Eiselen & Van Huyssteen 2021

PDF
RIS file
External files

English: Afrikaans, Likert scale, linguistics, offensiveness, ordinal logistic regression, statistical modelling, swearing

Afrikaans: Afrikaans, Likertskaal, linguistiek, aanstootlikheid, ordinale logistiese regressie, statistiese modellering, vloek

English: Likert-type data is commonly used in many research fields in humanities: from gauging the usability of different user-interface designs, to determining users’ likeliness to vote for a particular political party, to evaluation of course materials – to name but a few examples. Despite its prevalence, there is still some disagreement within the statistics community on whether Likert-type scales are true ordinal variables, and by implication whether parametric tests are legitimate to be used in such cases (Endresen & Janda 2017). In this paper, we explore one parametric statistical test, viz. cumulative odds ordinal logistic regression (OLR), as an analysis method for self-reported data in the humanities. For illustration purposes, our focus is specifically on data of users’ self-reported usage of, and attitudes towards swearwords, with the aim of identifying demographic attributes that are predictive of their usage and/or attitudes. After a brief description of the data we’re using, including how the data is being collected, we give a layman’s overview of OLR. Since one of our aims is to demonstrate the usability of OLR, we apply our discussion practically to a step-by-step procedure (based on Laerd Statistics 2015) that could be followed easily. We demonstrate the usefulness of the results in reporting on the usage of, and attitude towards two near synonymous Afrikaans swearwords. We show, amongst others, that the odds ratios that are generated as part of the modelling procedure can be used to draw direct conclusions about specific demographic groups.

Afrikaans: Likert-tipe data word algemeen in baie navorsingsvelde in die geesteswetenskappe gebruik: van die peiling van die bruikbaarheid van verskillende gebruikerskoppelvlakontwerpe, tot die bepaling van gebruikers se waarskynlikheid om vir ‘n bepaalde politieke party te stem, tot die evaluering van kursusmateriaal – om maar ‘n paar voorbeelde te noem. Ten spyte van die voorkoms daarvan, is daar steeds ‘n mate van meningsverskil binne die statistiekgemeenskap oor of Likert-tipe skale ware ordinale veranderlikes is, en by implikasie of parametriese toetse geldig is om in sulke gevalle gebruik te word (Endresen & Janda 2017). In hierdie bydrae ondersoek ons ​​een parametriese statistiese toets, nl. kumulatiewekans- ordinale logistiese regressie (OLR) as ‘n ontledingsmetode vir self-gerapporteerde data in die geesteswetenskappe. Vir illustrasiedoeleindes is ons fokus spesifiek op data van gebruikers se selfgerapporteerde gebruik van en houding teenoor vloekwoorde, met die doel om demografiese eienskappe te identifiseer wat voorspellend is vir hul gebruik en/of houdings. Na ‘n kort beskrywing van die data wat ons gebruik, insluitend hoe die data ingesamel word, gee ons ‘n lekeoorsig van OLR. Aangesien een van ons doelwitte is om die bruikbaarheid van OLR te demonstreer, pas ons ons bespreking prakties toe op ‘n stap-vir-stap-prosedure (gebaseer op Laerd Statistics 2015) wat maklik gevolg kan word. Ons demonstreer die bruikbaarheid van die resultate in verslagdoening oor die gebruik van en houding teenoor twee naby sinonimiese Afrikaanse vloekwoorde. Ons wys onder andere dat die kansverhoudings wat as deel van die modelleringsprosedure gegenereer word, gebruik kan word om direkte gevolgtrekkings oor spesifieke demografiese groepe te maak.

In: English

On: Afrikaans