Psychometric properties of a year-end form four chemistry paper 1 in selected schools in Petaling Utama District / Rose Enne Emellia Mohamed Razali

• Main Author: Rose Enne Emellia , Mohamed Razali
• Format: Thesis
• Published: 2020
• Subjects: LB1603 Secondary Education. High schools; Q Science (General)
• Online Access: http://studentsrepo.um.edu.my/15155/1/Rose_Enne_Emellia.pdf; http://studentsrepo.um.edu.my/15155/2/Rose_Enne_Emellia.pdf; http://studentsrepo.um.edu.my/15155/

The low-performance of science stream students in Chemistry especially in high-stakes testing, has alarmed the stakeholders. This problem has led to the need of analyzing the instruments used to measure the achievement of students. The present study examined the psychometric properties of multiple-choice questions in the Year-end Form Four Chemistry Paper 1 using the Rasch Model in the Klang Valley. A quantitative research design has been used for this study. The sample comprised of 435 Form Four Pure Science students from four randomly selected secondary schools in the Petaling Utama district. The Rasch analysis was conducted in two stages. The first stage was to prove that there was no violation of the unidimensionality assumption and the data fitness to the model. The second stage of the analysis focussed on the validity and reliability test paper. The Principal Component Analysis (PCA) result reveals that Chemistry Paper 1 was unidimensional. The raw variance measures observed by the data was almost equivalent to the raw variance of the model indicated the data set fitted the Rasch Model. Moreover, the eigenvalue of the first contrast showed a strength of 2 items which proved no secondary dimension existed in the Chemistry items. In terms of infit and outfit statistics, the results showed that all items are in the acceptable range. These comprehensive analyses demonstrated not only the fitness of the data set for the Rasch model but also supported the concept of unidimensionality. The dimension, however, was held only at a reasonably acceptable level. The unexplained variance in the first contrast of the data set signifies 3% of the noise level compared to the variance. This indicated that there were no residual factors in measuring the ability of the students. The local independence assumption was met and held across the Chemistry Paper 1 as residual correlations for each pair of test items were less than 0.7. This indicated no redundancy of the test items. In the second stage, estimates of reliability were 0.99 for items and 0.87 for persons with the separation index is 8.95 and 2.54 respectively. Thus, means that the ability of the students were efficiently distinguished and the items separation is broad. The person-item map exhibited that most of the test items measured students' abilities only in a specific range of measurement continuums. The Rasch statistical analysis by point measure correlation (PTMEA Corr.) established that all test items were positively correlated with the measured constructs and moved in one direction. Thus, there was no misfitting item. The result of the distractor analysis showed that all distractors of the test items were efficient. The DIF analysis examined the students’ answers based on the gender. It identified six items that were found to be difficult for the male students compared to the female students. In conclusion, the Year-end Form Four Examination of Chemistry Paper 1 instrument has good psychometric properties and is capable of producing valid and reliable scores to measure the achievement of the students. Besides that, the Year-end Form Four Chemistry Paper 1 instrument has the same standard as the actual Chemistry Paper 1 of Sijil Pelajaran Malaysia (SPM).