magdalena bennett
@maibennett.com
Research Scientist working on causal inference. The Anna Wintour of slide decks. If you have something to say, say it with a nice plot #rstats (Disclaimer: All opinions are my own)
Reposted by magdalena bennett
Reposted by magdalena bennett
Offenders from different socio-demographic groups receive different sentences. This appears to violate the principle of equality under law.
However, this may be explained by differences in the nature and circumstances of the crimes performed. I.e the different sentences may be 'warranted'.
🧵 2/10
However, this may be explained by differences in the nature and circumstances of the crimes performed. I.e the different sentences may be 'warranted'.
🧵 2/10
December 8, 2025 at 10:20 AM
Offenders from different socio-demographic groups receive different sentences. This appears to violate the principle of equality under law.
However, this may be explained by differences in the nature and circumstances of the crimes performed. I.e the different sentences may be 'warranted'.
🧵 2/10
However, this may be explained by differences in the nature and circumstances of the crimes performed. I.e the different sentences may be 'warranted'.
🧵 2/10
(cont.) an RCT useful. If you’re take was “we shouldn’t run an RCT without _credible_ evidence from a DD, RD, or IV, etc.”, I’d maybe understand it (but still disagree). Using obs data for hypothesis generation I think it’s useful and might even be more efficient than the current status quo.
November 29, 2025 at 9:48 PM
(cont.) an RCT useful. If you’re take was “we shouldn’t run an RCT without _credible_ evidence from a DD, RD, or IV, etc.”, I’d maybe understand it (but still disagree). Using obs data for hypothesis generation I think it’s useful and might even be more efficient than the current status quo.
Yes, clearly the disagreement is where the bar is. I’m just finding it difficult to reconcile your take on “evidence can come from a mouse study or personal experiences” vs “associations are not enough”. Both are clearly NOT robust causal evidence, but they do provide info that may warrant (cont.)
November 29, 2025 at 9:47 PM
Yes, clearly the disagreement is where the bar is. I’m just finding it difficult to reconcile your take on “evidence can come from a mouse study or personal experiences” vs “associations are not enough”. Both are clearly NOT robust causal evidence, but they do provide info that may warrant (cont.)