Monthly Archive for May, 2013

Page 2 of 2

ACS to drop “Number of Times Married” question

This notice is from a Minnesota Population Studies Center data alert:

Dear IPUMS User,

I am writing to alert you that the Census Bureau is planning to drop the question on “number of times married” from the American Community Survey. For those of us who study family demography, this change would be a major loss. The times married question is not only vital for understanding blended families, it is also necessary for basic studies of nuptiality and marital instability. A recent working paper by Sheela Kennedy and myself demonstrated that the ACS is the only reliable source currently available for national divorce statistics. Without the number of times married, however, the divorce data will be badly compromised; for example, it will be impossible to construct a life table for first marriages, or to estimate the percentage of people who have ever divorced.

The news of this plan appears in the Federal Register in a single sentence at the end of an otherwise harmless notice of request for comments. If you believe as I do that this change would significantly harm the nation’s statistical infrastructure, you should make your feelings known to the responsible OMB desk officer, Dr. Brian Harris-Kojetin. He can be reached at (202) 395-7245 or by email at bharrisk@omb.eop.gov. The deadline for comments is May 16.

Thank you,

Steven Ruggles
Regents Professor
Director, Minnesota Population Center

Research from The Data Privacy Lab

Respondent re-identification is a big worry for data projects who want to share their data. And, some recent cases illustrate that can/is occurring with genetic data. But, sometimes the case is over-stated. Here is an illustration with a case that hit the press with great fanfare.

First, the fun stuff. See, if you are unique. The following link has you type in your gender, exact age of birth and your 5-digit zip code. The latter two do not meet HIPAA guidelines:

Next are several links: The first is the coverage of re-identification in the press (Forbes, The Scientist, & xxxx) followed by the researcher’s version of the story (Sweeney). The next is a rebuttal, which reminds readers that administrative matches, e.g., voting registration are not as ubiquitous as some claim. There is also a link to an article by Barth-Jones where he discusses the famous case of the re-identification of Governor William Weld, which lead to much of the HIPAA rules.

Harvard Professor Re-Identifies Anonymous Volunteers In DNA Study
Adam Tanner | Forbes
April 24, 2013

Participants in Personal Genome Project Identified by Privacy Experts
MIT Technology Review
May 1, 2013

“Anonymous” Genomes Identified
Dan Cossins | The Scientist
May 3, 2013

Identifying Participants in the Personal Genome Project by Name
Latanya Sweeney, Akua Abu, Julia Winn | Data Privacy Lab

Reporting Fail: The Reidentification of Personal Genome Project Participants
Jane Yakowitz Bambauer | Info/Law [Harvard Law Blogs]
May 1, 2013

The ‘Re-Identification’ of Governor William Weld’s Medical Information: A Critical Re-Examination of Health Data Identification Risks and Privacy Protections, Then and Now
Daniel C. Barth-Jones | Social Science Research Network (SSRN)
June 4, 2012

“it’s an Alice in Wonderland moment”

A post last week covered the House Republican "Census Reform Act of 2013." Here is some useful commentary from the national press.

GOP Census Bill Would Eliminate America's Economic Indicators
Michael McAuliffe | Huffington Post
May 1, 2013
This post has the best quotes:

Indeed, the government would not be able to produce any of the major economic indices that move markets every month, said multiple statistics experts, who were aghast at the proposal.

"They simply wouldn't exist. We won't have an unemployment rate," said Ken Prewitt, the former director of the U.S. Census who is now a professor of public affairs at Columbia University.

"I don't know how the market reacts if there is suddenly no unemployment rate at the start of the month," Prewitt said. "How does the market react if we don't have a GDP [gross domestic product]?"

"Do they understand that these data that the Census Bureau collects are fundamental to everything else that's done?" asked Maurine Haver, founder of business research firm Haver Analytics and a past president of the National Association for Business Economics. "They think the country doesn't need to know how many people are unemployed, either?"

"Independent observers had a hard time wrapping their minds around the legislation."

"It's hard to take this seriously because they're really saying also they don't want GDP. They want no facts about what's going on in the U.S. economy," said Haver. "It's so fundamental to a free society that we have this kind of information, I can't fathom where they're coming from. I really can't."

"It's so unimaginable. It would be like saying we don't need policemen anymore, we don't need firemen anymore," said Prewitt. "To say suddenly we don't need statistical information about the American economy, or American society, or American demography, or American trade, or whatever -- it's an Alice in Wonderland moment."

"Just as the House effort to stop the ACS went nowhere in the Senate last year, the current bill looks similarly likely to die there."

But supporters of the Census Bureau and of government-backed science are acutely aware that pieces of such measures have a way of getting attached to higher-priority legislation. In March, a measure from Sen. Tom Coburn (R-Okla.) that bars the National Science Foundation from doing political science research this year slid through the Senate attached to legislation to keep the government running.

And Duncan's bill comes as Congress has already proposed slashing the Census budget 13 percent below the president's request, and the bureau lacks a director to complain. There is also no secretary or deputy secretary at the Commerce Department, which oversees the bureau and would generally advocate its cause in Congress.

A new GOP bill would prevent the government from collecting economic data
Dylan Matthews | Washington Post Wonk Blog
May 1, 2013
One should never read comments, but this one by ottoparts sums this proposed bill succinctly: "The Party of Stupid strikes again"

Some selected quotes from the article:

"In what’s becoming a biennial tradition, another House Republican wants to cut the Census down to size. Rep. Jeff Duncan (R-S.C.) is rolling out the Census Reform Act this week, having formally introduced it April 18."

"It’s hard to overstate the loss of knowledge that this bill would bring about."

And, the best is an image that explains the "WHY" of this bill:


Congress: No more unemployment data for U.S.
Dan Primack | CNN Money
May 1, 2013
"Republican representatives want to gut the way we collect national economic data."

FORTUNE -- Bummed out by the latest unemployment or GDP report? Don't worry, Congress wants to help you out. Not by adding jobs or increasing productivity, but by eliminating the government surveys that help calculate such statistics in the first place.

Republicans introduce census reform bill that would end unemployment estimates
Stephen C. Webster | The Raw Story blog
May 1, 2013
"If the Census Reform Act of 2013 (PDF) becomes law, all data-gathering efforts at the U.S. Census Bureau except for the once-a-decade census mandated by the Constitution would come to an end."

"Republicans in the House tried and failed to kill the ACS last year. That sentiment appears to have returned in Duncan’s new bill, albeit in a much broader fashion."

Best Way to Deal With Unemployment? Don’t Track It.
Holly Scott | HardHatters Blog
May 1, 2013