Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch Model
There is some debate in the psychometric literature about item parameter estimation in multistage designs. It is occasionally argued that the conditional maximum likelihood (CML) method is superior to the marginal maximum likelihood method (MML) because no assumptions have to be made about the trait...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Psych |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-8611/3/3/22 |
| _version_ | 1797517424963092480 |
|---|---|
| author | Jan Steinfeld Alexander Robitzsch |
| author_facet | Jan Steinfeld Alexander Robitzsch |
| author_sort | Jan Steinfeld |
| collection | DOAJ |
| description | There is some debate in the psychometric literature about item parameter estimation in multistage designs. It is occasionally argued that the conditional maximum likelihood (CML) method is superior to the marginal maximum likelihood method (MML) because no assumptions have to be made about the trait distribution. However, CML estimation in its original formulation leads to biased item parameter estimates. Zwitser and Maris (2015, <i>Psychometrika</i>) proposed a modified conditional maximum likelihood estimation method for multistage designs that provides practically unbiased item parameter estimates. In this article, the differences between different estimation approaches for multistage designs were investigated in a simulation study. Four different estimation conditions (CML, CML estimation with the consideration of the respective MST design, MML with the assumption of a normal distribution, and MML with log-linear smoothing) were examined using a simulation study, considering different multistage designs, number of items, sample size, and trait distributions. The results showed that in the case of the substantial violation of the normal distribution, the CML method seemed to be preferable to MML estimation employing a misspecified normal trait distribution, especially if the number of items and sample size increased. However, MML estimation using log-linear smoothing lea to results that were very similar to the CML method with the consideration of the respective MST design. |
| first_indexed | 2024-03-10T07:16:27Z |
| format | Article |
| id | doaj.art-729381a366a94fad9209c0aabc6ee3b8 |
| institution | Directory Open Access Journal |
| issn | 2624-8611 |
| language | English |
| last_indexed | 2024-03-10T07:16:27Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Psych |
| spelling | doaj.art-729381a366a94fad9209c0aabc6ee3b82023-11-22T15:01:15ZengMDPI AGPsych2624-86112021-07-013327930710.3390/psych3030022Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch ModelJan Steinfeld0Alexander Robitzsch1Differential Psychology and Psychological Assessment, Department of Developmental and Educational Psychology, Faculty of Psychology, University of Vienna, Liebiggasse 5, A-1010 Vienna, AustriaIPN—Leibniz Institute for Science and Mathematics Education, Olshausenstraße 62, D-24118 Kiel, GermanyThere is some debate in the psychometric literature about item parameter estimation in multistage designs. It is occasionally argued that the conditional maximum likelihood (CML) method is superior to the marginal maximum likelihood method (MML) because no assumptions have to be made about the trait distribution. However, CML estimation in its original formulation leads to biased item parameter estimates. Zwitser and Maris (2015, <i>Psychometrika</i>) proposed a modified conditional maximum likelihood estimation method for multistage designs that provides practically unbiased item parameter estimates. In this article, the differences between different estimation approaches for multistage designs were investigated in a simulation study. Four different estimation conditions (CML, CML estimation with the consideration of the respective MST design, MML with the assumption of a normal distribution, and MML with log-linear smoothing) were examined using a simulation study, considering different multistage designs, number of items, sample size, and trait distributions. The results showed that in the case of the substantial violation of the normal distribution, the CML method seemed to be preferable to MML estimation employing a misspecified normal trait distribution, especially if the number of items and sample size increased. However, MML estimation using log-linear smoothing lea to results that were very similar to the CML method with the consideration of the respective MST design.https://www.mdpi.com/2624-8611/3/3/22multistage testingRasch modelmarginal maximum likelihoodconditional maximum likelihoodparameter estimationlog-linear smoothing |
| spellingShingle | Jan Steinfeld Alexander Robitzsch Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch Model Psych multistage testing Rasch model marginal maximum likelihood conditional maximum likelihood parameter estimation log-linear smoothing |
| title | Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch Model |
| title_full | Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch Model |
| title_fullStr | Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch Model |
| title_full_unstemmed | Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch Model |
| title_short | Item Parameter Estimation in Multistage Designs: A Comparison of Different Estimation Approaches for the Rasch Model |
| title_sort | item parameter estimation in multistage designs a comparison of different estimation approaches for the rasch model |
| topic | multistage testing Rasch model marginal maximum likelihood conditional maximum likelihood parameter estimation log-linear smoothing |
| url | https://www.mdpi.com/2624-8611/3/3/22 |
| work_keys_str_mv | AT jansteinfeld itemparameterestimationinmultistagedesignsacomparisonofdifferentestimationapproachesfortheraschmodel AT alexanderrobitzsch itemparameterestimationinmultistagedesignsacomparisonofdifferentestimationapproachesfortheraschmodel |