If you follow standard DEI criteria,
Iâm commenting on LessWrong; I donât do âstandard.âđ
More seriously, I apologize. I should have clarified what I meant by diversity. In particular, I mean that diverse groups are spread out in a parsimonious description space.
A pretty detailed example
As a concrete example of one understanding that would match my idea of diversity, consider some very high-dimensional space representing available people who can also do the work measured on as many axes as you can use to characterize them (characteristics of mind, body, experiences, etc.) and reduced by a technique to cause the remaining dimensions to give little mutual information about one another. Define a âdiversity-growing procedureâ for adding members to be one that chooses new members farthest away from the current subset. The more ways a diversity-growing procedure would choose a particular group, and the fewer exceptions that need to be made to the procedure to end up with that group, the more diverse the group.
Making an instance of this concrete example, imagine that our parsimonious space is 2D and that candidates are at all integer intersections of (0,1,2,3,4) x (0,1,2,3,4). If we choose candidates (2,2),(0,0), and (2,4), how diverse is that group? If you start with (0,0), the farthest away is (4,4), so youâll need to make an exception to add (2,4) (the farthest actually in the group). From (2,4), the farthest away is (0,4); once again, we need an exception to add (2,2). If we start with (2,2), then (0,0) is one of the farthest away, but we need an exception to add (2,4). The sequence (2,4) â (0,0) â (2,2) requires one exception. So, we have three ways with five exceptions. (I may have gotten some of this wrong since I did it in my head, but I think this gives the picture.)
This is just one example. Many ways to define diversity match my intuition of spread in a parsimonious description space.
A note on parsimony
Since weâre looking for diversity to help us in a particular context, we should choose dimensions that predict differences in that context. For example, a characteristic like âability to roll your tongueâ is probably less predictive of behavior in a research environment than gender, so we might want to down-weight it. However, we donât have good models of what matters yet, so it might be hubris to down-weight characteristics until we know they donât matter for covering research hypothesis space because weâve determined the effects by looking at groups actually doing research.
If you promote âdiversityâ then you have not only take in mind what you mean with it, but also how policy is likely going to work in practice.
In practice, there are some dimensions that are easy to measure like race and gender. There are other dimensions that are harder to measure. Some dimensions are also not conducive to research progress. Researchers with IQ under a hundred are underrepresented in grant giving.
Then there are variables like vaccination status, where being unvaxxed does not result in you having a worse ability to do research in the same way as having a lower IQ but there are perspectives on medical research that will correlate with vaccination status.
If your policy tries to increase the representation of unvaxxed researchers, that might be threatening to hegemonic beliefs and thus a research bureaucracy likely prefers increasing representation of minority races that are unlikely to threaten any hegenomic beliefs.
If you donât specify the dimensions, the dimensions that are going to selected are most likely those that donât threaten hegemony of current opinions and thus the dimensions that are least likely to actually matter for diversity of ideas and the selected dimensions might even be chosen to strengthen the hegemony of the existing ideas.
If you actually want real diversity by doing things like calling for diversity in vaccination status you should do that explicitly.
More seriously, I apologize. I should have clarified what I meant by diversity. In particular, I mean that diverse groups are spread out in a parsimonious description space.
A pretty detailed example
As a concrete example of one understanding that would match my idea of diversity, consider some very high-dimensional space representing available people who can also do the work measured on as many axes as you can use to characterize them (characteristics of mind, body, experiences, etc.) and reduced by a technique to cause the remaining dimensions to give little mutual information about one another. Define a âdiversity-growing procedureâ for adding members to be one that chooses new members farthest away from the current subset. The more ways a diversity-growing procedure would choose a particular group, and the fewer exceptions that need to be made to the procedure to end up with that group, the more diverse the group.
Making an instance of this concrete example, imagine that our parsimonious space is 2D and that candidates are at all integer intersections of (0,1,2,3,4) x (0,1,2,3,4). If we choose candidates (2,2),(0,0), and (2,4), how diverse is that group? If you start with (0,0), the farthest away is (4,4), so youâll need to make an exception to add (2,4) (the farthest actually in the group). From (2,4), the farthest away is (0,4); once again, we need an exception to add (2,2). If we start with (2,2), then (0,0) is one of the farthest away, but we need an exception to add (2,4). The sequence (2,4) â (0,0) â (2,2) requires one exception. So, we have three ways with five exceptions. (I may have gotten some of this wrong since I did it in my head, but I think this gives the picture.)
This is just one example. Many ways to define diversity match my intuition of spread in a parsimonious description space.
A note on parsimony
Since weâre looking for diversity to help us in a particular context, we should choose dimensions that predict differences in that context. For example, a characteristic like âability to roll your tongueâ is probably less predictive of behavior in a research environment than gender, so we might want to down-weight it. However, we donât have good models of what matters yet, so it might be hubris to down-weight characteristics until we know they donât matter for covering research hypothesis space because weâve determined the effects by looking at groups actually doing research.
If you promote âdiversityâ then you have not only take in mind what you mean with it, but also how policy is likely going to work in practice.
In practice, there are some dimensions that are easy to measure like race and gender. There are other dimensions that are harder to measure. Some dimensions are also not conducive to research progress. Researchers with IQ under a hundred are underrepresented in grant giving.
Then there are variables like vaccination status, where being unvaxxed does not result in you having a worse ability to do research in the same way as having a lower IQ but there are perspectives on medical research that will correlate with vaccination status.
If your policy tries to increase the representation of unvaxxed researchers, that might be threatening to hegemonic beliefs and thus a research bureaucracy likely prefers increasing representation of minority races that are unlikely to threaten any hegenomic beliefs.
If you donât specify the dimensions, the dimensions that are going to selected are most likely those that donât threaten hegemony of current opinions and thus the dimensions that are least likely to actually matter for diversity of ideas and the selected dimensions might even be chosen to strengthen the hegemony of the existing ideas.
If you actually want real diversity by doing things like calling for diversity in vaccination status you should do that explicitly.