PEMODELAN MIXTURE RASCH UNTUK MENGUKUR TINGKAT KECEMASAN MAHASISWA TERHADAP MATA KULIAH STATISTIKA DASAR

ZAHRA AYU RAHMADANI, . (2026) PEMODELAN MIXTURE RASCH UNTUK MENGUKUR TINGKAT KECEMASAN MAHASISWA TERHADAP MATA KULIAH STATISTIKA DASAR. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text COVER.pdf Download (833kB)
	Text BAB 1.pdf Download (277kB)
	Text BAB 2.pdf Restricted to Registered users only Download (585kB) | Request a copy
	Text BAB 3.pdf Restricted to Registered users only Download (553kB) | Request a copy
	Text BAB 4.pdf Restricted to Registered users only Download (687kB) | Request a copy
	Text BAB 5.pdf Restricted to Registered users only Download (247kB) | Request a copy
	Text DAFTAR PUSTAKA.pdf Download (242kB)
	Text LAMPIRAN RIWAYAT HIDUP.pdf Restricted to Registered users only Download (969kB) | Request a copy

Abstract

Statistics anxiety merupakan bentuk kecemasan yang dialami mahasiswa terhadap konten, proses pembelajaran, maupun evaluasi pada mata kuliah Statistika Dasar. Akibat tingginya heterogenitas tingkat kecemasan tersebut, penelitian ini bertujuan mengidentifikasi jumlah kelas laten yang terbentuk pada mahasiswa UNJ yang telah menempuh mata kuliah tersebut. Berbeda dengan model Rasch standar yang mengasumsikan populasi homogen, penelitian ini menerapkan Mixture Rasch Model (MRM) untuk mengelompokkan mahasiswa secara probabilistik. Data diperoleh dari 500 mahasiswa program sarjana FMIPA dan FISH Universitas Negeri Jakarta menggunakan instrumen Statistical Anxiety Scale (SAS) 22 item yang mencakup tiga dimensi (examination anxiety, interpretation anxiety, dan asking for help anxiety) dengan respons dikotomi (0 dan 1). Pendugaan parameter dilakukan menggunakan metode Conditional Maximum Likelihood Estimation (CMLE) dan algoritma Expectation-Maximization (EM). Hasil penelitian membuktikan populasi tidak homogen dan terbagi ke dalam tiga kelas laten optimal berdasarkan kriteria AIC, BIC, dan SABIC. Kelas 2 menjadi kelompok terbesar (43,6%), diikuti kelas 3 (28,5%) dan kelas 1 (27,9%). Setiap kelas menunjukkan karakteristik psikometris yang spesifik, kelas 1 diinterpretasikan sebagai kelompok kecemasan situasional dan ujian (rentang kesulitan -2,142 hingga 3,087 logit), kelas 2 sebagai kelompok kecemasan sosial-akademik akibat hambatan diskusi kelompok (-1,504 hingga 1,699 logit), sedangkan kelas 3 menunjukkan kecemasan mendalam dan menyeluruh yang didominasi ketakutan relasi kuasa dosen (-5,486 hingga 4,251 logit). Secara umum, mahasiswa perempuan konsisten menunjukkan kerentanan psikologis yang lebih tinggi terhadap kecemasan statistika dibandingkan mahasiswa laki-laki.*****Statistics anxiety is a form of anxiety experienced by students toward the content, learning process, and assessment in the Basic Statistics course. Given the high heterogeneity of students' anxiety levels, this study aimed to identify the optimal number of latent classes among students at Universitas Negeri Jakarta who had completed the course. Unlike the standard Rasch model, which assumes a homogeneous population, this study applied the Mixture Rasch Model (MRM) to probabilistically classify students into latent groups. Data were collected from 500 undergraduate students of the Faculty of Mathematics and Natural Sciences (FMIPA) and the Faculty of Social Sciences and Humanities (FISH) at Universitas Negeri Jakarta using the 22-item Statistical Anxiety Scale (SAS), which comprises three dimensions: examination anxiety, interpretation anxiety, and asking for help anxiety, with dichotomous responses (0 and 1). Parameter estimation was conducted using Conditional Maximum Likelihood Estimation (CMLE) and the Expectation–Maximization (EM) algorithm. The results indicated that the population was heterogeneous and was optimally classified into three latent classes based on the Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and Sample-Size Adjusted Bayesian Information Criterion (SABIC). Latent class 2 represented the largest group (43.6%), followed by latent class 3 (28.5%) and latent class 1 (27.9%). Each latent class exhibited distinct psychometric characteristics. Latent class 1 was interpreted as a situational and examination anxiety group (item difficulty range: –2.142 to 3.087 logits), latent class 2 as a social-academic anxiety group characterized by difficulties in group discussions (– 1.504 to 1.699 logits), and latent class 3 as a deep and pervasive anxiety group predominantly associated with fear of interactions with lecturers (–5.486 to 4.251 logits). Overall, female students consistently showed greater psychological vulnerability to statistics anxiety than male students.

Item Type:	Thesis (Sarjana)
Additional Information:	1). Prof. Dr. Dian Handayani, M.Si. ; 2). Siti Rohmah Rohimah, S.Pd., M.Si.
Subjects:	Pendidikan > Psikologi Pendidikan Sains > Statistika
Divisions:	FMIPA > S1 Statistika
Depositing User:	Zahra Ayu Rahmadani .
Date Deposited:	20 Aug 2026 07:54
Last Modified:	20 Aug 2026 07:54
URI:	http://repository.unj.ac.id/id/eprint/71641

Actions (login required)

View Item