eli knaap
banner
knaaptime.com
eli knaap
@knaaptime.com
urban planning & public policy prof @ UC Irvine | core dev @ PySAL & QuantEcon | urban social science & spatial data science | open source

https://knaaptime.com
often people resort to 'data driven neighborhoods', i.e. geodemographics or regionalization algos where 'neighborhood' means an area of relative homogeneity across many social indicators--but thats not really the same as officially demarcated boundaries. Maybe see oturns.github.io/geosnap-guide/
A Guide to Geosnap
oturns.github.io
November 9, 2025 at 11:27 PM
depends on what you mean by "actual neighborhoods". Usually there's no such thing. There are special cases like chicago or pittsburgh where 'neighborhood' means something historically so there are established boundaries but in most places there's no "real" delineation (so no official data to draw)
November 9, 2025 at 11:24 PM
(that said, still very proud of california for having opportunity analysis part of the formal policymaking process)
November 2, 2025 at 11:48 PM
unfortunately, however, due to the Guy's Paradox, your Guy is likely to have more Guys than you
October 14, 2025 at 3:30 AM
also it would've been a riot had one of the senators called her on this in the moment. especially since it was kinda obvious what she was doing

"...are you reading from a set of prepared insults instead of answering the question? You're not equipped to even remember the insults?"
October 8, 2025 at 5:11 AM
😆
October 8, 2025 at 4:42 AM
is central time as a base gonna help, or destroy you? I have a miserable time going east these days. If you're in the middle i can imagine the marginal change being mildly easier unless you have big swings
October 8, 2025 at 4:30 AM
dude good luck
October 8, 2025 at 4:20 AM
yep. imperfect data but it's got the smoothness @stephenjacobsmith.com was expecting; definitely looks like a rent distribution

admittedly a bit surprised by the result!
October 7, 2025 at 8:39 PM
gotcha. still the shape is a bit different? and my weighted median is still lower *without* the zeros?
October 7, 2025 at 8:31 PM
(this is specific to *"market rate"* 3br in brooklyn [by unit, not person], so the downward skew isnt from rent control or some other subsidy)

would be very curious to see the original code
October 7, 2025 at 7:46 PM
extremely quick and dirty, but ignoring the survey weights, you can basically recreate these numbers from NYCHVS in ~9 lines. Only gives you 138 observations and the histogram is a little different (original seems to include $0? among a few other diffs), but the 2300 number shows up, fwiw.
October 7, 2025 at 7:42 PM
Reposted by eli knaap
Yeah. Fuck Penn State.
October 6, 2025 at 4:57 AM