LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (March 1996, week 2)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Fri, 8 Mar 1996 23:31:56 -0800
Reply-To:     Karsten Self <karsten@NEWAGE1.STANFORD.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>
From:         Karsten Self <karsten@NEWAGE1.STANFORD.EDU>
Subject:      solution & thanks - SSN distribution & interpretation

A few days behind the times having wrapped at Stanford, getting ready for SUGI. BTW -- weather update for Chicago:

Saturday Hi: 28 Lo: 19 Sunny Sunday Hi: 41 Lo: 26 Sunny Monday Hi: 48 Lo: 35 Sunny Tuesday Hi: 46 Lo: 37 Sunny Wednesday Hi: 51 Lo: 39 Rain

First, thanks to 'Doc' Muhlbaier, Ron (rbcrosic@cbdcom.apgea.army.mil), Chris Scott, Tom Soeder, Al Stone, Richard Epstein, Andrew Cary, Joel Achtenberg (not the 'why things are' dude), Matthew Zack, and others, for your responses.

'Computer Related RISKS' (Peter G. Neumann -- moderator of comp.risks on usenet, Addison Wesley, 1995) makes several interesting observations and anecdotes about SSN's. The book is currently on unauthorized loan to me by my ex-roommate in Menlo Park. I guess I'm just a guy who's know to take RISKS.... I also heartily plug the book, and comp.risks for everyone out there.

My question was on how to generate roughly equivalent subsets of SSN's for subsequent processing. Collate order was important, so I had to select data by the left side rather than the right side of the SSN (several people noted that when random sampling, you want to take, say, some all SSN's ending in '30', '45', '66', and '87'. This will generate a sample which is distributed in time and space, whereas sampling from the beginning of SSN will chose individuals who were all (when they received their SSN) in the same national region.)

Matthew gave me the specific data I was looking for -- triads and quartiles for SSN distribution. Matthew is at CDC and is probably working with the same types of data I am (was) -- Medicare:

> In a 5% systematic sample of 1991 Medicare enrollees 65 years old or > older, the breakdown of the first three digits of the SSN/Railroad > Retirement number was the following: > > Three digit range Percent range > > <= 173 0.0 - 24.9% > 174-326 25.0 - 50.0% > 327-461 50.1 - 75.0% > >= 462 75.1 - 100.0% > > <= 232 0.0 - 33.3% > 233-425 33.4 - 66.5% > >= 426 66.6-100.0% > > Matthew Zack

Chris and Al both forwarded me a detailed description of how SSN's are generated.

Structure of Social Security Numbers by Chris Hibbert

A Social Security Number (SSN) consists of nine digits, commonly written as three fields separated by hyphens: AAA-GG-SSSS. The first three-digit field is called the "area number". The central, two-digit field is called the "group number". The final, four-digit field is called the "serial number".

The process of assigning numbers has been changed at least twice. Until 1965, only half the group numbers were used. Before 1972, numbers were assigned by field offices; since 1972, they have all been assigned by the central office. The order in which numbers were assigned was changed in the 1972 transition. There may have been other changes, but it's difficult to get information on how things used to be done.

Area Numbers

The area numbers are assigned to geographical locations. They were originally assigned the same way that zip codes were later assigned (in particular, area numbers increase from east to west across the continental US as do the ZIP codes). Most area numbers were assigned according to state (or territorial) boundaries, although the series 700-729 was assigned to railroad workers regardless of location (this series of area numbers was discontinued in 1964 and is no longer used for new SSNs). Area numbers assigned prior to 1972 are an indication of the SSA office which originally issued the SSN. Since 1972 the area number in SSNs corresponds to the residence address given by the applicant on the application for the SSN.

In many regions the original range of area number assignments was eventually exhausted as population grew. The original area number assignments have been augmented as required. All of the original assignments were less than 585 (except for the 700-729 railroad worker series mentioned above). Area numbers of "000" have never been issued.

001-003 NH 400-407 KY 530 NV 004-007 ME 408-415 TN 531-539 WA 008-009 VT 416-424 AL 540-544 OR 010-034 MA 425-428 MS 545-573 CA 035-039 RI 429-432 AR 574 AK 040-049 CT 433-439 LA 575-576 HI 050-134 NY 440-448 OK 577-579 DC 135-158 NJ 449-467 TX 580 VI Virgin Islands 159-211 PA 468-477 MN 581-584 PR Puerto Rico 212-220 MD 478-485 IA 585 NM 221-222 DE 486-500 MO 586 PI Pacific Islands* 223-231 VA 501-502 ND 587-588 MS 232-236 WV 503-504 SD 589-595 FL 237-246 NC 505-508 NE 596-599 PR Puerto Rico 247-251 SC 509-515 KS 600-601 AZ 252-260 GA 516-517 MT 602-626 CA 261-267 FL 518-519 ID 627-645 TX 268-302 OH 520 WY 646-647 UT 303-317 IN 521-524 CO 648-649 NM 318-361 IL 525 NM *Guam, American Samoa, 362-386 MI 526-527 AZ Philippine Islands, 387-399 WI 528-529 UT Northern Mariana Islands

650-699 unassigned, for future use 700-728 Railroad workers through 1963, then discontinued 729-799 unassigned, for future use 800-999 not valid SSNs. Some sources have claimed that numbers above 900 were used when some state programs were converted to federal control, but current SSA documents claim no numbers above 799 have ever been used.

Group Numbers

The group number is not related to geography but rather to the order in which SSNs are issued for a particular area. Before 1965, only half the group numbers were used: odd numbers were used below 10 and even numbers were used above 9. In 1965 the system was changed so assignments continued with the low even numbers and the high odd numbers. So, group numbers for each area number are assigned in the following order:

1. Odd numbers, 01 to 09 2. Even numbers, 10 to 98 3. Even numbers, 02 to 08 4. Odd numbers, 11 to 99

Group codes of "00" aren't assigned

In each region, all possible area numbers are assigned with each group number before using the next group number. This means the group numbers can be used to find a chronological ordering of SSNs within a region. When new group numbers are assigned to a state, the old numbers are usually used up first.

SSA publishes a list every month of the highest group assigned for each SSN Area. For example, if the highest group assigned for area 999 is 72, then we know that the number 999-04-1234 is an invalid number because even Groups under 9 have not yet been assigned.

Serial Numbers

Serial numbers are assigned in chronological order within each aread and group number as the applications are processed. Serial number "0000" is never used. Before 1965, when number assignment was transferred from field offices to the central office, serial numbers may have been assigned in a strange order. (Some sources claim that 2000 and 7000 series numbers were assigned out of order. That no longer seems to be the case.) Currently, the serial numbers are assigned in strictly increasing order with each area and group combination.

Invalid SSNs

Any SSN conforming to one of the following criteria is an invalid number:

1. Any field all zeroes (no field of zeroes is ever assigned). 2. First three digits above 740

A pamphlet entitled "The Social Security Number" (Pub. No. 05-10633) provides an explanation of the SSN's structure and the method of assigning and validating Social Security numbers.

This description of the structure of the Social Security Number is based on messages written by Jerry Crow and Barbara Bennett. The information has been verified by its correspondence to the SSA's Program Operations Manual System (POMS) Part 01, Chapter 001, subchapter 01, which can be found at Federal Depository Libraries. (SSA Pub. No. 68-0100201.)

--------------------------------------------- Karsten M. Self -- Analytic Programmer

PM Squared, Inc 250 Montgomery St., Suite 810 San Francisco, California 94104

New: KMSelf@ix.netcom.com Old: Karsten@newage1.Stanford.EDU

What part of gestalt don't you understand?


Back to: Top of message | Previous page | Main SAS-L page