I am forwarding this message as this may be of interest to Polmethers:

--- Title: rpms: An R Package for Modeling Survey Data with Regression Trees ---

Date/Time: Wednesday, March 8, 2017, 12:00 – 1:30 PM (ET)
Location: Bureau of Labor Statistics Conference Center, Room 9
(Please email [log in to unmask] to RSVP; see more location and call-in details below)

Speakers: Daniell Toth, Bureau of Labor Statistics 
Sponsor: WSS Methodology Section

Abstract: In this presentation, we introduce the R package rpms (Recursive Partitioning for Modeling Survey Data). The main function rpms fits a linear model to the data conditionally on variables selected through recursively partitioning. This application of recursive partitioning produces design consistent regression tree models of survey data with one-stage designs, accounting for any stratification and clustering, as well as unequal probability of selection. We test the properties of the algorithm using samples from a simulated population dataset and demonstrate it by modeling household level data from the U.S. Bureau of Labor Statistics’ Consumer Expenditure survey. These applications demonstrate the easily interpretable structure and the ability of regression trees to handle large data sets with complex associations among the variables.

Location:  To be placed on the seminar attendance list at the Bureau of Labor Statistics, you need to e-mail your name, affiliation, and seminar name to [log in to unmask] (underscore after 'wss') by noon at least two days in advance of the seminar. Please bring a photo ID to the seminar. BLS is located at 2 Massachusetts Avenue, NE. Use the Red Line to Union Station. Parking in the area of BLS is available at Union Station. For parking information see http://www.unionstationdc.com/parking. No validation is available from BLS for reduced parking rates.

 

WebEx: WebEx event address:
https://dol.webex.com/dol/j.php?MTID=mce6739c8bcff1244803ff27a74879dbe
Note: Particular computer configurations might not be compatible with WebEx.

For audio:
   Call-in toll-free number (Verizon): 1-866-865-9536  (US)
   Call-in number (Verizon): 1-517-966-0857  (US)
   Attendee access code: 744 124 3

 

 

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 
Eric Plutzer 
Editor, Public Opinion Quarterly 
Professor of Political Science, Penn State University

**************************************************************
               Political Methodology E-Mail List
   Editors: Jonathan Homola  <[log in to unmask]>
               Michelle Torres     <[log in to unmask]>
**************************************************************
     Send messages to [log in to unmask]
  To join the list, cancel your subscription, or modify
                 your subscription settings visit:

  https://www.cambridge.org/core/membership/spm/mailing-list

**************************************************************