Pedagogical Issues in Hypothesis Testing (Isu-isu Pedagogi dalam Pengujian Hipotesis)
DOI:
https://doi.org/10.17576/JPEN-2018-43.01-04Keywords:
Hypothesis testing, scientific method, mistakes, misinterpretations, pedagogical strategiesAbstract
Hypothesis testing is a statistical technique which is used to evaluate assumptions about a population on the basis of sample data, to determine the extent to which they are tenable. Hypothesis testing is the most widely-applied statistical technique, particularly because of the emphasis on hypothesis development and testing in the scientific method. Unfortunately, students and researchers are quite prone to making mistakes and misinterpreting inferences in hypothesis testing. These mistakes and misinterpretations tend to arise from insufficient understanding of the probability and sampling theory underlying the logic of hypothesis testing. The present study attempts to identify the causes of different types of mistakes made in hypothesis testing, in order to suggest pedagogical strategies to avoid these mistakes. The data for the study was collected from a sample of postgraduate management students in Bangalore, India, using specially-designed business decision-making case lets based on hypothesis testing. The analysis focuses on the incidence of different types of mistakes that the respondents committed, particularly with respect to the type of tests, and uses multiple linear discriminant analysis to identify the factors impacting the overall inference, i.e. the correct taking of the decision and the correct drawing of the conclusion. The key finding of the study is that both the formulation and computation factors play a significant role in taking the overall inference. Further, in each panel, the critical discriminator was found to be the aspect for which the incidence of mistakes was highest. With increasing complexity of the hypothesis test, the computation factor was found to become more important. In panels A and B (tests for a single population mean and proportion, respectively), formulation aspects were found to be the most significant discriminators, and in panel C (test for equality of means), both formulation and computation aspects were significant; on the other hand, for the remaining panels (test for independence, one-way ANOVA, and two-way ANOVA), only computation aspects were significant. The study contributes to the literature by proposing some pedagogical strategies for teaching of different types of hypothesis tests based on the findings.Keywords: Hypothesis testing; scientific method; mistakes; misinterpretations; pedagogical strategies Pengujian hipotesis adalah teknik statistik yang digunakan untuk menilai andaian mengenai populasi berdasarkan data sampel, untuk mengenal pasti sejauh mana ia dapat dipertanggungjawabkan. Pengujian hipotesis adalah teknik statistik yang paling banyak digunakan, terutamanya teknik ini memberi penekanan kepada perkembangan hipotesis dan ujian dalam kaedah saintifik. Malangnya, pelajar dan penyelidik agak cenderung melakukan kesilapan dan menyalahtafsirkan kesimpulan dalam ujian hipotesis. Kesalahan dan salah tafsiran ini cenderung timbul daripada pemahaman yang tidak mencukupi tentang teori kebarangkalian dan pensampelan yang mendasari logik pengujian hipotesis. Kajian ini cuba untuk mengenal pasti punca pelbagai jenis kesilapan yang dibuat dalam pengujian hipotesis serta untuk mencadangkan strategi pedagogi bagi mengelakkan kesilapan-kesilapan ini terus berlaku. Data untuk kajian ini diambil dariapada sampel pelajar pengurusan pasca siswazah di Bangalore, India dengan menggunakan reka bentuk pembuat keputusan perniagaan yang direka khusus berdasarkan ujian hipotesis. Analisis ini memberi tumpuan kepada kejadian pelbagai jenis kesilapan yang dilakukan oleh responden, terutamanya berkenaan dengan jenis ujian, dan menggunakan analisis diskriminasi berganda untuk mengenal pasti faktor-faktor yang mempengaruhi kesimpulan keseluruhan, iaitu pengambilan keputusan yang betul dan yang betul lukisan kesimpulan. Temuan utama kajian ini adalah bahawa kedua-dua faktor perumusan dan perhitungan memainkan peranan penting dalam mengambil kesimpulan keseluruhan. Selanjutnya, dalam setiap panel, diskriminator kritikal didapati merupakan aspek kesilapan kesilapan tertinggi yang dilakukan. Dengan meningkatkannya kesukaran pengujian hipotesis, maka faktor perhitungan dijumpai menjadi lebih penting dalam pengujian hipotesis. Dalam panel A dan B (ujian bagi min dan populasi masing-masing), aspek perumusan didapati sebagai diskriminator yang paling penting. Dalam panel C (ujian untuk kesamaan sarana), aspek perumusan dan perhitungan adalah penting; Di sisi lain, untuk panel yang tinggal (ujian untuk kebebasan, ANOVA sehala, dan ANOVA dua hala), hanya aspek pengiraan yang signifikan. Kajian ini menyumbang kepada ulasna kepustakaan dengan mencadangkan beberapa strategi pedagogi untuk mengajar pelbagai jenis pengujian hipotesis berdasarkan hasil kajian.Kata kunci: Pengujian hipotesis; kaedah sainstifik; kesilapan; salah interpretasi; strategi pedagogiDownloads
Published
2018-05-31
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.