Kesahan dan Kebolehpercayaan Instrumen Disposisi Pemikiran Komputasional (IDPeK) berdasarkan Model Pengukuran Rasch (Validity and Reliability of Computational Thinking Disposition Instrument (IDPeK) among Secondary School Computer Science Students)
DOI:
https://doi.org/10.17576/JPEN-2021-46.02-06Abstract
Pemikiran Komputasional (PK) merupakan kompetensi baharu pemikiran digital dalam pendidikan menjelang revolusi industri 4.0 (IR 4.0). Bagi menguji tahap disposisi pemikiran komputasional pelajar, instrumen IDPeK berskala Likert 4-poin yang mengandungi 55 item dihasilkan. Kajian tinjauan ini bertujuan menguji kesahan dan kebolehpercayaan instrumen IDPeK berdasarkan model pengukuran Rasch dan melibatkan 535 murid Sains Komputer Tingkatan Empat. Dapatan menunjukkan bahawa bagi aspek kesepadanan item, nilai infit dan outfit MNSQ yang dicatatkan adalah dalam julat yang ditetapkan (antara 0.81-1.31 logits). Ujian polariti item menunjukkan nilai korelasi PTMEA memenuhi syarat asas (antara 0.43-0.68). Syarat kebebasan setempat juga dipenuhi, di mana 10 padanan item mempunyai nilai piawai korelasi residual antara 0.29-0.47. Analisis unidimensi instrumen memenuhi keempat-empat kriteria yang ditetapkan dengan nilai varians sebanyak 40.7%. Indeks kebolehpercayaan keseluruhan item menunjukkan nilai 0.98 dan nilai Cronbach’s Alpha 0.97 yang disifatkan cemerlang. Dapatan analisis indeks pengasingan item bagi keseluruhan konstruk ialah sebanyak 6.88, manakala indeks pengasingan setiap konstruk adalah antara 5.65-8.70. Secara keseluruhannya, pengujian ciri-ciri psikometrik instrumen IDPeK yang dibina mematuhi syarat analisis model pengukuran Rasch. Kajian ini menyumbang kepada suatu instrumen pengukuran tahap disposisi pemikiran komputasional berciri teori respons item yang sesuai digunakan dalam konteks pelajar Sains Komputer sekolah menengah di Malaysia. Instrumen ini berperanan untuk menentukan keberhasilan intervensi PK sama ada secara formal atau informal.Kata Kunci: Pemikiran Komputasional; Model pengukuran Rasch; kesahan; kebolehpercayaan; disposisi Computational thinking (CT) is a new competence of digital thinking in education ahead of industrial revolution 4.0 (IR 4.0). In order to test the level students’ computational thinking disposition, an IDPeK instrument with a 4-point Likert scale containing 55 items was produced. This survey study aims to test the validity and reliability of the IDPeK instrument based on the Rasch measurement model and involved 535 Form Four Computer Science students. Findings show that for the aspect of item compatibility, the recorded MNSQ infit and outfit values are within the set range (between 0.81-1.31 logits). The item polarity test showed that PTMEA correlation values met the basic conditions (between 0.43-0.68). The condition of local independence is also met, where the 10 matching items have standardized residual correlation values between 0.29-0.47. Unidimensional analysis of the instrument meets all four criteria set with a variance value of 40.7%. The overall reliability index of the item shows a value of 0.98 and a Cronbach's Alpha value of 0.97 which is considered excellent. The result of the analysis of the item separation index for the entire construct is 6.88, while the separation index of each construct is between 5.65-8.70. Overall, the psychometric characteristics of the IDPeK instrument complies with the requirements of the Rasch measurement model. This study contributes an instrument for measuring the level of computational thinking disposition with item response theory characteristics that is suitable for use in the context of high school Computer Science students in Malaysia. This instrument plays a role in determining the success of CT intervention either formally or informally.Key Words: Computational Thinking; Rasch measurement model; validity; reliability; dispositionDownloads
Published
2022-09-10
Issue
Section
Articles
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright of the article and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) Licence that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
It is the author’s responsibility to ensure that his or her submitted works do not infringe any other existing copyright. Authors should obtain letters of permission to reproduce or adapt copyright material and enclose copies of these letters with the final version of the accepted manuscript.
The author indemnifies the editors and publisher against any breach of such a warranty.