Selection Strategies for Bivariate Loglinear Smoothing Models and Their Effects on NEAT Equating Functions NEAT
- Author(s):
- Moses, Tim P.; Holland, Paul W.
- Publication Year:
- 2009
- Report Number:
- RR-09-04
- Source:
- ETS Research Report
- Document Type:
- Report
- Page Count:
- 31
- Subject/Key Words:
- Loglinear Smoothing, Selection Strategies, Equating, Non-Equivalent-Groups Anchor Test (NEAT) Design
Abstract
The results showed that selection strategies differ in terms of their tendencies to select complex versus simple bivariate parameterizations and that the strategies that tended to select more complex parameterizations (i.e., Pearson and Cressie-Read chi-squares) usually produced the least biased and most variable equating functions.
Read More
- Request Copy (specify title and report number, if any)
- http://dx.doi.org/10.1002/j.2333-8504.2009.tb02161.x