Vincent Bagilet

Postdoctoral Fellow in Economics at ENS Lyon, CERGIC

[CERGIC @InfoCERGIC]

We are happy to host @VinPons (Harvard Business School) at @ENSdeLyon for tomorrow's seminar!

More info 👉 https://t.co/huCZKDG9Qj

@CedricChambru
@MatCoutt
@Sophie_Hatte
@mg_elisa
@VBagilet

[CERGIC @InfoCERGIC]

On Friday November 8, we're glad to host Patrick Pintus (@CNRS) for a seminar at @ENSdeLyon.

More info 👉 https://t.co/qvMu7tkPex

@CedricChambru
@MatCoutt
@Sophie_Hatte
@mg_elisa
@VBagilet

[Gallicagram @gallicagram]

@Gallicagram débarque sur #RStats !
Nous avions lancé une bouteille à la mer, demandant si un adepte de #RStats ne voudrait pas développer un package pour notre API. @VBagilet (Columbia) s'en est chargé et bien davantage...
D'où sort ce beau graphe ?🧵

https://t.co/p5TmtWVVgG

[Vincent Bagilet @VBagilet]

@deaneckles Thank you for sharing this! There is a new version with substantial additions coming soon!

A preliminary version of the new intro: https://t.co/S3f6d3I8D3

[Vincent Bagilet @VBagilet]

Website for the project: https://t.co/dicK6e6CmC

Working paper: https://t.co/BQqO8h0VPZ

The paper summed up in a picture:
N/N

[Vincent Bagilet @VBagilet]

Léo Zabrocki and I published a working paper arguing that causal inference methods can produce inflated published estimates.

They intrinsically reduce statistical power and it creates a trade-off between confounding and exaggerating true effect sizes. 1/N

#EconTwitter

[Vincent Bagilet @VBagilet]

A systematic reporting of pre and post analysis power calculations in observational studies would help gauge the risk of falling into this low power trap. 8/N