Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jurnal Pendidikan Matematika (JUDIKA EDUCATION) Jurnal Riset Pendidikan dan Inovasi Pembelajaran Matematika (JRPIPM) Scientific Timeline
Mumtaza, Mutiara
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Education Mathematics Social Sciences

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
REGRESI LOGISTIK BINER UNTUK MENGKLASIFIKASIKAN CARA BELAJAR MAHASISWA MENURUT SUMBER BELAJARNYA Rizki, Nanda Arista; Mumtaza, Mutiara; Dewi, Carolina Fadia; Syahlafandi, Dhira
Scientific Timeline Vol. 4 No. 1 (2024)
Publisher : UNU Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini bertujuan untuk membuat model regresi logistik biner yang dapat mengklasifikasikan cara belajar Mahasiswa berdasarkan sumber belajarnya. Data diambil dari 111 Mahasiswa program studi pendidikan matematika Universitas Mulawarman. Sumber belajar yang menjadi variabel prediktor merupakan pilihan ganda majemuk. Hasil penelitian menunjukkan bahwa Mahasiswa yang menjadikan YouTube sebagai sumber belajarnya berpeluang untuk belajar secara mandiri sebesar 2,232 kali lebih besar dari pada belajar matematika berkelompok. Sementara Mahasiswa yang menjadikan buku cetak sebagai sumber belajarnya berpeluang untuk belajar secara kelompok sebesar 1,968 kali lebih besar dari pada belajar matematika mandiri. Nilai skor F1 tertinggi terletak pada pembagian data 90:10 yaitu sebesar 0,643. Skor AUC untuk model regresi logistik biner yang digunakan adalah sebesar 0,611.
Penerapan Pohon Keputusan untuk Memetakan Gaya Kognitif Berdasarkan Kesalahan Siswa dalam Berpikir Aljabar Menurut Teori Newman Mumtaza, Mutiara; Rizki, Nanda Arista
Jurnal Pendidikan Matematika : Judika Education Vol 7 No 2 (2024): Jurnal Pendidikan Matematika:Judika Education
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/judika.v7i2.12903

Abstract

An understanding of Field Independent (FI) and Field Dependent (FD) cognitive styles is important for teachers because these two styles affect the way students understand and process information, which ultimately has an impact on the effectiveness of learning. This study aimed to build a decision tree model to map the cognitive style of students based on errors that students make in solving algebra problems according to Newman's error theory. The method used in this study was a quantitative approach with the ID3 algorithm in decision tree modeling. The instruments used include the GEFT test to identify students' cognitive style and the basic algebra ability test containing 6 aspects of algebra ability according to Lew, i.e. generalization, abstraction, analytical thinking, dynamic thinking, modeling, and organization. The decision tree model was built based on the errors made by students according to Newman's error theory. The results showed that the decision tree generated from algebra problems in the generalization aspect had an accuracy of 82.5%. This decision tree has a main attribute in the form of process skill errors, which can map the cognitive style of students as FI or FD. This decision tree formed three implication rules, which became the basis for classifying the cognitive style of students. This finding was expected to be a guide for teachers in designing a more adaptive and efficient learning strategy with an approach that is on the cognitive style of students to improve students' algebraic thinking ability. Keywords: Cognitive Style, Algebraic Thinking Ability, Decision Tree, Newman's Error Theory
Applying Binary Logistic Regression to Map Cognitive Styles Based on Students’ Errors in Algebraic Thinking Generalization Problems According to Newman’s Theory Rizki, Nanda Arista; Cahyaningrum, Gyta Krisdiana; Mumtaza, Mutiara
Jurnal Riset Pendidikan dan Inovasi Pembelajaran Matematika Vol. 10 No. 1 (2026): JRPIPM APRIL 2026
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jrpipm.v10n1.p48-58

Abstract

Algebraic generalization problems pose a significant challenge, requiring teachers to recognize influencing factors like Field Independent (FI) and Field Dependent (FD) cognitive styles. The purpose of this study was to apply binary logistic regression to map students' cognitive styles, either FI or FD, based on their error patterns when solving algebraic thinking generalization problems. These errors were classified using the five categories of Newman’s Theory: Reading (R), Comprehension (C), Transformation (T), Process Skill (S), and Encoding (E). This exploratory correlational study involved 40 tenth-grade students from SMA IT Granada Samarinda. Cognitive style (the dependent variable) was measured using the GEFT, while the Newman error categories (the independent variables) were identified from a generalization instrument adopted from TIMSS (2003–2019). The results found that 23 out of 40 students made mistakes, consisting of 9 FI students and 31 FD students. The binary logistic regression results showed that the Process Skill (S) error was the strongest predictor for the FI style, with an odds ratio of 18.025. This means that students who make an S error are 18 times more likely to be classified as FI. This finding leads to the conclusion that FI students struggle with the details of procedural implementation, despite possessing a strong strategic understanding. Binary logistic regression proved effective as a diagnostic tool to support more personalized mathematics learning strategies.
Co-Authors Dewi, Carolina Fadia Nanda Arista Rizki Syahlafandi, Dhira