2016
DOI: 10.1177/0734282915623053
|View full text |Cite
|
Sign up to set email alerts
|

Application of a Cognitive Diagnostic Model to a High-Stakes Reading Comprehension Test

Abstract: General cognitive diagnostic models (CDM) such as the generalized deterministic input, noisy, “and” gate (G-DINA) model are flexible in that they allow for both compensatory and noncompensatory relationships among the subskills within the same test. Most of the previous CDM applications in the literature have been add-ons to simulation studies. Although there are some applications of CDMs such as the Fusion Model and the Rule Space Model to educational assessment data in general and second-language data in par… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

2
60
0
6

Year Published

2017
2017
2023
2023

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 74 publications
(84 citation statements)
references
References 54 publications
2
60
0
6
Order By: Relevance
“…Although it has been found in the CDM context that the LR test is relatively more robust than the W test (Sorrel et al, 2017), the current implementation of the LR test is very time consuming, given that it requires to calibrate many different models and compare them to the general model. For this reason, the W test is generally preferred (e.g., de la Torre et al, 2015;Ravand, 2016) and is the one implemented in the software available (e.g., the CDM and GDINA packages in R; Ma & de la Torre, 2016;Robitzsch, Kiefer, George, & Uenlue, 2016). In this work, we introduce an efficient approximation to the LR test, 2LR, based on a two-step estimation procedure under the G-DINA model framework originally introduced by de la .…”
Section: Discussionmentioning
confidence: 99%
“…Although it has been found in the CDM context that the LR test is relatively more robust than the W test (Sorrel et al, 2017), the current implementation of the LR test is very time consuming, given that it requires to calibrate many different models and compare them to the general model. For this reason, the W test is generally preferred (e.g., de la Torre et al, 2015;Ravand, 2016) and is the one implemented in the software available (e.g., the CDM and GDINA packages in R; Ma & de la Torre, 2016;Robitzsch, Kiefer, George, & Uenlue, 2016). In this work, we introduce an efficient approximation to the LR test, 2LR, based on a two-step estimation procedure under the G-DINA model framework originally introduced by de la .…”
Section: Discussionmentioning
confidence: 99%
“…Lee y Sawaki (2009) dispusieron una estructura más simple de atributos: Comprensión de detalles, conexión de ideas e inferencias. Intentos posteriores han identificado otros atributos, como: Vocabulario, sintaxis, extracción de información explícita y comprensión de información implícita (Li, Hunter, & Lei, 2015), los identificados por Ravand (2016): Lectura de detalles, lectura inferencial (inferencia), lectura de idea principal, sintaxis y vocabulario o los propuestos en el trabajo de Hemmati, Baghaei y Bemani (2016): Generación de inferencias, extracción de información explícita, identificación del significado de palabras de acuerdo al contexto, identificación de referencias pronominales y evaluación de opciones de respuesta. En todos estos casos, el paso siguiente a la identificación y selección inicial de las habilidades o atributos que permitieron explicar el desempeño en comprensión, fue la elección del modelo cognitivo más adecuado al constructo y los datos.…”
Section: Atributos Cognitivos En Comprensión De Lecturaunclassified
“…De acuerdo a estos autores, una decisión de importancia corresponde a la elección de un modelo compensatorio o no compensatorio, también llamado conjuntivo. Estos últimos han sido mucho más comunes en comprensión de lectura (Buck, Tatsuoka, & Kostin, 1997;Buck, Van Essen, Tatsuoka, Kostin, Lutz, & Phelps, 1998;Hemmati, Baghaei, & Bemani, 2016;Jang, 2009;Ravand, Barati, & Widhiarso, 2013;Ravand, 2016;von Davier, 2005). Algunos conocidos modelos de tipo no compensatorio son el Rule Space Model (Svetina, Gorin, & Tatsuoka, 2011;Tatsuoka, 2009), el Attributes Hierarchy Model o AHM (Wang & Gierl, 2011), el modelo Deterministic-Input, Noisy-And-Gate, DINA, el modelo Reparameterized Unified Model (RUM) o su sutil derivación, el Fusion Model (Jang, 2009) y el modelo Reduced Reparameterized Unified Model, o RRUM (Jang, 2009;Jang, Dunlop, Wagner, Kim, & Gu, 2013;Li, Hunter, & Lei, 2015), también reconocido como Noncompesatory Reparameterized Unified Model, NC-RUM (Ravand & Robitzsch, 2015).…”
Section: Modelos De Diagnóstico Cognitivo En Comprensión De Lecturaunclassified
See 2 more Smart Citations