Course main content

  •  Estimators: bias, variance. Consistency, bias-variance decomposition.
  •  Likelihood and maximum likelihood estimators. Exponential models.
  •  Fisher information, Fréchet-Darmois-Cramer-Rao bound, asymptotic normality, delta-method.
  •  Asymptotic properties of the maximum likelihood estimators. Associated tests.
  •  Concentration inequalities
  •  Bayesian statistics (a priori and a posteriori distributions, maximum a posteriori estimator), variational and EM algorithms