An inevitable drawback of focusing on the within-person variation and not being able to isolate exogenous events is that we are unable to say anything concrete about the direction of causality.
...contrary to the authors’ own statements that “Fostering the conditions where personality growth occurs – such as through positive schooling, communities, and parenting—may be a more effective way of improving national wellbeing than GDP growth.”
This is a subtle but extremely common form of “burying the lead”. Not directly committing the sin of confusing correlation and causation, but freely allowing correlation to “waggle its eyebrows and gesture furtively while mouthing ‘look over there’”—letting readers draw the almost inevitable unwarranted conclusions.
...contrary to the authors’ own statements that “Fostering the conditions where personality growth occurs – such as through positive schooling, communities, and parenting—may be a more effective way of improving national wellbeing than GDP growth.”
This makes the study sound very politically motivated.
It makes the study sound like political double-talk regardless of motivation. Are there any political parties in favor of negative schooling, communities, and parenting? No? Then that phrase doesn’t actually say anything remarkable, it just acts as priming to benefit any candidate or policy proponents whose propaganda uses similar phrasing.
It might be unwarranted to make those conclusions, but it might not be unwarranted to act on the assumption that those conclusions could be correct. If previously I was attempting to influence the well being of myself or someone else through economic gain, this study would suggest that spending at least some time considering making personality changes would be more effective.
My thinking is that if two factors are correlated in some data, and it’s not a fluke/fraud/coincidence/etc., it’s reasonable to conclude that at least one of these three is true:
The first factor (directly or indirectly) causes the second.
The second factor (directly or indirectly) causes the first.
Some third factor (directly or indirectly) causes both.
In other words, if you can only think of one plausible explanation for a correlation, it’s reasonable to assign it a lot of probability mass (in the same way that if you can think of only one plausible explanation for a murder, it’s reasonable to assign it a lot of probability mass). Of course, it’s important to keep in mind unknown unknowns, things you didn’t think of, and all of the improbable scenarios that might add up to a lot of probability.
it’s reasonable to conclude that at least one of these three is true
These often aren’t exhaustive. There’s the example of a prestigious university that only admits students who are exceptional either academically or musically. Among students at that university, academic ability is negatively correlated with musical ability, since either one is enough to be admitted, but it is rare to be exceptional in both, assuming they are uncorrelated in the general population. This does not fit into any of those three common reasons for correlation.
A similar, possibly more politically fraught example is the university that grants scholarships either on the basis of academic merit or financial need.
If personality correlates with well-being more strongly than economic factors then it seems unlikely that economic factors would influence personality to any significant extent. Because otherwise we would see a stronger correlation between those factors and well-being. So I don’t see a contradiction there.
Edit: now I see a possible contradiction. But I don’t agree with the reading of the second quoted sentence as drawing unwarranted conclusions.
I think they meant that they can’t say anything concrete about the causal relationship between personality change and change of life satisfaction, not about any kind of causal relationship at all. But you’re still right. It’s possible that personality change doesn’t cause changes in life satisfaction and then we still can’t do better than trying to make people richer.
On the other hand, the hypothesis that changes in life satisfaction follow changes in personality seems quite reasonable. They said “Fostering the conditions where personality growth occurs [...] may be a more effective way of improving national wellbeing than GDP growth.” This seems to me more like raising that hypothesis rather than presenting a conclusion. (And if readers can’t tell the difference then it’s hardly the scientists’ fault.)
From the paper:
...contrary to the authors’ own statements that “Fostering the conditions where personality growth occurs – such as through positive schooling, communities, and parenting—may be a more effective way of improving national wellbeing than GDP growth.”
This is a subtle but extremely common form of “burying the lead”. Not directly committing the sin of confusing correlation and causation, but freely allowing correlation to “waggle its eyebrows and gesture furtively while mouthing ‘look over there’”—letting readers draw the almost inevitable unwarranted conclusions.
This makes the study sound very politically motivated.
It makes the study sound like political double-talk regardless of motivation. Are there any political parties in favor of negative schooling, communities, and parenting? No? Then that phrase doesn’t actually say anything remarkable, it just acts as priming to benefit any candidate or policy proponents whose propaganda uses similar phrasing.
It might be unwarranted to make those conclusions, but it might not be unwarranted to act on the assumption that those conclusions could be correct. If previously I was attempting to influence the well being of myself or someone else through economic gain, this study would suggest that spending at least some time considering making personality changes would be more effective.
My thinking is that if two factors are correlated in some data, and it’s not a fluke/fraud/coincidence/etc., it’s reasonable to conclude that at least one of these three is true:
The first factor (directly or indirectly) causes the second.
The second factor (directly or indirectly) causes the first.
Some third factor (directly or indirectly) causes both.
In other words, if you can only think of one plausible explanation for a correlation, it’s reasonable to assign it a lot of probability mass (in the same way that if you can think of only one plausible explanation for a murder, it’s reasonable to assign it a lot of probability mass). Of course, it’s important to keep in mind unknown unknowns, things you didn’t think of, and all of the improbable scenarios that might add up to a lot of probability.
These often aren’t exhaustive. There’s the example of a prestigious university that only admits students who are exceptional either academically or musically. Among students at that university, academic ability is negatively correlated with musical ability, since either one is enough to be admitted, but it is rare to be exceptional in both, assuming they are uncorrelated in the general population. This does not fit into any of those three common reasons for correlation.
A similar, possibly more politically fraught example is the university that grants scholarships either on the basis of academic merit or financial need.
That’s a good scenario to think about. So maybe we can add an additional case where there’s some filtering process that’s affecting the data we see.
If personality correlates with well-being more strongly than economic factors then it seems unlikely that economic factors would influence personality to any significant extent. Because otherwise we would see a stronger correlation between those factors and well-being. So I don’t see a contradiction there.
Edit: now I see a possible contradiction. But I don’t agree with the reading of the second quoted sentence as drawing unwarranted conclusions.
The contradiction is between “nothing to say about causality” on the one hand, and “something to say about causality” on the other hand.
I think they meant that they can’t say anything concrete about the causal relationship between personality change and change of life satisfaction, not about any kind of causal relationship at all. But you’re still right. It’s possible that personality change doesn’t cause changes in life satisfaction and then we still can’t do better than trying to make people richer.
On the other hand, the hypothesis that changes in life satisfaction follow changes in personality seems quite reasonable. They said “Fostering the conditions where personality growth occurs [...] may be a more effective way of improving national wellbeing than GDP growth.” This seems to me more like raising that hypothesis rather than presenting a conclusion. (And if readers can’t tell the difference then it’s hardly the scientists’ fault.)