Developing a Common Metric in Item Response Theory

Stocking, Martha L.; Lord, Frederic M.

doi:10.1177/014662168300700208

Cited by 561 publications

(170 citation statements)

References 3 publications

Supporting

Mentioning

154

Contrasting

Unclassified

Order By: Relevance

“…24 In this process, the 5 to 10 conserved questions acted as anchor points. The IRT equate software first compared the calculated IRT question parameters for each year on these particular questions.…”

Section: Irt Equating Methodsmentioning

confidence: 99%

How we have used Item Response Theory and Classroom Management to improve student success rates in large General Chemistry classes

Casselman¹,

Ohlsen²,

Atwood³

2017

Quim. Nova

View full text Add to dashboard Cite

Since 2012 we have tracked general chemistry student success rates at the University of Utah. In efforts to improve those rates we have implemented math prerequisites, changed our discussion session format, installed some metacognitive exercises aimed at the lowest quartile of students and instituted a flipped classroom model. Furthermore, using Item Response Theory we have identified what topics each individual student struggles with on practice tests. These steps have increased our success rates to ~76%. As well, student performance on nationally normed American Chemical Society final exams has improved to a median of 86 percentile. Our lowest quartile of students in spring 2016 scored at the 51 st percentile, above the national median.

show abstract

Section: Irt Equating Methodsmentioning

confidence: 99%

How we have used Item Response Theory and Classroom Management to improve student success rates in large General Chemistry classes

Casselman¹,

Ohlsen²,

Atwood³

2017

Quim. Nova

View full text Add to dashboard Cite

show abstract

“…Lord continued to contribute to IRT methodology with works by himself as well as coauthoring works dealing with unbiased estimators of ability parameters and their parallel forms reliability (1983d), a four-parameter logistic model (Barton and Lord 1981), standard errors of IRT equating (1982), IRT parameter estimation with missing data (1983a), sampling variances and covariances of IRT parameter estimates (Lord and Wingersky 1982), IRT equating (Stocking and Lord 1983), statistical bias in ML estimation of IRT item parameters (1983c), estimating the Rasch model when sample sizes are small (1983b), comparison of equating methods , reducing sampling error , conjunctive and disjunctive item response functions (1984), ML and Bayesian parameter estimation in IRT (1986), and confidence bands for item response curves with Pashley (Lord and Pashley 1988).…”

Section: Further Developments and Evaluation Of Irt Modelsmentioning

confidence: 99%

Item Response Theory

Carlson

Davier

2017

Methodology of Educational Measurement and Assessment

View full text Add to dashboard Cite

Item response theory (IRT) models, in their many forms, are undoubtedly the most widely used models in large-scale operational assessment programs. They have grown from negligible usage prior to the 1980s to almost universal usage in largescale assessment programs, not only in the United States, but in many other countries with active and up-to-date programs of research in the area of psychometrics and educational measurement.Perhaps the most important feature leading to the dominance of IRT in operational programs is the characteristic of estimating individual item locations (difficulties) and test-taker locations (abilities) separately, but on the same scale, a feature not possible with classical measurement models. This estimation allows for tailoring tests through judicious item selection to achieve precise measurement for individual test takers (e.g., in computerized adaptive testing, CAT) or for defining important cut points on an assessment scale. It also provides mechanisms for placing different test forms on the same scale (linking and equating). Another important characteristic of IRT models is local independence: for a given location of test takers on the scale, the probability of success on any item is independent of that of every other item on that scale. This characteristic is the basis of the likelihood function used to estimate test takers' locations on the scale.Few would doubt that ETS researchers have contributed more to the general topic of IRT than individuals from any other institution. In this chapter we briefly review most of those contributions, dividing them into sections by decades of publication. Of course, many individuals in the field have changed positions between

show abstract

“…The item parameters for item j on Scale J are , , and ; the item parameters for item j on Scale I are , , and . Kim and Lee (2006) indicated that there are four scale linking methods which are applicable to mixed-format tests: the mean/sigma (Marco, 1977), mean/mean (Loyd & Hoover, 1980), Haebara (1980), and Stocking and Lord (1983). Mean/mean and mean/sigma methods are referred to as moment methods while the Haebara and, Stocking and Lord methods are referred to as characteristic curve methods (Kolen & Brennan, 2004).…”

Section: Irt Test Equatingmentioning

confidence: 99%

The Impact of Test Dimensionality, Common-Item Set Format, and Scale Linking Methods on Mixed-Format Test Equating

2016

EDUC SCI-THEOR PRACT

View full text Add to dashboard Cite

The purpose of this study was to examine the impact of dimensionality, common-item set format, and different scale linking methods on preserving equity property with mixed-format test equating. Item response theory (IRT) true-score equating (TSE) and IRT observed-score equating (OSE) methods were used under common-item nonequivalent groups design. The equity property was evaluated based on firstorder equity (FOE) and second-order equity (SOE) properties. A simulation study was conducted based on actual item parameter estimates obtained from the TIMSS 2011 8th grade mathematics assessment.The results showed that: (i) The FOE and SOE properties were best preserved under the unidimensional condition, were poorly preserved when the degree of multidimensionality was severe. (ii) The TSE and OSE results, which were provided by using a mixed-format common-item set, preserved FOE better compared to equating results, which provided only a multiple-choice common item set. (iii) Under the unidimensional and multidimensional test structure, characteristic curve methods performed significantly better than moment scale linking methods in terms of preserving FOE and SOE properties.

show abstract

Developing a Common Metric in Item Response Theory

Cited by 561 publications

References 3 publications

How we have used Item Response Theory and Classroom Management to improve student success rates in large General Chemistry classes

How we have used Item Response Theory and Classroom Management to improve student success rates in large General Chemistry classes

Item Response Theory

The Impact of Test Dimensionality, Common-Item Set Format, and Scale Linking Methods on Mixed-Format Test Equating

Contact Info

Product

Resources

About