From Words to Numbers: How to Transform Qualitative Data into Meaningful Quantitative Results

Abstract

HoW to traNsForm Qualitative data iNto meaNiNgFul QuaNtitative results ** abstract in proposing a procedure for transforming qualitative data into quantitative results, we address the manifold requests for discovery-oriented research in the business disciplines. We present a systematic classification of combined qualitative-quantitative research designs and argue in favor of the generalization model. We give guidelines for its implementation and provide a blueprint for systematically converting respondents' words into numbers that can be used for further (statistical) analyses. We delimit and discuss the stages of unitization, categorization, and coding. We also raise quality issues and propose relevant quality criteria in the transformation process. in particular, we suggest the intercoder consistency-matrix for determining the incisiveness of categories developed through content analysis. Finally, we demonstrate in an exemplary study how the blueprint can be applied and highlight the benefits of the proposed research design.Jel-Classification: M19.

Women’s reported health behaviours before and during pregnancy: A retrospective study

“…This retrospective study assessed participant"s behaviour at pre-pregnancy and during pregnancy. This approach provides an accurate description of human behaviour (32) especially in health research (33) , with the qualitative data providing meaning and explanation of the quantitative data.…”

“…More specifically, 35 per cent of Australian women of child-bearing age (ages [25][26][27][28][29][30][31][32][33][34][35] are overweight or obese (9) .…”

The Adoption of Web-Based Marketing in the Travel and Tourism Industry: An Empirical Investigation in Egypt

“…Categorization then follows which consists of structuring and condensing data by grouping the qualitative material into theoretically insightful ways (Mayring, 2002). This stage is followed by coding which involves assigning codes to units (Srnka and Koeszegi, 2007). Content analysis has been criticized for not being truly qualitative and has long been realised as an important way to acquire historical quantitative data (Lacey and Luff, 2007;Ginsberg, 1988).…”

Content Analysis Through the Machine Learning Mill

“…Ideally, more than one researcher (coder) performs every stage, and the results of each coder are compared at each step to assure inter-coder reliability of the findings (Srnka and Koeszegi, 2007). The whole process of content analysis is often seen as an insurmountable task, since -if performed with scientific rigour -it is extremely labour-intensive (Weingart et al, 2004).…”