Students' error profiles in solving statistical problems based on Newman's error analysis

Abstract

Many students experience difficulties when solving statistical problems, indicating the need for further research to address these issues. The purpose of this study is to identify the types of errors students make and the factors contributing to these errors. The error types in this study are analyzed using Newman's Error Analysis (NEA), which includes reading and decoding errors, comprehension errors, transformation errors, process skill errors, and encoding errors. This study employs a qualitative method with six ninth-grade students as research subjects. Data were collected through tests, interviews, and documentation. A purposive sampling technique was employed, and the data were analyzed using Miles and Huberman's data analysis model. The results show that students with low cognitive ability committed comprehension errors, while students with medium and high cognitive ability did not. Process skill errors and encoding errors occurred among students across all cognitive ability levels—high, medium, and low. The factors contributing to these errors include limited literacy skills, lack of student accuracy, and the influence of previous errors.