Monday, July 19, 2021

Diversity and complexity? Where should we focus our attention?

 This posting has been promoted by Michael Bamberger's recent two blog postings on "Building complexity into development evaluation" on the 3ie website: Evidence Matters: Towards equitable, inclusive and sustainable development

I started to make some comments underneath each of the two postings but have now decided to try to organise and extend my thoughts here. 

My starting point is an ongoing concern about how unproductive the discussion has been about  complexity (especially in relation to evaluation). Like an elephant giving birth to a mouse, has been my chosen metaphor in the past. There probably is some rhetorical overkill here, but it does express some of my felt frustration with the limited value of the now quite extended discussion.

Michael's blog postings have not allayed these concerns. My concerns start with the idea of measuring complexity, both how you do it and if it would be useful. Measuring complexity is Michael's proposed first step in a "practical five-step approach to address complexity-responsive evaluation in a systematic way" A lot of ink has already been spilled on the topic of measurement, which is the first of the five steps. A useful summary can be found in Melanie Mitchel's widely read Complexity: A guided Tour (2009:94-114) and Loyd, 1998, who counted at least 40 different ways. But I cant see any references back to any of these methods, suggesting that not much is being learned from past efforts, which is a pity.  

Along with the challenge of how to do it is the question of why you would want to do it, how might it be useful? The second blog posting explains that " In addition to providing stakeholders with an understanding of what complexity means for their program, the checklist also helps decide whether the program is sufficiently complex to merit the additional investment of time and resources required to conduct a complexity-focused evaluation" The second of these outcomes might be a more observable consequence, so my question here is where is the cut-off point in a checklist derived score that would at least inform such a decision, and how is that cut-off point justified. The checklist has 25 attribute questions spread over 4 dimensions. My next question is how do the results of this measurement exercise inform the next of the five steps: "Breaking the project into evaluable components and identifying the units of analysis for the component evaluation ". So far, I have not found any answers to either of these questions.

Another concern which I have already written about in my comment on the blog postings is that complexity seems to be very much “in the eye of the beholder”, i.e. depending on who you are and what you are looking for. My partner sees much more complexity in the design and behaviour of moths and butterflies than I do. A friend of mine sees much more complexity in the performance of classical music than I do.  Such observations prompt me to thinking that perhaps we should not put too much effort into trying to objectively measure complexity. Rather, perhaps we should take a more ethnographic perspective on complexity – i.e. we should pay attention to where people are seeing complexity and where they are not, and what are the implications thereof.

If we accept this suggestion it is still the case that the challenge of identifying complexity is still with us, but in a different form. So, I have another suggestion, which is to pay much more attention to diversity, as an important and related concept to complexity. As Scott Page has well described, there is a close and complicated relationship between diversity and complexity. Nevertheless, there are some practically useful points to note about the concept of diversity.  Firstly the presence of diversity is indicative of the absence of a common constraint, and the operation of many different causal influences. So can be treated as a proxy - indicating the presence of complex processes.  Secondly, there is extensive and more internally consistent and practically useful set of ways in which diversity can be measured.  These mainly have their origins in the studies of biodiversity but have a much wider applicability.  Diversity can also be measured in other spheres, in human relationships (using social network analysis tools) and how people see the world (using forms of ethnographic enquiry known as pile or card sorting).Thirdly, diversity has some potentially global relevance as a value and as objective.  Diversity of behaviour can be indicative of choice and empowerment. Fourthly, diversity can also be seen as an important independent variable as well, enabling adaptation and creativity. 

All this is not to say that diversity cannot also be problematic.  Some forms of diversity in the present could severely limit the extent of diversity in the future. For example, if within a population there was a wide range of different types of guns held by households and many different views on how and when they could legitimately be used.  At the more mundane level, within organisations different tasks may benefit from more versus less diversity within the groups addressing those tasks.  So diversity presents a useful and important problematic in a way that the concept of complexity does not. What forms of diversity we want to see, and see sustained over time, and how can they be enabled? Where do we want choice and where should be accept restriction?

Arguing for more attention to diversity, rather than complexity, does not mean there also needs to be a whole new school of evaluation developed around this idea. It is consistent with the idea of equifinality (An outcome can arise from multiple different causes) and multifinality ( A cause can have multiple different outcomes, And the idea of multiple conjunctural causation. It is also compatible with a social constructionist and interpretive perspective on social reality.