Database Dangers: The easy evidence is what they follow

You may have run into the story of a fireman charged with burning down his own home. They charged him because his Safeway Club card records showed he had purchased the type of firestarter that was used in the arson on his house.

Sounds like a good case? Problem is somebody else confessed to the arson. He's now a free man.

People often wonder why privacy advocates get up in arms about things like the Safeway database. I mean, how can it harm you, especially if you're not doing anything suspicious?

The problem is that police are attracted to the evidence that is easy to find. But when databases become more and more comprehensive, the chance that they will contain something interesting grows.

In an old-time investigation, finding receipts for the firestarters would be a major clue, and mind convict somebody. That's because searches of what you bought weren't so easy. If you bought the very tool used in the crime, and it was prominent enough that they found it, it looked bad for you.

But the cops aren't aware they are falling into one of the traps of bad science. When you have a lot of data, you can always find something that matches what you are looking for. When you find it, your intuition tells you "this is too strange to be coincidence." But in fact math tells us that it is. That's why you must never start with the conclusion and dig around in a big pool of data looking for evidence of your conclusion. Good scientists have known not to do this for years. Cops haven't.

Comments

Makes it look like scientists have learned not to do it and cops haven't. Unfortunately good scientists are few and far apart. And journalists reporting half stories and copycatting them one from another are doing their share of damage too.

A typical example is finding a correlation. You want to know what causes A. Statistics show a correlation between A and B. Bingo, B causes A. Well, yes, unless A causes B. Hands down to a scientist that may have needed a lot of work to find a correlation. That can be an achievement in itself, worth publishing. But beware of those who non-scientifically interpret the results and think they know what is causing what, simply because it seems to be an answer to a particular question they want answered. BTW, perhaps both A and B are caused by C...

Maybe the WA firefighter didn't do it and the police caught some bad data in their review of Safeway records. But other times, that data is helpful (example below). From which:

"Kalytiak reminded jurors that three days before the blaze someone used Welton's Carrs' (Safeway affliate) card to purchase sleeping pills and a gas can.

Prosecutors have argued that Welton put sleeping pills in the boys' drinks, then poured gasoline around their bedrooms and ignited the fuel."

And she'd taken out life insurance policies on teenage boys !! and had financial trouble.

Not that there are a lot of clever crooks out there, but another problem with these databases is that you could set someone up by purchasing gas cans, drugs, etc simply using their phone number.

David in Kenai, Alaska

Not sure if this requires registration, I'll post it below:

http://peninsulaclarion.com/stories/052902/ala_052901ala0020001.shtml

Web posted Wednesday, May 29, 2002

Jurors hear closing arguments in Welton murder trail

PALMER (AP) -- In closing arguments Tuesday in the murder trial of Suzette Welton, the defense urged jurors to avoid another tragedy and find the defendant innocent of setting a house fire that killed her 14-year-old son.

''The state has shown a collection of circumstantial facts,'' said Greg Heath, the public defender representing the 38-year-old defendant. ''What happened that night we don't know, and neither do you. Please do not commit another tragedy. The evidence is not there.''

Heath described Welton as a mother in shock, very emotional, ''who was not allowed to properly grieve her losses'' after the September 2000 fire in a Wasilla duplex that killed her younger son Samuel.

Palmer District Attorney Roman Kalytiak painted a different picture, describing Welton as a woman in financial trouble, ''a fly by night person ...who was not thinking straight.''

Welton is charged with first- and second-degree murder, first- and second-degree arson and attempted first-degree murder.

The Palmer Superior Court jury was to begin deliberations Wednesday.

Welton and two of her other children -- Jeremiah, 16, and Bree, 6 -- escaped the fire, but Samuel died of smoke inhalation in an upstairs bedroom. ''He was trapped in an oven,'' Kalytiak said.

In nearly seven hours of closing arguments, the prosecution maintained that events surrounding the fire were more than just a strange series of coincidences.

''This was a great plan,'' Kalytiak said. ''It was pure evil. What went wrong with the plan? The defendant never expected Jeremiah to jump out of the window.''

The prosecution maintained that this was arson, rather than an accidental fire, and that the defendant, a former daycare worker, set the blaze. Expert witnesses including John Glenn, a private investigator who represents State Farm Insurance Companies, agreed that this was not an accidental fire, Kalytiak said.

''You think State Farm wants to pay this claim?'' asked Heath, arguing that Glenn's work was flawed because he chose an incompetent lab to test floor and carpet samples, and never interviewed firefighters.

The prosecution reiterated its arguments that Welton had little money at the time of the blaze, was facing eviction from the rented duplex, and had recently taken out life insurance policies on her sons. Kalytiak reminded jurors that three days before the blaze someone used Welton's Carrs' card to purchase sleeping pills and a gas can.

Prosecutors have argued that Welton put sleeping pills in the boys' drinks, then poured gasoline around their bedrooms and ignited the fuel.

The defense countered that Welton had a steady income, including $1,100 a month in child support, that it was possible that one of the boys had started the fire and that their mother tried frantically to put out the fire.

Heath said there is no proof that Welton drugged her sons' drinks with sleeping pills the night of the fire.

''We are not here to attack Jeremiah, but the truth is he lied and he has no credibility and he is the key witness in this case,'' Heath said.

Nobody knows who started the fire, how it started or when it started, he told jurors. ''Do not speculate.''

I read in this blog entry about The welton trial that they say that Jeremiah lied & lost his credibuility. What did he lie about? If you could respond to me in an email I would greatly appreciate it.

Add new comment