The integration of qualitative and quantitative data in mixed methods research can generate confirmed, discordant, or expanded findings. Based on your provided information, it seems that some of your results are either discordant or expanded. Discordance refers to the inconsistencies between qualitative and quantitative findings. Expansion means when the integration of qualitative and quantitative data generate further insights about the studied phenomenon.

As Matthew Kerry indicated, you can provide rationale for discordant results and further explain the expanded findings. I would suggest review the studies that you have cited in your literature review and identify the reasons for the discordant or expanded results.

Predict difference or explain it.

Hope this helps

Matt

The integration of qualitative and quantitative data in mixed methods research can generate confirmed, discordant, or expanded findings. Based on your provided information, it seems that some of your results are either discordant or expanded. Discordance refers to the inconsistencies between qualitative and quantitative findings. Expansion means when the integration of qualitative and quantitative data generate further insights about the studied phenomenon.

As Matthew Kerry indicated, you can provide rationale for discordant results and further explain the expanded findings. I would suggest review the studies that you have cited in your literature review and identify the reasons for the discordant or expanded results.

The qualitative results might be from the experts and quantitative results from the real data. One set of results may or may not corroborate with the other. But you can get to know how aligned or divergent the findings are. You can just explain it. It is well and good.

Yes it may vary while interpretating you can mention out of (no of interviews conducted) 6 respondents agreed with quant results and so can mention their views.

The quantitative and qualitative techniques are employed in the same research when there are two different questions and both required different methods to answer. In that case, then the answers are interpreted for final analysis. If same question is answered while using two different methods then obviously different results will obtain. It is same when doctor treat a patient with medicine and other patient with same disease with surgery. both qualitative and quantitative data may be interpreted to support each other but they will never be identical.

Yes, this case may be an axiom in scientific research due to several factors related to the researcher and the envoys alike, but there are researchers who try to combine and merge qualitative and quantitative research to strengthen the search results

Quantitative analysis typically provides a statistical test of a null. Failure to reject the null does not mean the null is true. Qualitative analysis typically provides no statistical test, so a qualitative analyst can exercise his or her own judgement. Surely one can reject a null based on qualitative reasoning and fail to reject the same null using Newman-Pearson testing. By the way, the mixed-methods literature requires both the quantitative and qualitative analysis to test the same null, else we have an approach to evaluative research that simply mixes methods, but is not mixed-method.

My answer serves as a complement for Ahtisham Younas'.

If the variables are affected by/variate in space, Spatial Statistic Modelling might be more accurate in measuring statistic correlation between variables. Traditional/Classic non-spatial statistic modelling is not sufficient when it comes to analyzing spatially varying data. Different techniques might be more or less efficient for different sets of data depending on their attributes.

For further information on that topic of spatial modelling, I suggest that you read:

FOTHERINGHAM, A. S; BRUNDSON, C.; CHARLTON, M. Geographically Weighted Regression: The Analysis of Spatially Varying Relationships.

SMITH, M.J; GOODCHILD, M. F; LONGLEY, P. A. Geospatial Analysis. A Comprehensive Guide to Principles, Techniques and Software Tools.

You'll need to consider what the divergence between the qualitative and quantitative results means -- that divergence is an interesting substantive finding in its own right.

It could be, depending on where the qualitative and quantitative data came from, that the divergence reflects something about the way instruments/data collection methods were constructed. For example, if you used interviews and questionnaires, perhaps the way items on the questionnaire were phrased or the way in which it was administered elicited different responses to those elicited by the interview questions (e.g. if respondents felt more/less comfortable answering honestly via one or the other).

You might want to take a look at this paper, which addresses possible ways of accounting for divergence in mixed methods studies:

Article Understanding divergence of quantitative and qualitative dat...

Hope this helps!

Your qualitative data variances may be so fine that to apply straight forward quantitative tools of measurement to bear will mean potentially losing fine yet significant variables of confirmation or refutation that could have helped you fine tune the study and resolve where the discordant element(s) lie and what their significance is. If that is the case using a fuzzy QCA approuch with a gradient rather than set 0.5 truth table may help eliminate clutter data. If time is also a considered variable then 3D statistical modelling based on the interactions between truth sets over time would probably yield greater clarity. For this finding the common variables from your qualitative studies to set your truth tables levels of significance is key. So maybe some narrative analysis?

Following

The inputs

From RG fellows

You are approaching research as an intellectual, not as a scientist. For me to explain this to you would take hours. Just think about building a bridge. Does anything go? Kids try and try to get their bridge to stand up on its own. Not every approach enables them to succeed.Why should it be different in science? Start with what you want to accomplish?