期刊名称：International Journal of Assessment Tools in Education
电子版ISSN：2148-7456
出版年度：2019
卷号：6
期号：2
页码：300-313
DOI：10.21449/ijate.534118
语种：English
出版社：International Journal of Assessment Tools in Education
摘要：In the literature,response style is one of the factors causing an achievement-attitude paradox and threatens the validity of the results obtained from studies.In this regard,the aim of this study is two-fold.Firstly,it attempts to determine which item response tree (IRTree) models based on the generalized linear mixed model (GLMM) approach (random intercept,random intercept with fixed effect of extreme response and random intercept-slope model) best fit the Trends in International Mathematics and Science Study (TIMSS) 2015 data.Secondly,it purports to explore how the extreme response style affects students’ attitudes toward mathematics of students.This study is both basic research and descriptive research in terms of seeking for answers for two different research questions.For the sample of this research,15 countries were randomly selected among countries participated in TIMSS 2015.The students’ responses to items measuring attitude in the student questionnaire were analyzed with the packages “lme4” and “irtrees” in R software.When the model fit indices were evaluated,the random intercept-slope model was found to be the best fit to the data.According to this model,the extreme response style explains a significant amount of variances in the students’ attitude toward mathematics.Additionally,students with a negative attitude toward mathematics were found to have an extreme response style.It was concluded that an extreme response style had an effect on students’ attitude.
