Curb-stoning, a Too Neglected and Very Embarrassing Survey Problem
Date/Time: December 2nd, 2014, 12:30pm to 2:30pm
Panelists:
| Cathy Furlong | Statistics without Borders |
| Arthur Kennickell | Federal Reserve Board |
| Rodrick Marquette | Census Bureau |
| Jaki McCarthy | NASS |
| Ali Mushtaq | Consultant |
| Fritz Scheuren | NORC |
| Steve Koczela | MassINC Polling Group |
Event Materials
Chair: Nancy Bates, Census Bureau
Sponsor: WSS Methodology Section
Abstract:
Curb-stoning or fabrication has been the bane of surveying since, perhaps, its
inception. Re-interviews have traditionally been used to detect curb-stoners.
But large enough re-interview samples to have a reasonable power of detection
are expensive and may only reliably identify the most Flagrant forms. There is
a belief, by some, that newer preventive and detective techniques have helped.
But there is also a belief, by others, that, in some settings, matters may have
even gotten worse. Which is it?
The experts on the panel will each cover one aspect of this broad subject, starting with a recent paper published in September issue of the Statistical Journal of the IAOS. The paper by Peter Winker has, with his students, been simulating various fabrication scenarios. His focus has been on the rate of their detection and, to a lesser degree, on the consequences of undetected results being used at inference.
The session is longer than normal to give everyone plenty of time for discussion. The results will be recorded and a publication may follow in the IAOS Statistical Journal next year.
POC email: Scheuren@aol.com
WebEx event address for attendees: https://dol.webex.com/dol/j.php?MTID=m7c6d2d06d4c1218ce4f18f57dc1a89c7
For audio:
Call-in toll-free number (Verizon): 1-866-747-9048 (US)
Call-in number (Verizon): 1-517-233-2139
(US) Attendee access code: 938 454 2
