= Arthur P. Dempster
{c}
{title2=1929-2026}
{wiki}
= Arthur Pentland Dempster
{c}
{synonym}
= A. P. Dempster
{c}
{synonym}
<Arthur P. Dempster> contributed to multivariate analysis, incomplete-data inference and the representation of uncertain evidence. With <Nan Laird> and <Donald Rubin>, he developed the general <expectation-maximization algorithm> formulation published in 1977. Its <expected value>[expectation] step averages a complete-data <log-likelihood function>[log likelihood] using the current <Conditional distribution> of latent or missing variables; its maximization step updates <statistical parameter>[parameters] using that average. This makes a difficult incomplete-data <likelihood function>[likelihood] accessible through a sequence of simpler calculations.
Harvard's institutional tribute also traces his work on <Dempster-Shafer theory>, in which evidence can leave an explicit component of uncertainty about an assertion. His dissertation concerned multivariate settings with more variables than observations, anticipating a central difficulty of <high-dimensional statistics>.https://statistics.fas.harvard.edu/news/2026/06/arthur-pentland-dempster-1929-2026-extended-obituary-and-tribute[Harvard tribute, dissertation, upper/lower probabilities and EM collaboration]{ref}
Identity and life dates: https://statistics.fas.harvard.edu/news/2026/06/arthur-pentland-dempster-1929-2026-extended-obituary-and-tribute[Harvard Department of Statistics obituary and tribute].
\Image[https://commons.wikimedia.org/wiki/Special:Redirect/file/Dempster_in_Brest.JPG?width=260]
{title=Portrait of <Arthur P. Dempster>}
{description=Llorenzi. https://creativecommons.org/licenses/by-sa/3.0/[CC BY-SA 3.0], via Wikimedia Commons.}
{source=https://commons.wikimedia.org/wiki/File:Dempster_in_Brest.JPG}
{width=260}
Back to article page
