Arthur Pentland Dempster (born 1929) is a Professor Emeritus in the Harvard University Department of Statistics. He was one of four faculty when the department was founded in 1957.[3]
Arthur P. Dempster | |
|---|---|
 Dempster at a workshop in Brest, France, 2010 | |
| Born | 1929 (age 94–95) |
| Alma mater | Princeton University (PhD 1956) University of Toronto (BA 1952; MA 1953) |
| Known for | Dempster–Shafer theory, EM algorithm |
| Awards | Putnam Fellow (1951) ASA Fellow (1964) [1] IMS Fellow (1963) [2] Guggenheim Fellow AAAS Fellow (1997) |
| Scientific career | |
| Fields | Statistics |
| Institutions | Harvard University |
| Thesis | The two-sample multivariate problem in the degenerate case (1956) |
| Doctoral advisor | John Tukey |
| Doctoral students | Augustine Kong Nan Laird |
Biography
Dempster received his B.A. in mathematics and physics (1952) and M.A. in mathematics (1953), both from the University of Toronto. He obtained his Ph.D. in mathematical statistics from Princeton University in 1956. His thesis, titled The two-sample multivariate problem in the degenerate case, was written under the supervision of John Tukey.
Academic works
Among his contributions to statistics are the Dempster–Shafer theory and the expectation-maximization (EM) algorithm.
Selected publications
- Dempster, A. P. (1967), "Upper and lower probabilities induced by a multivalued mapping", The Annals of Mathematical Statistics, 38 (2): 325–339, doi:10.1214/aoms/1177698950
- Dempster, A. P.; Laird, N.; Rubin, D. B. (1977), "Maximum likelihood from incomplete data via the EM algorithm", Journal of the Royal Statistical Society, Series B, 39 (1): 1–38, JSTOR 2984875
Honors and awards
Dempster was a Putnam Fellow in 1951.[4] He was elected as an American Statistical Association Fellow in 1964,[1] an Institute of Mathematical Statistics Fellow in 1963,[2] and an American Academy of Arts and Sciences Fellow in 1997.[5]