Can IRT solve the missing data problem in test equating?
In this paper test equating is considered as a missing data problem. The unobserved responses of the reference population to the new test must be imputed to specify a new cutscore. The proportion of students from the reference population that would have failed the new exam and those having failed th...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2016-01-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fpsyg.2015.01956/full |
| _version_ | 1811238385652596736 |
|---|---|
| author | Maria eBolsinova Maria eBolsinova Gunter eMaris Gunter eMaris |
| author_facet | Maria eBolsinova Maria eBolsinova Gunter eMaris Gunter eMaris |
| author_sort | Maria eBolsinova |
| collection | DOAJ |
| description | In this paper test equating is considered as a missing data problem. The unobserved responses of the reference population to the new test must be imputed to specify a new cutscore. The proportion of students from the reference population that would have failed the new exam and those having failed the reference exam are made approximately the same. We investigate whether item response theory (IRT) makes it possible to identify the distribution of these missing responses and the distribution of test scores from the observed data without parametric assumptions for the ability distribution. We show that while the score distribution is not fully identifiable, the uncertainty about the score distribution on the new test due to non-identifiability is very small. Moreover, ignoring the non-identifiability issue and assuming a normal distribution for ability may lead to bias in test equating, which we illustrate in simulated and empirical data examples. |
| first_indexed | 2024-04-12T12:41:58Z |
| format | Article |
| id | doaj.art-adfd6eb5ada746758364219e2b4a58d6 |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-04-12T12:41:58Z |
| publishDate | 2016-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-adfd6eb5ada746758364219e2b4a58d62022-12-22T03:32:46ZengFrontiers Media S.A.Frontiers in Psychology1664-10782016-01-01610.3389/fpsyg.2015.01956153826Can IRT solve the missing data problem in test equating?Maria eBolsinova0Maria eBolsinova1Gunter eMaris2Gunter eMaris3Utrecht UniversityDutch National Institute for Educational Measurement (Cito)Dutch National Institute for Educational Measurement (Cito)University of AmsterdamIn this paper test equating is considered as a missing data problem. The unobserved responses of the reference population to the new test must be imputed to specify a new cutscore. The proportion of students from the reference population that would have failed the new exam and those having failed the reference exam are made approximately the same. We investigate whether item response theory (IRT) makes it possible to identify the distribution of these missing responses and the distribution of test scores from the observed data without parametric assumptions for the ability distribution. We show that while the score distribution is not fully identifiable, the uncertainty about the score distribution on the new test due to non-identifiability is very small. Moreover, ignoring the non-identifiability issue and assuming a normal distribution for ability may lead to bias in test equating, which we illustrate in simulated and empirical data examples.http://journal.frontiersin.org/Journal/10.3389/fpsyg.2015.01956/fullitem response theorymissing dataNon-identifiabilityincomplete designmarginal Rasch modeltest equating. |
| spellingShingle | Maria eBolsinova Maria eBolsinova Gunter eMaris Gunter eMaris Can IRT solve the missing data problem in test equating? Frontiers in Psychology item response theory missing data Non-identifiability incomplete design marginal Rasch model test equating. |
| title | Can IRT solve the missing data problem in test equating? |
| title_full | Can IRT solve the missing data problem in test equating? |
| title_fullStr | Can IRT solve the missing data problem in test equating? |
| title_full_unstemmed | Can IRT solve the missing data problem in test equating? |
| title_short | Can IRT solve the missing data problem in test equating? |
| title_sort | can irt solve the missing data problem in test equating |
| topic | item response theory missing data Non-identifiability incomplete design marginal Rasch model test equating. |
| url | http://journal.frontiersin.org/Journal/10.3389/fpsyg.2015.01956/full |
| work_keys_str_mv | AT mariaebolsinova canirtsolvethemissingdataproblemintestequating AT mariaebolsinova canirtsolvethemissingdataproblemintestequating AT gunteremaris canirtsolvethemissingdataproblemintestequating AT gunteremaris canirtsolvethemissingdataproblemintestequating |