BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//AMSE//Event Calendar//FR
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:event-11531@www.amse-aixmarseille.fr
DTSTAMP:20260421T151503Z
CREATED:20260421T151503Z
LAST-MODIFIED:20260421T151503Z
STATUS:CONFIRMED
SEQUENCE:0
SUMMARY:big data and econometrics seminar - Yannis Yatracos
DTSTART:20241015T120000Z
DTEND:20241015T133000Z
DESCRIPTION:Breiman (2001) urged statisticians to provide tools when data\,
  X=s(Y) or X=s(θ\,Y)\, but his suggestion was ignored\; s is either known 
 or a Black-Box\; parameter θεΘ\, Y is random\, latent or not. However\, 
 computer scientists work with X=s(θ\,Y)\, calling s learning machine. In t
 his talk\, statistical inference tools are presented for θ when X=s(θ)\, 
 Y latent: a) The Empirical Discrimination Index (EDI)\, to detect a.s. θ-d
 iscrimination and identifiability. b) Matching estimates of θ with upper b
 ounds on the errors in prob. that depend on the “massiveness” of Θ. c)
  For known stochastic model of X\, Laplace’s 1774 frequentist Principle i
 s proved without Bayes rule\, thus obtaining a unique Fiducial distribution
  and showing finally Laplace’s and Fisher’s intuitions were correct! Fr
 equentists can now reclaim\, at least\, distributions obtained with flat im
 proper priors. For unknown X-model\, an Approximate Fiducial distribution f
 or θ is obtained. The tools are used in ABC\, providing F-ABC\, that inclu
 des all θ* drawn from a Θ-sampler\, unlike the Rubin (1984) ABC-rejection
  method followed until now. Thus\, when X=s(θ) and a cdf\, Fθ\, is assume
 d for X\, a risk averse researcher can use instead the sampler\, s\, and a)
 -c)\, since Fθ and an assumed θ-prior may be wrong. Le Cam’s Statistica
 l Experiments that use {Fθ* \, θ*εΘ}  are now extended to Data Generat
 ing Experiments using instead {s(θ*)\, θεΘ}\, which allow “learning�
 � cdfs Fθ* with repeated “training” samples.\\n\\nContact: Sullivan Hu
 é : sullivan.hue[at]univ-amu.frMichel Lubrano : michel.lubrano[at]univ-amu
 .fr\n\nPlus d'informations: https://www.amse-aixmarseille.fr/fr/evenements/
 yannis-yatracos
LOCATION:Îlot Bernard du Bois - Salle 24\, AMU - AMSE\, 5-9 boulevard Maur
 ice Bourdet\, 13001 Marseille
URL;VALUE=URI:https://www.amse-aixmarseille.fr/fr/evenements/yannis-yatracos
CONTACT:Sullivan Hué : sullivan.hue[at]univ-amu.frMichel Lubrano : michel.
 lubrano[at]univ-amu.fr
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR