INSTRUMEN DIAGNOSTIK SPLDV BERBASIS COGNITIVE DIAGNOSTIC MODEL
Abstract
The low mathematics achievement of Indonesian students in PISA 2022 highlights the need for assessment instruments that not only measure learning outcomes but also diagnose students’ learning difficulties in a detailed manner. This study aimed to develop a diagnostic instrument for Systems of Linear Equations in Two Variables (SPLDV) using a complex multiple-choice format to support data-driven instructional decisions. Content validity was evaluated by five experts using Aiken’s V. The instrument was tested through a pilot study involving 200 students and a field test with 960 eighth-grade students from Jakarta, West Java, and Banten. Data analysis employed Classical Test Theory (CTT), Item Response Theory using the Generalized Partial Credit Model (GPCM), and the Cognitive Diagnostic Model based on GDINA. The results indicated that the final instrument consisting of 13 items demonstrated strong content validity (Aiken’s V = 0.80–1.00) and good internal consistency (α = 0.829). GPCM analysis showed that the instrument provided optimal measurement information at low to moderate ability levels, while GDINA analysis confirmed accurate attribute specification, with all items achieving PVAF ≥ 0.95. The novelty of this study lies in the integration of a complex multiple-choice format with polytomous IRT and GDINA-based diagnostic analysis to generate detailed cognitive attribute profiles that are directly applicable for instructional diagnosis. Overall, the instrument is empirically valid, practically informative, and effective for supporting diagnostic assessment and differentiated instruction in SPLDV learning.
Rendahnya capaian literasi matematika siswa Indonesia pada PISA 2022 menunjukkan perlunya instrumen asesmen yang tidak hanya mengukur hasil belajar, tetapi juga mampu memberikan informasi diagnosis kesulitan belajar siswa secara rinci. Penelitian ini bertujuan mengembangkan instrumen diagnostik literasi matematika pada materi Sistem Persamaan Linear Dua Variabel (SPLDV) menggunakan format pilihan ganda kompleks dan Cognitive Diagnostic Model (CDM) berbasis Generalized Deterministic Input, Noisy “And” gate (GDINA). Validitas isi instrumen dievaluasi oleh lima pakar menggunakan koefisien Aiken’s V. Uji coba awal melibatkan 200 siswa kelas VIII, sedangkan uji lapangan melibatkan 960 siswa kelas VIII SMP di Jakarta, Jawa Barat, dan Banten. Analisis data dilakukan menggunakan Classical Test Theory (CTT), Item Response Theory dengan Generalized Partial Credit Model (GPCM), serta analisis diagnostik berbasis GDINA. Hasil penelitian menunjukkan bahwa instrumen final yang terdiri atas 13 butir memiliki validitas isi yang kuat (Aiken’s V = 0,80–1,00) dan reliabilitas yang baik (α = 0,829). Analisis GPCM menunjukkan bahwa instrumen memberikan informasi pengukuran optimal pada tingkat kemampuan rendah hingga sedang, sedangkan analisis GDINA mengonfirmasi ketepatan spesifikasi atribut kognitif dengan seluruh butir mencapai nilai PVAF ≥ 0,95. Kebaruan penelitian ini terletak pada integrasi format pilihan ganda kompleks dengan analisis IRT politomus dan Cognitive Diagnostic Model berbasis GDINA untuk menghasilkan profil penguasaan atribut kognitif siswa yang rinci, bermakna secara pedagogis, dan aplikatif bagi pengambilan keputusan pembelajaran berbasis data. Secara keseluruhan, instrumen yang dikembangkan valid secara empiris, informatif secara diagnostik, dan efektif untuk mendukung asesmen diagnostik serta diferensiasi pembelajaran SPLDV.
Keywords
Full Text:
PDFReferences
Amelia, A. (2016). Pengembangan instrumen literasi numerasi berbasis higher order thinking skills pada materi aritmatika sosial. Jurnal Riset Pendidikan Matematika, 3(2), 112–125. https://journal.unirow.ac.id
Anjarrani, A., & Kurniasih, R. (2023). Analisis kualitas soal numerasi dalam meningkatkan higher order thinking skills siswa. Jurnal Pendidikan Matematika, 10(2), 123–135.
Anwar, F., & Kartika, R. (2023). Kemampuan literasi matematis calon guru dalam pengajuan masalah berorientasi data. Jurnal Matematika dan Pendidikan Matematika, 11(1),65–78. https://ojs.fkip.ummetro.ac.id/index.php/matematika/article/view/6463
Aulia, M., & Umi, M. (2019). Pengembangan soal matematika model PISA level 5 untuk program pengayaan SMP. Jurnal Pendidikan Matematika, 6(2), 123–135. https://www.researchgate.net/publication/335496256
Auliya, L. (2022). Pengembangan instrumen tes literasi matematis berbasis budaya Betawi untuk meningkatkan pemahaman siswa dalam konteks budaya lokal [Skripsi, Universitas Islam Negeri Syarif Hidayatullah Jakarta]. https://repository.uinjkt.ac.id
Cohen, L., Manion, L., & Morrison, K. (2018). Research methods in education (8th ed.). Routledge.
de la Torre, J. (2011). The generalized DINA model framework. Psychometrika, 76(2), 179–199. https://doi.org/10.1007/s11336-011-9207-7
DeVellis, R. F. (2017). Scale development: Theory and applications (4th ed.). Sage Publications.
Fatimah, S., & Handayani, D. (2020). Pengembangan soal matematika model PISA menggunakan konteks Kalimantan Timur. Jurnal Pendidikan Matematika, 7(1), 68–77. https://www.researchgate.net/publication/339938499
Fullan, M., Quinn, J., & McEachen, J. (2018). Deep learning: Engage the world, change the world. Corwin Press.
Kemendikbudristek. (2022). Panduan pelaksanaan Asesmen Nasional. Pusat Asesmen Pendidikan.
Maradani, R., & Wilson, M. (2021). Development of diagnostic instruments in education: Applying the construct modeling approach. Journal of Educational Measurement and Evaluation, 15(2), 55–70.
McCrindle, M., & Fell, J. (2020). Understanding Generation Alpha: Educating and engaging the youngest generation. McCrindle Research.
Muraki, E. (1992). A generalized partial credit model: Application of an EM algorithm. Applied Psychological Measurement, 16(2), 159–176. https://doi.org/10.1177/014662169201600206
OECD. (2019a). PISA 2018 assessment and analytical framework: Mathematics, reading, science and global competence. OECD Publishing.
OECD. (2019b). PISA 2018 results: What students know and can do. OECD Publishing. https://doi.org/10.1787/5f07c754-en
OECD. (2021). The future of education and skills: Assessment in the 21st century. OECD Publishing.
OECD. (2023). Mathematics literacy and PISA performance: Trends and challenges in digital learning. OECD Publishing.
Retnawati, H. (2016). Validitas dan reliabilitas instrumen penelitian. Parama Publishing.
Retnawati, H., Hadi, S., & Nugraha, A. (2016). Difficulties in the implementation of higher order thinking skills in mathematics learning curriculum. Journal of Physics: Conference Series, 755, 012047.https://doi.org/10.1088/1742-6596/755/1/012047
Rizki, S., & Retnawati, H. (2020). Developing diagnostic test instruments in mathematics education: A systematic approach. Jurnal Riset Pendidikan Matematika, 7(2), 145–160.
Yusrizal, B., Susanti, T., & Astuti, R. (2020). Validasi instrumen dengan koefisien Aiken’s V. Jurnal Pengukuran Psikologi dan Pendidikan Indonesia, 9(3), 221–230.
Zimmerman, B. J., & Schunk, D. H. (2021). Self-regulated learning and academic achievement: Theoretical perspectives. Routledge.
DOI: https://doi.org/10.17509/e.v25i1.94820
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 EDUTECH
Ciptaan disebarluaskan di bawah Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional.