Tuesday, December 31, 2019

Book roundup 2019

A friend recently noted that she read more than 100 books in 2019, which sort of dampened my pride at reading 30 (15 non-fiction). Neither one of us counts flipping glossy cookbooks nor "early reader" chapter books read with the pint-sized members of our respective families. (My friend does count audiobooks, though, so maybe our eyes-on-words reading tallies aren't quite as disparate as it might seem?)

Anyway, since it's year-end, it's a good time for reflection. In addition to rethinking my stance on audiobooks, I'm going to share some reflections on what I read this year.

Some of the best non-fiction books I read in 2019 (regardless of original publication date):

Invisible Women
by Caroline Criado Perez

Thick
by Tressie McMillan Cottom

Heart: A History
by Sandeep Jauhar

The Library Book
by Susan Orlean


Tenth Island
by Diana Marcum

Saturday, December 14, 2019

Differential Privacy and the 2020 Census

December 11-12 the National Academies hosted a workshop on 2020 Census Data Products, with a focus on the implications of implementing differential privacy as a key privacy protection tool in the "disclosure avoidance system."


Presentations and recordings (including mine) can be found here:

https://sites.nationalacademies.org/DBASSE/CNSTAT/DBASSE_196518


17-Session E Jarosz from The National Academies on Vimeo.

Wednesday, November 6, 2019

Test run of Differential Privacy for the 2020 Census

The Census Bureau is investigating a technique, known as Differential Privacy, to avoid inadvertently disclosing individual information in the 2020 Census. (See the Census Bureau's overview for more on how differential privacy works.)


But some data users are concerned that the level of noise added to the data, or the process used to add that noise, may result in poor data quality.

To give data users a chance to assess how Differential Privacy (DP) would affect the quality of data, the Census Bureau released demonstration data based on the 2010 Census. The demonstration data can be compared with original 2010 Census tables to see how much "noise" DP would introduce. Files are available via FTP download and require SAS or other statistical programming to open the files and extract the data.

For users who do not have access to the statistical software or coding skills required to work with the raw demonstration data tables, IPUMS NHGIS produced user friendly data tables that can be accessed on their website.

The Committee on National Statistics has also issued a Call for Input for their December Workshop on 2020 Census Data Products: Data Needs and Privacy Considerations.

Friday, June 14, 2019

Geeky jokes about demography, statistics, epidemiology, and census

I post a #GeekJoke on Twitter (almost) every Friday afternoon.
Here are a few recent favorite demographer jokes, statistician jokes, census jokes, and even a an epidemiology joke...

Demographer, to therapist: "I started to count every single person I saw, but eventually I lost my census."


(scene: therapists office)
Therapist: So tell me why you're here?
New patient: I'm a math teacher. I have problems.


At my last job interview, I told my interviewer that I plan to give 110%.
Unfortunately, I was applying to be a statistician.


(Scene: Two neighbors having a chat)
Neighbor 1: How's your husband doing?
Neighbor 2, a statistician: That depends. What's the reference group?


SAS is user friendly. It’s just selective about who its friends are.


Teen: Hey mom, I talked to my guidance counselor today, and I know what I want to do for a job.
Mom: Great, honey, what did you choose?
Teen: Demography. It's the only career that counts.


Researcher 1: Shouldn't you be pooling across years to increase sample size?
Researcher 2 (glares from under fedora): No! This is small batch, artisanal data.


I changed my password to "incorrect."
So whenever I forget my password, my computer will remind me: "Your password is incorrect."


Genealogists are sometimes confused, but eventually they come to their census.


An infectious disease walks into a bar...
Bartender: We don't serve your kind here. Get out!
Disease: Well you're not a very good host!


P-hacking is the only way I've been able to find a significant other.


Why shouldn't you argue with a decimal?
Decimals always have a point.

Friday, April 19, 2019

FactFinder is dead! Long live data.census.gov!

Did you know... 
American FactFinder is going away and will be replaced by data.census.gov

If you've been working with Census Bureau data for many years (as some of us have), you'll recall how much fun (it was fun, right?) we had with the first iteration of FactFinder. But eventually CB worked out the kinks and we all grew to know and love (it's love, right?) the interface.

So this swap to a new system feels like a little bit of history repeating. We data users will probably pull out our hair for awhile, bemoan the loss of a familiar system, gripe about the new platform early and often... Then eventually we'll figure out the new tricks, and one day we'll realize this "new thing" has become the "old, familiar thing."

And that transition starts now.

2018 ACS data will NOT be loaded into AFF, so if you need new data, your choices will be data.census.gov or the API.

Here's a helpful video on how to us the new system: