In: Meta-Psychology, 2021, vol. 5, p. 1-11
Once they have learnt about the effects of collinearity on the output of multiple regression models, researchers may unduly worry about these and resort to (sometimes dubious) modelling techniques to mitigate them. I argue that, to the extent that problems occur in the presence of collinearity, they are not caused by it but rather by common mental shortcuts that researchers take when...
|
In: PyArXiv, 2020, p. 1-45
In cluster-randomised experiments, participants are randomly assigned to the conditions not on an individual basis but in entire groups. For instance, all pupils in a class are assigned to the same condition. This article reports on a series of simulations that were run to determine (1) how the clusters (e.g., classes) in such experiments should be assigned to the conditions if a relevant...
|
In: ITL - International Journal of Applied Linguistics
The average quantitative research report in applied linguistics is needlessly complicated. Articles with over fifty hypothesis tests are no exception, but despite such an onslaught of numbers, the patterns in the data often remain opaque to readers well-versed in quantitative methods, not to mention to colleagues, students, and non-academics without years of experience in navigating results...
|
In: Taal en Tongval, 2019, vol. 71, no. 1, p. 89-93
|
(Rapports du Centre scientifique de compétence sur le plurilinguisme)
The project Heritage language and school language: are literacy skills transferable? (HELASCOT) addresses the linguistic development in migrant children of Portuguese descent in Switzerland. It focuses primarily on the children’s literacy skills (reading comprehension and writing skills) in their heritage language (i.e. Portuguese) and in the language of instruction in the region in...
|
In: Studies in Second Language Learning and Teaching, 2019, vol. 9, no. 2, p. 397-419
Whereas Standard Dutch only distinguishes between two adnominal grammatical genders, substandard varieties of Belgian Dutch distinguish between three such genders. German, too, distinguishes between three genders. Nevertheless, when assigning gender to German nouns with Dutch cognates, speakers of Belgian Dutch are strongly influenced by Standard Dutch gender but to a much lesser degree (if at...
|
In: Second Language Research
Researchers commonly estimate the prevalence of nativelikeness among second-language learners by assessing how many of them perform similarly to a sample of native speakers on one or several linguistic tasks. Even when the native (L1) samples and second-language (L2) samples are comparable in terms of age, socio-economic status, educational background and the like, these nativelikeness estimates...
|
In: Journal of Writing Research, 2019, vol. 10, no. 3, p. 499-525
We investigated how well readers’ perceptions of the lexical richness of short texts can be predicted on the basis of automatically computable indices of the texts’ lexical properties. 3,060 French, German and Portuguese texts (between 9 and 284 words long) written by 8- to 10-year-olds were rated for their lexical richness by between 3 and 18 uninstructed raters, and over 150 indices were...
|
In: Zeitschrift für Interkulturellen Fremdsprachenunterricht
Lexical diversity and sophistication (in term of average corpus frequency) development in the school language (German or French) is investigated longitudinally in a population of Portuguese heritage speakers aged 8 to 10. Results show an improvement in lexical diversity scores but not in lexical sophistication. Differences were found between Portuguese heritage speakers and age matched children...
|
In: Studies in Second Language Learning and Teaching, 2015, vol. 5, no. 1, p. 135-152
I discuss three common practices that obfuscate or invalidate the statistical analysis of randomized controlled interventions in applied linguistics. These are (a) checking whether randomization produced groups that are balanced on a number of possibly relevant covariates, (b) using repeated measures ANOVA to analyze pretest-posttest designs, and (c) using traditional significance tests to...
|
