A model for predicting achievement in statistics courses /
This study aims to identify the predictors of achievement in statistics courses (ASC) among undergraduate students. The central issue addressed in this study is the low performance among social sciences students in statistics courses. Consequently, the students have difficulties in dealing with more...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Islamic Revealed Knowledge and Human Sciences, International Islamic University Malaysia,
2018
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study aims to identify the predictors of achievement in statistics courses (ASC) among undergraduate students. The central issue addressed in this study is the low performance among social sciences students in statistics courses. Consequently, the students have difficulties in dealing with more advanced courses such as a Final Year Project. Both quantitative and qualitative studies were carried out to identify the predictors of achievement in statistics courses (ASC) among undergraduate students. This study tests an ASC model and examines its invariance with regards to ethnicity, in specific, the Malay and Chinese. The study adopts a structural equation modelling (SEM) analysis in examining the predictors of the ASC model. It involves three phases: initial preparation, exploratory study, and model testing (main study). A total of 415 undergraduates participated across the three phases (n=28, n=109, n=278 respectively). Data from the main study (n=278) were subjected to model testing involving both measurement and structural models. Based on the model fit measures (data-driven approach), the Chiesi and Primi's (2010) ASC model was selected and used as the framework for model testing. There are five variables predicting ASC in the model: attitudes towards statistics (post-course); mathematics knowledge: statistics anxiety; attitudes towards statistics (pre-course); and mathematics background. Results from the model testing phase indicate that the final model achieved the minimum requirements for a model fit (Normed χ2=2.1, CFI=.975, RMSEA=.063, TLI=.959). The final model of ASC contains two significant predictors: mathematics knowledge and mathematics background. These two predictors have a positive direct effect on ASC. Three variables in the original framework (Chiesi & Primi, 2010) were found to be non-significant predictors of ASC: statistics anxiety, attitudes towards statistics (pre-course), and attitudes towards statistics (post-course). With regards to ethnicity invariance, the analysis was performed at two levels: the model level for an overall analysis and the path level for a specific causal relationship analysis. Both Malay and Chinese ethnic groups did not show any difference at the model level. However, there were differences at the path level. The relationship between mathematics background and ASC was stronger for the Chinese as compared to the Malays, while, the relationship between mathematics background and mathematics knowledge was stronger for the Malays as compared to the Chinese. The study has two important implications. Theoretically, the findings extend the model developed by Chiesi and Primi (2010) regarding predictors of ASC. A new causal relationship was found between mathematics background and ASC. Practically, since mathematics factors were found to significantly predict ASC, an early assessment of mathematics competency can be conducted during the first week of a statistics course to gauge students' abilities in statistics. Further discussion on the implications of the findings and future research was also provided. |
|---|---|
| Physical Description: | xiii, 136 leaves : illustrations ; 30cm. |
| Bibliography: | Theses, IIUM local |