Neil Dorans ColloquiumThursday, November 19, 2015 - 2:45pm
Statistics Department Colloquium
Where: Close-Hipp Building, Room 364
Speaker: Neil Dorans
Affiliation: Educational Testing Services
Title: Linking Outcomes Obtained from Multiple Instruments
Abstract: When the outcomes of assessment instruments are to be used interchangeably, these outcomes need to be equated or made comparable. If the outcomes of different assessment instruments are not equated, inferences based on them could be flawed, and might have serious consequences such as misperceptions about the efficacy of a treatment. It would be nice if outcomes were comparable as a result of careful instrument design. In reality, some type of statistical intervention is often needed to check for comparability and to make adjustments if necessary.
This presentation, which will be conceptual in nature and hence light on the mathematics, will address key questions associated with the linking of outcomes. What is meant by outcome linking and equating? How does equating differ from other types of linking? What are common data collection designs used to capture data for outcomes linking? What are some of the standard statistical procedures used to link outcomes? What assumptions do they make? What procedures can be used to assess whether outcomes can be used interchangeably?