TY - JOUR
T1 - Exploring Interrelationships Among L2 Writing Subskills
T2 - Insights from Cognitive Diagnostic Models
AU - Ravand, Hamdollah
AU - Effatpanah, Farshad
AU - Ma, Wenchao
AU - de la Torre, Jimmy
AU - Baghaei, Purya
AU - Kunina-Habenicht, Olga
N1 - Publisher Copyright:
© 2024 Taylor & Francis Group, LLC.
PY - 2024
Y1 - 2024
N2 - The purpose of this study was to explore the nature of interactions among second/foreign language (L2) writing subskills. Two types of relationships were investigated: subskill–item and subskill–subskill relationships. To achieve the first purpose, using writing data obtained from the writing essays of 500 English as a foreign language (EFL) students, the fit of the G-DINA model as general cognitive diagnostic model (CDM) was compared against a Wald-selected model (i.e., a model in which different CDMs such as DINA, DINO, A-CDM, LLM, and RRUM were selected for each item). To study cross-subskill impacts, two-way interactions between the subskills were estimated, and lens and scatter plots were checked. Subskill–item relationships showed that the subskills of L2 writing contribute additively and independently to the probability of successful performance. Furthermore, the loglinear analysis revealed that some of the subskills draw information from the other subskills. The plots showed that neglecting inter-subskill relationships would lead to misclassification of students.
AB - The purpose of this study was to explore the nature of interactions among second/foreign language (L2) writing subskills. Two types of relationships were investigated: subskill–item and subskill–subskill relationships. To achieve the first purpose, using writing data obtained from the writing essays of 500 English as a foreign language (EFL) students, the fit of the G-DINA model as general cognitive diagnostic model (CDM) was compared against a Wald-selected model (i.e., a model in which different CDMs such as DINA, DINO, A-CDM, LLM, and RRUM were selected for each item). To study cross-subskill impacts, two-way interactions between the subskills were estimated, and lens and scatter plots were checked. Subskill–item relationships showed that the subskills of L2 writing contribute additively and independently to the probability of successful performance. Furthermore, the loglinear analysis revealed that some of the subskills draw information from the other subskills. The plots showed that neglecting inter-subskill relationships would lead to misclassification of students.
UR - http://www.scopus.com/inward/record.url?scp=85209944980&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85209944980&partnerID=8YFLogxK
U2 - 10.1080/08957347.2024.2424550
DO - 10.1080/08957347.2024.2424550
M3 - Article
AN - SCOPUS:85209944980
SN - 0895-7347
VL - 37
SP - 329
EP - 355
JO - Applied Measurement in Education
JF - Applied Measurement in Education
IS - 4
ER -