Georg Rasch used the term "specific objectivity" to describe that case essential to measurement in which "comparisons between individuals become independent of which particular instruments -- tests or items or other stimuli -- have been used. Symmetrically, it ought to be possible to compare stimuli belonging to the same class -- measuring the same thing -- independent of which particular individuals, within a class considered, were instrumental for comparison." (1980 p. xx).
Local objectivity is the term used to designate the case in which relative measures are empirically discovered to be independent of which instrument is actually used to take the measures. Local objectivity is a consequence of a set of data fitting the Rasch model. When data fit, differences among person measures and among item calibrations are independent of one another, and hence of the sampling of items and persons. Fit means that any two items can be shown always to differ by a statistically equivalent amount no matter which sample of persons actually respond to the items. Similarly, any two persons can be shown always to differ by the a statistically equivalent amount, no matter which sample of items is used to implement the measurement procedure. Consequently, when data fit the Rasch model, then the relative locations of persons and items on the underlying continuum for a construct are independent of their sampling. Absolute measures can only be obtained indirectly by introducing some reference persons or reference items of specified absolute measure into the analysis.
Since local objectivity is empirically based, it can only be statistically confirmed by further sampling. Sampled results may imply a promising variable -- promising because it spaces items into a useful substantive hierarchy of "meaningful moreness". Results may encourage, even confirm, a strong intention of how items "ought to" order. But the numerical specifics of the item difficulties are estimates form this sample of persons. They may turn out, on further sampling, to be statistically reproducible, but their quantities cannot be deduced other than by reference to empirical data.
An ideal, approximated by instruments in physics and chemistry, is that absolute calibration of an instrument, such as a thermometer, does not require the services of an object or another instrument. Further the location of an object on, say, the Celsius scale, is not instrument dependent, i.e., any "thermometer" will do. Neither does that location depend on measuring any other object. Temperature theory is well enough developed that thermometers can be constructed and calibrated without reference to any object or any other thermometer. Measurement of the temperature of two objects results in not just instrument independence for the difference between their temperatures, but also instrument independence for the amount of each object's temperature measure.
Absolute measures are obtained directly when a specification equation, which implements a theory, calibrates instruments with useful and reproducible precision. The instrument calibrations are then based, not on the measurement of any objects, but on the design and efficiency of the specification equation.
The term general objectivity is reserved for the case in which absolute measures (i.e., amounts) are independent of which instrument (within a class considered) is employed, and no other object is required. By "absolute" we mean the measure "is not dependent on, or without reference to, anything else; not relative" (Webster 1972).
The Table compares local and general objectivity. "The difference between local and general objectivity is seen not to be a consequence of the fundamental natures of the social and physical sciences, nor to be a necessary outcome of the method of making observation, but to be entirely a matter of the level of theory underlying the construction of the particular measurement instruments." (Stenner, 1990).
|Anatomy of Objectivity|
|Aspect||Local objectivity||General objectivity|
|Data||sampled, exploratory, effects unknown||constructed, specified, effects known|
|Construct Definition||incomplete, data-discovered||complete, theory-specified|
|Observations||quantified by data-based inference||quantified by theory-based specification|
|Origin, Unit, Precision||sample-estimated, varies||theory-specified, fixed|
|Calibrations||sample-estimated differences||theory-specified amounts|
|Misfit Diagnosis||depends on person and item sampling||construct consistency|
|Measures||sample-estimated differences||theory-calculated amounts|
|Misfit Diagnosis||item-by-person confounded||person-specific|
|Criterion||implied by sampled items||defined by theory|
|Norms||sample and test specific||general to the scale|
|Meta-analyses||aggregates indices of relative effects||aggregates amounts in measured units|
|Test Costs||person/item sampling, many iterations, expert supervision & evaluation||person and item targeting, routine review|
|Equating & Banking||sampled from common persons or items||pre-specified by common theory|
|Quality Control||expert evaluation, person-by-item confounding||pre-designed routine|
Specific objectivity - local and general. Stenner AJ. Rasch Measurement Transactions, 1994, 8:3 p.374
|Rasch Measurement Transactions (free, online)||Rasch Measurement research papers (free, online)||Probabilistic Models for Some Intelligence and Attainment Tests, Georg Rasch||Applying the Rasch Model 3rd. Ed., Bond & Fox||Best Test Design, Wright & Stone|
|Rating Scale Analysis, Wright & Masters||Introduction to Rasch Measurement, E. Smith & R. Smith||Introduction to Many-Facet Rasch Measurement, Thomas Eckes||Invariant Measurement: Using Rasch Models in the Social, Behavioral, and Health Sciences, George Engelhard, Jr.||Statistical Analyses for Language Testers, Rita Green|
|Rasch Models: Foundations, Recent Developments, and Applications, Fischer & Molenaar||Journal of Applied Measurement||Rasch models for measurement, David Andrich||Constructing Measures, Mark Wilson||Rasch Analysis in the Human Sciences, Boone, Stave, Yale|
|in Spanish:||Análisis de Rasch para todos, Agustín Tristán||Mediciones, Posicionamientos y Diagnósticos Competitivos, Juan Ramón Oreja Rodríguez|
|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|
|Feb. 28 - June 18, 2022, Mon.-Sat.||On-line course: Introduction to Classical and Rasch Measurement Theories (D. Andrich, I. Marais, RUMM), The Psychometric Laboratory at UWA, Australia|
|Feb. 28 - June 18, 2022, Mon.-Sat.||On-line course: Advanced Course in Rasch Measurement Theory (D. Andrich, I. Marais, RUMM), The Psychometric Laboratory at UWA, Australia|
|May 20 - June 17, 2022, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com|
|June 24 - July 22, 2022, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Further Topics (E. Smith, Winsteps), www.statistics.com|
|Aug. 12 - Sept. 9, 2022, Fri.-Fri.||On-line workshop: Many-Facet Rasch Measurement (E. Smith, Facets), www.statistics.com|
|Oct. 7 - Nov. 4, 2022, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com|
|June 23 - July 21, 2023, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Further Topics (E. Smith, Winsteps), www.statistics.com|
|Aug. 11 - Sept. 8, 2023, Fri.-Fri.||On-line workshop: Many-Facet Rasch Measurement (E. Smith, Facets), www.statistics.com|
The URL of this page is www.rasch.org/rmt/rmt83e.htm