What is a "correct" measure in the presence of disturbing influences (biases)? The answer depends on the goal of the researcher. If the goal is to create reproducible measures, measures which are the same from one testing situation to another, the "correct" measure is the unbiased one - so long as all measures are subject to the same iterative process of removing biases and misfits. If the goal is to describe the outcome of a particular testing situation, the biased measure is more reflective of what actually happened.
This was crucial during a recent analysis of data compression methods for audio samples. In the Figure below, the "biased" measure for each data compression "Codec" is the measure produced by the complete data. The "unbiased" measure is produced by omitting idiosyncratic portions of the data. Notice that the measure for Codec 4 changes substantially relative to the others depending on whether biased data are included. Which is the "correct" measure of Codec 4?
Approximately 75% of the drop in Codec 4 is due to an interaction with one audio sample featuring percussion. It performed consistently on the other samples. This identified for removal a technical error that caused the percussion interaction. Thus, even though the observed data produce the "biased" measure, the "correct" measure for future development is the "unbiased" one!
Mark Moulton
Biased or unbiased measures.Moulton M. Rasch Measurement Transactions, 1998, 12:3 p. 649.
Forum | Rasch Measurement Forum to discuss any Rasch-related topic |
Go to Top of Page
Go to index of all Rasch Measurement Transactions
AERA members: Join the Rasch Measurement SIG and receive the printed version of RMT
Some back issues of RMT are available as bound volumes
Subscribe to Journal of Applied Measurement
Go to Institute for Objective Measurement Home Page. The Rasch Measurement SIG (AERA) thanks the Institute for Objective Measurement for inviting the publication of Rasch Measurement Transactions on the Institute's website, www.rasch.org.
Coming Rasch-related Events | |
---|---|
Oct. 4 - Nov. 8, 2024, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
Jan. 17 - Feb. 21, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
May 16 - June 20, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
June 20 - July 18, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Further Topics (E. Smith, Facets), www.statistics.com |
Oct. 3 - Nov. 7, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
The URL of this page is www.rasch.org/rmt/rmt123b.htm
Website: www.rasch.org/rmt/contents.htm