Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search
5 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
Scary tidbit from my sociology textbook: (Original Post) Brigid Jun 2012 OP
Well, let's see... cthulu2016 Jun 2012 #1
Latyana Sweeney showed that in 2000 salvorhardin Jun 2012 #2
Back in the 1800's Speck Tater Jun 2012 #3
I dated a fella in college who was from a small town in Wisconsin. WillowTree Jun 2012 #4
When I was a kid our small town had four-digit phone numbers. Speck Tater Jun 2012 #5

cthulu2016

(10,960 posts)
1. Well, let's see...
Sat Jun 9, 2012, 09:40 PM
Jun 2012

DOB = 365 x (call-it) 75 years... about 27,000 unque DOB per zip code

Gender roughly doubles the refinement of DOB, so call it 50,000 DOB/Gender combinations per zipcode

About 44,000 zipcodes.

So about 2.2 Billion DOB/Gender/ZIP combinations.

Yup, even accounting for the fact that not all zipcodes have people in them (soe are business or government reserved zips) it seems more than plausible

salvorhardin

(9,995 posts)
2. Latyana Sweeney showed that in 2000
Sat Jun 9, 2012, 10:41 PM
Jun 2012
The Massachusetts Group Insurance Commission had a bright idea back in the mid-1990s—it decided to release "anonymized" data on state employees that showed every single hospital visit. The goal was to help researchers, and the state spent time removing all obvious identifiers such as name, address, and Social Security number. But a graduate student in computer science saw a chance to make a point about the limits of anonymization.

Latanya Sweeney requested a copy of the data and went to work on her "reidentification" quest. It didn't prove difficult.

...

But it was only an early mile marker in Sweeney's career; in 2000, she showed that 87 percent of all Americans could be uniquely identified using only three bits of information: ZIP code, birthdate, and sex.

Link: http://arstechnica.com/tech-policy/2009/09/your-secrets-live-online-in-databases-of-ruin


It's problematic because medical and other researchers depend on anonymized data, and that's the sort of thing we want to be open and free, but if it's very hard to actually anonymize data, then what do you do?
 

Speck Tater

(10,618 posts)
3. Back in the 1800's
Sun Jun 10, 2012, 12:03 AM
Jun 2012

It was common to address a letter with first and last name and name of the city.*
If you added date of birth, name, city, and date of birth would have been enough to identify close to 100% of the U.S. population before 1900, and maybe even till 1920 or 1930, at a guess.

*People even used to play games with mail addresses, like:

HILL
-----
JAMES
-------
MASS

(James Underhill Andover Mass. which was an adequate and acceptable postal address back in those days.)


WillowTree

(5,325 posts)
4. I dated a fella in college who was from a small town in Wisconsin.
Sun Jun 10, 2012, 02:43 AM
Jun 2012

He addressed mail to his parents with just their last name and the ZIP Code.

 

Speck Tater

(10,618 posts)
5. When I was a kid our small town had four-digit phone numbers.
Sun Jun 10, 2012, 07:48 PM
Jun 2012

And if you wanted to call outside of town you had to call the operator.

Latest Discussions»General Discussion»Scary tidbit from my soci...