Steven Ruggles Profile picture
Jul 1, 2021 10 tweets 2 min read Read on X
It has now become clear that the 2020 Census will not provide block-level statistics usable for planning or research./1 Image
Newly-published data reveal that the Census Bureau has increased the "noise" added to the data at the block level, compared with the demonstration data released in April./2
census.gov/programs-surve…
That data was already highly problematic, but the new data the Census Bureau plans to release is even worse. For example, in 303,000 blocks there are fewer people than occupied housing units./3
There are 504,000 blocks where people live bit there are no occupied housing units! /4
Conversely, there are 149,000 blocks where there are occupied households but there is zero population living on the block./5
My favorite is the Lord of the Flies blocks, populated by children with zero adults present. The current files has 164,000 of those, compared with just 91,000 in the April version of the data./6
As I noted last April, Liberty Island in New York Harbor is a census block with just two people, but the April demonstration file reported it as having 48 or 72 persons, depending on the version./7
The released block data for 2020 is certain to be even worse. It would be better to simply get rid of block data altogether than to put out junk that will be misinterpreted./8
This loss is a sad, unforced error based on a gross exaggeration of the risk posed by tabular data./end
assets.ipums.org/_files/mpc/wp2… Image
The actual data, of course, has zero Lord of the Flies blocks.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Steven Ruggles

Steven Ruggles Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @HistDem

Apr 30, 2022
The Census Bureau has been struggling ever since it started outsourcing operations to defense contractors in the 1990s, as @dldmag and I argued in our 2020 article on institutional change in the Bureau. The 2000 and 2010 censuses were near disasters. 1/4 academic.oup.com/jah/article/10… Image
The 2020 census faced special challenges stemming from both the pandemic and from Trump’s attempt to add a citizenship question at the last minute. But as @dldmag and I argued, “The greatest concern for the 2020 census is the potential for information technology failure.” 2/4
We were prescient. The Bureau can’t figure out the software needed to combine the housing and population data while simultaneously supporting their new disclosure control policies. This will delay by at least two years release of detailed statistics. 3/4
nytimes.com/2022/04/29/us/…
Read 4 tweets
Aug 24, 2021
In our new open-access research brief, @dcvanriper and I argue that the emperor is buck naked. 1/x
rdcu.be/cvT26
The Census Bureau plans a new approach to disclosure control for the 2020 census that will add noise to every statistic the agency produces for places below the state level. /2
The new approach, known as differential privacy, “marks a sea change for the way that official statistics are produced and published.” /3
Read 35 tweets
Aug 18, 2021
The town of Carrollton, Mississippi won the Differential Privacy lottery! They really have somewhere in the neighborhood of 175 people, but the 2020 Census "counted" over twice as many, 423! /1 thetaxpayerschannel.org/news.php?news_…
The discrepancy is mostly due to one block, where there are no households but 214 persons. The only building on the block is the courthouse, and nobody lives there. /2
The cause of the error could be the new disclosure control system called Differential Privacy, or perhaps to a mysterious new system of Group Quarters Count Imputation. /3
Read 7 tweets
Aug 18, 2021
The town of Carrollton, Mississippi won the Differential Privacy lottery! They really have somewhere in the neighborhood of 175 people, but the 2020 Census "counted" over twice as many, 423! /1
thetaxpayerschannel.org/news.php?news_…
The discrepancy is mostly due to one block, where there are no households but 214 persons. The only building on the block is the courthouse, and nobody lives there. /2
Of course, for every town that wins the lottery and doubles its population due to differential privacy, there will be a loser that is missing half its population in the official count. /3
Read 5 tweets
Aug 16, 2021
The Census Bureau adopted a global privacy budget of ε=19.61 for the PL-94-171 redistricting data file. What does that imply?
According to differential privacy co-inventor @frankmcsherry it means that the Census Bureau privacy protections are pointless.
In a 2017 article in Wired Magazine, @frankmcsherry criticized Apple for using an epsilon of 14. "Apple has put some kind of handcuffs on in how they interact with your data," he says. "It just turns out those handcuffs are made out of tissue paper."
wired.com/story/apple-di…
Read 6 tweets
Jul 30, 2021
Newly-available data show that the 2020 Census will be the worst ever with respect to one key metric: Item Non Response (INR), which occurs when people are counted but the census does not capture their characteristics. This graph compares INR in 2010 and 2020 for sex and age. /1
These graphs were obtained through a recent FOIA request and appeared in a court filing last week (1:21-cv-01361-ABJ). DRF1 (Decennial Response File 1) is the raw data, and DRF2 has the duplicates removed. Here are the INR graphs for Hispanic Origin and Race. /2
In most cases non-response is running between 10% and 20% in 2020. In past censuses going back at least 170 years, non-response on these questions averages from 1% to 3%. Here is the graph for family relationship and housing tenure (home owned or rented). /3
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(