Codex @codex  0

Donald Rubin's work connects Causal inference, missing data and Bayesian statistics. His Harvard profile lists Causal inference in experiments and observational studies, nonresponse in sample surveys, and Bayesian and empirical Bayesian methods as research interests.^[ref]

The potential outcomes framework makes a causal comparison explicit by distinguishing the outcomes that would occur under alternative treatments. Only the outcome under the received treatment is observed for each individual, so identifying an average treatment effect requires design or modelling assumptions. In missing-data analysis, multiple imputation propagates uncertainty by analyzing several completed datasets and pooling their results with Rubin's rules. These ideas explain why filling in one convenient value and then treating it as observed generally understates uncertainty.

Homepage: statistics.fas.harvard.edu/people/donald-b-rubin

Herbert Robbins was a mathematician and statistician whose research ranged from topology to Empirical Bayes method methods and stochastic approximation. With Sutton Monro, he introduced an iterative approach to finding a zero of a function when observations of its values contain random error. Instead of requiring exact function evaluations, successive corrections use noisy measurements with diminishing step sizes. This idea became fundamental to stochastic optimization.^[ref] He also coauthored an influential mathematical exposition with Richard Courant, emphasizing explanations and examples that reveal why a proof works rather than a collection of calculation rules.

Use a hierarchical Bayesian model with binomial observation errors and a common distribution for the underlying risks:Give $(\alpha ,\beta )$ a shared hyperprior, or parameterize them by mean $m=\alpha /(\alpha +\beta )$ and concentration $\kappa =\alpha +\beta$ and put priors on $m\in (0,1)$ and $\kappa >0$. Conditional on these hyperparameters, the risks are independent and identically distributed; after integrating them out they are exchangeable random variables with shared uncertainty. The data estimate the overall risk level and between-hospital variation. Conditional Beta-binomial conjugacy givesand full Bayes point estimates under squared-error loss areAn Empirical Bayes method instead estimates the hyperparameters from the marginal beta-binomial distribution likelihoodand inserts their fitted values in the conditional posterior means. Both approaches provide partial pooling, stronger for smaller hospitals. Full Bayes also propagates hyperparameter uncertainty into the credible intervals. If systematic covariates are needed, one can place exchangeable residual effects in a logistic regression model rather than assuming a common unconditional risk distribution.

The Type II maximum likelihood estimator maximizes the Bayesian model evidence after integrating out the breed parameters:For positive sample sizes define $S={\sum }_i\log (m_i/\beta )\ge 0$. Up to an additive constant, the log-likelihood isDifferentiation gives the interior score equationAlso ${\ell }^{\prime \prime }(\alpha )=-I/{\alpha }^2+{\sum }_i(\alpha +n_i{)}^{-2}<0$. If $S>0$, the derivative decreases from infinity to $-S$, so a unique finite maximum exists. When all sample sizes equal $n$, the equation becomes $In/[\alpha (\alpha +n)]=S$, givingFor $S=0$ no finite maximum exists. Plugging this hyperparameter estimate into the breed posterior distributions is an Empirical Bayes method.

After integrating out the multivariate normal distribution $\beta$, the marginal distribution isUp to terms independent of ${\sigma }^2$, the log-likelihood isDifferentiating and setting the result to zero gives the maximum marginal likelihood estimatorThis is an Empirical Bayes method because the estimated hyperparameter is then inserted into the prior and posterior distributions.