I have developed a conceptual model of critical success factors of digital libraries in Iran using a grounded theory approach. for the second phase of the study I am going to confirm the model by a statistical analysis. I prepared a questionnaire based on the model asking the experts' opinions. What statistical analysis method can I use for analyzing the results of the survey? Do you know a similar study?
I investigated conferences & poster presentations which have not been subject to much previous research. After the literature review, I ran a mixed method questionnaire that had quantifiable data (e.g. Likert scores & agreement options), plus qualitative areas where respondents could expand/clarify/comment. The response was quite low, so I proceeded by using the questions to form a mixed method interview structure. The selection process determined 'expertise', and the findings were directly compatible (+/- some scaling adjustments) with the preceding survey & some other published work. I used qualitative content analysis to evaluate & report the free-form answers, and standard mean averages & percentages to compare the quantitative data. If you have a large sample, then you can use more advanced inferential or deductive statistics, but it might not be meaningful or accurate to use them with smaller samples. Of course, if you are using genuine grounded theory, then you will need to 'close the circle' by showing that repeated themes/codes form the categories that fit (or don't fit) with your original starting point. In your case, the theory will develop as you find links & consistencies between existing literature, related themes & theories, & the constants you draw from your expert opinion data.
Confirming a conceptual model is tricky, because it is always possible that more information from different situations may show that the model is in error. Popper spoke about a model receiving a degree of corroboration if it has withstood good tests to try to show that it is in error (i.e., falsified). Degree of corroboration is a vague phrase, but if your model makes bold conjectures which turn out true this is good. Also, Fisher spoke about making theories elaborate which means that you should make as many predictions as possible from your model.
If you validated the model theoretically with experts, you may do Confirmatory factor analysis to test the structure of the model.
I am attaching some articles, and you can search for more articles in this regards.
Good luck
It sounds like you have a mixed methods design of the from QUAL --> quant. Depending on your purposes, this can be quite useful, as I have argued in the attached publication.
Still, I have to agree with Daniel Wright that the term "confirm" can be problematic, especially when you are dealing with the results from qualitative research. So, you should be sensitive to the preferences of your audience when you choose the language you use.
Article From Themes to Hypotheses: Following Up With Quantitative Methods
- Badges
- Science topic
- Similar topics
- Methodology
- Research Methodology