pay attention when it fits, not when it doesn't.

Like a lot of forensic techniques, it seems to have jumped from the theoretically plausible to practice, without going through the intermediate step of check that it works. "Junk science" may be a fair characterisation.

Re:"junk science" of behavioral profiling (2)

kale77in (703316) | more than 2 years ago | (#38722730)

Mod parent up. I don't know whether profiling works or not, but that final comment was certainly tacked on without justification.

  1. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. Reasonable statement. ... P.
  2. Therefore P.

Re:"junk science" of behavioral profiling (2, Interesting)

lightknight (213164) | more than 2 years ago | (#38722860)

The General Practitioner, however, does serve a purpose. He / She has general knowledge of a multitude of diseases, forming a kind of filter, that if he can't treat a disease, he can generally point you in the right direction (refer you to a specialist who may have better equipment / knowledge for a better diagnosis). If medical specialists are encyclopedic albums, then the General Practitioner typically serves the role of the index.

You don't want to be treated by a dermatologist if you need an oncologist.

And yes, profiling is a "junk science." The saying "You would not have seen, if you had not believed" applies here -> the number of laws on the books right now are sufficient to charge anyone with a crime, misdemeanor or felony. You give me a week, with some information about a person, I can find a law to have them put away for a few years. Open a phone book, pick a name at random from the White Pages, and through no artifice, I will find a way to have them charged.

Re:"junk science" of behavioral profiling (2)

Hognoxious (631665) | more than 2 years ago | (#38723074)

For behavioral profiling being a "junk science" they've had a lot of successes, and more success than this idea will ever yield

I agree. It sounds to me like the author has an axe to grind.

Chikatilo the subject of a movie back then (1)

Provocateur (133110) | more than 2 years ago | (#38722530)

Was this the one protrayed by Malcolm McDowell? I don't know if anyone here has seen that... I think he was the only recognizable one in that film.

Re:Chikatilo the subject of a movie back then (1)

taiwanjohn (103839) | more than 2 years ago | (#38723312)

Do you mean Citizen X [imdb.com] which starred Stephen Rea, Donald Sutherland, Max von Sydow?

Just the data, ma'am, please.. (4, Insightful)

nmnilsson (549442) | more than 2 years ago | (#38722564)

Oh man, I get so bothered when someone presents interesting data - only to append a theory that isn't connected to it.
Why is that? Don't you get to publish unless you have a theory, no matter how unrelated an implausible it is?
Human sciences especially - it's understandable though, as it's hard to read people's minds.

Neurons firing? Really?? Does fantasizing about objects we can actually see and touch suddenly make it science?
If the study included brains scans or something, sure. But all they did was look at numbers.

If you don't have a theory that's related to your study, just post your data and spare us your fantasies. Thank you.

Re:Just the data, ma'am, please.. (1)

Shavano (2541114) | more than 2 years ago | (#38723850)

Couldn't they have stuck with a hypothesis of "the temporal pattern of serial killing will be aperiodic but display a power-law distribution?"

Oh wait... they haven't analyzed enough data to support that conclusion either!

The Sudoku Killer (5, Funny)

Anonymous Coward | more than 2 years ago | (#38722586)

And in other news, police warn that the Sudoku killer will kill either 1, 4, or 9 victims next.

Power-Law distributions in empirical data (3, Informative)

G3ckoG33k (647276) | more than 2 years ago | (#38722608)

Here is the abstract of an article, "Power-Law distributions in empirical data" by Clauset et al (2009):

"Power-law distributions occur in many situations of scientific interest and have significant consequences for our understanding of natural and man-made phenomena. Unfortunately, the detection and characterization of power laws is complicated by the large fluctuations that occur in the tail of the distribution—the part of the distribution representing large but rare events— and by the difficulty of identifying the range over which power-law behavior holds. Commonly used methods for analyzing power-law data, such as least-squares fitting, can produce substantially inaccurate estimates of parameters for power-law distributions, and even in cases where such methods return accurate answers they are still unsatisfactory because they give no indication of whether the data obey a power law at all. Here we present a principled statistical framework for discerning and quantifying power-law behavior in empirical data. Our approach combines maximum-likelihood fitting methods with goodness-of-fit tests based on the Kolmogorov-Smirnov statistic and likelihood ratios. We evaluate the effectiveness of the approach with tests on synthetic data and give critical comparisons to previous approaches. We also apply the proposed methods to twenty-four real-world data sets from a range of different disciplines, each of which has been conjectured to follow a powerlaw distribution. In some cases we find these conjectures to be consistent with the data while in others the power law is ruled out."

So, I would recheck this guy's analysis.

Next step... (1)

oyenamit (2474702) | more than 2 years ago | (#38722672)

Pickup the pattern of other randomly chosen serial killers and see if they also fit the same mathematical model.
Only then this paper would be worth looking at.
Frankly, I am surprised how they developed and published this model with just a single data point !

Obvious problem? (1)

RogueSounds (2545546) | more than 2 years ago | (#38722842)

I wonder how they got their hands on the brain activity data of a serial killer in action?

Re:Obvious problem? (1)

azalin (67640) | more than 2 years ago | (#38722898)

Maybe the Matrix shared it's data with them. *cough*

Re:Obvious problem? (2, Informative)

Anonymous Coward | more than 2 years ago | (#38722920)

I wonder how they got their hands on the brain activity data of a serial killer in action?

They didn't. They "assume" it may be the same as epilepsy based on a 1879 (yes, 1879) book by a criminologist called Lombroso who believe that crime was caused by hereditary defects or the 'reversed' evolution of some populations. While discredited by later work, it remained a favourite source for people who wanted reasons to believe certain populations were inherently criminal or defective, in order to justify exterminating or sterilising them (along with the disabled).

However, Lombroso [5] long ago pointed out a link between epilepsy and criminality. A link between epilepsy and psychosis had been also established [6]. Thus, one may speculate that similar processes in the brain may lead to both epileptic seizures and serial killings.

While I am not a very 'politically correct' person, I believe that scientific papers should avoid making grossly offensive comparisons (even as 'speculation') about disabled people unless they can produce solid evidence and references less than 130 years old.

They then develop a model of neurons firing that they already know analytically will produce a power law and do a numerical simulation to show it produces a power law.

They then plot the simulation against the data on a log-log graph and claim they are similar, although there is no actual statistical analysis in the paper. Also, to me they don't actually look that similar, other than both having heavy tails. This is the attempt to comment on the central claim of their thesis:

Figures 2-3 show the results of these simulations. They decently agree with the experimental data.

There is no attempt to consider other possible models such as exponential etc. There is no comparison with datasets from other serial killers.

That seems backwards (1)

vadim_t (324782) | more than 2 years ago | (#38722880)

Given any dataset, you can come up with a formula that would match it.

That doesn't mean though that if they tried doing this back when he was on his 3rd or even 20th murder, they'd have managed to come up with something useful.

Re:That seems backwards (0)

Anonymous Coward | more than 2 years ago | (#38722908)

If we could predict the likelihood of a future event based on some mathematical model of the past, we would all be stockbrokers. What could possibly go wrong?

Re:That seems backwards (1)

BlueTrin (683373) | more than 2 years ago | (#38723182)

That is what this man did for a very long time: Jim Simons [wikipedia.org]

you Fail I7? (-1)

Anonymous Coward | more than 2 years ago | (#38722956)

Con7amiNated while

I see! (0)

Anonymous Coward | more than 2 years ago | (#38723014)

So all it takes to profile a serial killer is, well, build a regression model upon a small sample of, let's say, 50 slayings. Hooray statistics - real science!

Serenity in murder? (1)

dimethylxanthine (946092) | more than 2 years ago | (#38723042)

Thats just messed up. Why not get off by taking up skydiving, mountain biking, or bungee jumping off the Macau tower? He must have had a pretty f*** up upbringing (in addition to genes the somehow didn't checksum). Oh yeah, in Soviet Rusia it would be hard to leave the USSR or even know about such "bourgoise" activities...

North Korea (2)

ThatsNotPudding (1045640) | more than 2 years ago | (#38723352)

Makes you wonder if this might be fertile ground for (non-government sanctioned) serial killers as well, given that people no doubt disappear all the time and no one is foolish enough to ask about them. Chikatilo might turn out to be a piker.

Data from only 1 subject (-1)

Anonymous Coward | more than 2 years ago | (#38723420)

This is data that describes the behavior of only one individual serial killer. The authors need to prove that the same pattern is observable across MANY serial killers. Until they do that, they cannot possibly hope to draw generalizable conclusions.

junk science (0)

Anonymous Coward | more than 2 years ago | (#38723518)

like the way most people do statistics?

1. Take a hard science like math.
2. Add a bunch of highly subjective parameters and tweak them until you get the results you want.
3. ......
4. Profit!

Brain pacemakers (0)

Anonymous Coward | more than 2 years ago | (#38723520)

In other words, give a criminal a brain pacemaker and he will never commit crimes again.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?