2
$\begingroup$

In a summary of this behavioral economics article, it says

Our third finding is that cross-consumer heterogeneity in biases is poorly explained by even a “kitchen sink” of other consumer characteristics, including classical decision inputs, demographics, and measures of survey effort. Most strikingly, we find more bias variance within classical sub-groups widely thought to proxy for behavioral biases than across them. E.g., we find more bias variation with the highest-education group than across the highest- and lowest-education groups.

And then:

Our fifth finding is that there are also some important correlations between biases and classical inputs. Classical inputs and demographics may not explain much of the variance in biases (per finding #3), but some of them are correlated with biases in patterns that align with prior work. Most notably, the average pairwise correlation between cognitive skills and biases is -0.25. Cognitive skills are strongly negatively correlated with most biases, but positively correlated with loss aversion and ambiguity aversion.

I'm having trouble coming up with a simple multivariate model where some input does not proxy for differences in a given statistic between samples, but nevertheless is well-correlated with that statistic. Evidently I need to sharpen up on my stats!

Could someone give me an illustrative toy example of this pattern, and/or perhaps a reading reference? Thanks

$\endgroup$
2
$\begingroup$

Graph it.

They say they get correlations around $0.25$. Let's see how that looks.

library(MASS)
set.seed(2021)
rho <- 0.25
X <- MASS::mvrnorm(1000, c(0, 0), matrix(c(1, rho, rho, 1), 2, 2))
plot(X)
cor(X)

enter image description here

library(MASS)
set.seed(2021)
rho <- 0.2
X <- MASS::mvrnorm(1000, c(0, 0), matrix(c(1, rho, rho, 1), 2, 2))
plot(X)
cor(X)
rho <- 0.9
Y <- MASS::mvrnorm(1000, c(0, 0), matrix(c(1, rho, rho, 1), 2, 2))
points(Y, col = 'red')
cor(X)

enter image description here

I believe they mean something like this, that there is a slight correlation, just not enough to explain much of the variability (tight fit to a diagonal line).

$\endgroup$
6
  • $\begingroup$ But to be clear, correlation is what would constitute “explaining the variability”, right? (Causal inference issues aside) $\endgroup$ – Eric Auld Jun 18 at 22:24
  • $\begingroup$ Correlation of $0.25$ means $r^2=12.5\%$ of the variability explained. That’s a real amount while also not being immense. $\endgroup$ – Dave Jun 18 at 22:37
  • $\begingroup$ Thanks for your helpful reply. I’m actually wondering something different: on a fundamental level, the thing that would justify the claim “this explains the variation” would be a high correlation, right? (Again, causal inference aside) $\endgroup$ – Eric Auld Jun 19 at 0:10
  • 1
    $\begingroup$ You’re definitely on the right track, particularly if you use a less specific “association” than “correlation”. The idea is that the variability of $Y$ might be considerable, but you can account for some of that variability by considering the values of $X$. More concretely, there is some variability in human height. If you consider heights at particular ages, however, there is less variability. While there is some correlation (or association), however, the age still does not account for tons of that variability. $\endgroup$ – Dave Jun 19 at 0:20
  • $\begingroup$ Is there a metric or a reserved term specifically associated with “variance of Y is reduced by focusing on level sets of X”? $\endgroup$ – Eric Auld Jun 19 at 4:50

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.