Please login or join to subscribe to this thread
I think quantitative. Can't explain it, but it is my opinion
1) People often want analysis to show them what they wanted to hear. With qualitative, it's easy to convince that your biases were valid. Quantitative data might show what you didn't want to hear.
2) By the time you reach a senior level, most people have forgotten most of their math. People fear what they don't understand, so younger employees who haven't forgotten it all, or senior technical specialists who still understand it can frighten management that wants to think it's smarter than the smart people.
3) I've seen so much junk analysis over the years that I'm skeptical. I've dissected enough analysis in my day that I found had no logical basis but looked complicated so convinced many people less critical than myself. I think of how many people freely accept junk science that fits their political views, but rejects the accepted science that doesn't, and I always have to consider whether or not the source is believable.
The point is: data analysis has no sense if you do not have the objective to convert it into information. So, qualitative or quantitative has to be consider in terms of that.
We are struggling with the same issue. In fact I'm working on doing some work for a client regarding their risk register, and it is coming down to whether or not to qualitative or quantitative analysis. Even the definitions of both are a bit confusing
The message versus the data. The data is meaningless without a valuable message to go with it, to explain the data and its value to the business. Both qualitative and quantitative are crucial.
It depends on the case. Mostly, quantitative
We recently stood up an entirely new "group" within our department (At the Assistant Deputy Minister level). It is called Data, Information, Analytics or ADM(DIA) for short. Information is power, and combing that with an analytics perspective is even more powerful. For such a large organization as ours, I can't imagine a future without this capability, throw in AI, and we cannot yet imagine the possibilities. Going forward, those that take advantage of data analytics and AI will be much better positioned than those that don't, and it will be all about quantitative data vs qualitative in most cases.
In either case the analysis is only as good as the assumptions. We spend way too much time on the results rather than looking critically at how we got those results.
Without the discipline associated with laying out the foundations of our analysis, qualitative of quantitative, the results will most likely reflect what we wanted them to be - using select data to rationalize what we wanted to do all along.
Qualitative analysis suggests that there is a certain level of subjective influence whereas Quantitative may appear to be more objective which can be misleading - there is an opportunity to misinterpret the data or manipulate the formulas.
When preparing an analysis or looking at the merits of an analysis I will spend much more time validating the conditions, constraints and assumptions that go into the analysis.
I recognize that the executives want numbers (quantitative) but the numbers can be much more misleading than a professional opinion (qualitative) when not based on reality.
My struggle is with applying the wrong analysis - insisting on quantitative when its just not there.
Please login or join to reply