Using bootstrapped quantile regression analysis for small sample research in applied linguistics: Some methodological considerations
Document Type
Article
Publication Date
1-1-2019
Abstract
Quantitative applied linguistics research often takes place in restricted settings of an intact language classroom, workplace, phonetics laboratory or longitudinal sample. In such settings the samples tend to be small, which raises several methodological problems. The main aim of the current paper is to give a detailed explanation of methodological and practical implications inherent in a robust statistical method called bootstrapped quantile regression (BQR) analysis. Importantly for applied linguistics research, the BQR method could help to deal with methodological difficulties inherent in small sample studies. The current study employed a moderately small sample (N = 27) of students learning the Japanese language in a Malaysian public university. It examined the relationships between the students’ language learning motivation (specifically, integrative orientation), the students’ images or stereotypes about Japan and their global attitudes toward the target language country and its people. The findings indicated that there was a statistically significant relationship between the students’ attitudes toward the target language country and their integrative orientation. In addition, these attitudes were found to be the most constant determinant of the integrative orientation. Besides the applied linguistics research, the BQR method can be used in a variety of the human sciences research where a sample size is small. © 2019 Nikitina et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Keywords
Foreign language, Language, Language anxiety
Divisions
arts,FLL,aei
Publication Title
PLoS ONE
Volume
14
Issue
1
Publisher
Public Library of Science