C R Rao
Calyampudi Radhakrishna Rao was born on 10 September
1920 in Huvvina Hadagalli of the then Madras province of
India. His father C. D. Naidu was an inspector of police and
mother Laxmikanthamma, a house wife. He did his high
school education in Visakhapatnam, Andhra Pradesh and
subsequently received his Master’s degree in Mathematics
from Andhra University in 1940. He joined the Indian Statistical Institute in January
1941 as a statistical trainee. He enrolled in the newly started master’s program of
the Calcutta University, receiving a Master’s degree in Statistics in 1943 securing
the highest rank and gold medal of the university. His master’s thesis was on a
Characterization of random variables based on regression properties, a problem
posed by Ragner Frisch.
Rao joined as a regular employee of the Institute in 1943 and embarked on
a research career making fundamental contributions to statistics and at the same
time assisting Mahalanobis in his projects. In 1946 he was deputed by Mahalanobis
to work on an anthropology project of J.C.Trevor, at Cambridge in England. While at
Cambridge, during 1946–48, he worked on classification problems based on which
he received his doctorate in 1948 (later in 1965 he received Sc.D from the same
Cambridge University). He returned to India and rejoined the Institute in 1948. He
married Bhargavi in the same year. He was a professor from 1949 and
subsequently became Director of the then Research and Training School of the
Institute. After the death of Mahalanobis, Rao became the Director and Secretary of
the Institute. In 1976 after he expressed a desire not to continue as Director, he
was honoured with Jawaharlal Nehru Professorship at the Institute. Though he
made short visits to the U.S.A earlier, it was only in 1978 that he took up a
temporary appointment at the University of Pittsburgh, U.S.A and subsequently
remained there on a permanent basis as University Professor. In 1988 he moved to
Pennsylvania State University as Eberly Professor of Statistics.
Rao made contributions to nearly all fields of statistics. He has extensively
contributed to estimation theory, testing of hypotheses introducing several new
tests, linear models developing g-inverses, multivariate analysis including cluster
analysis and factor analysis, characterizations of probability distributions, entropy
measures, signal processing, sequential boot-strap, shape analysis, design of
experiments and sample surveys. He made significant contributions to
econometrics as well. Cramér-Rao inequality, Rao-Blackwellization, Rao’s score
test, Rao’s U-test, Fisher-Rao metric, Rao distance, Rao’s orthogonal arrays, and
Kagan-Linnik-Rao theorem are now classical.
Cramér-Rao bound is one of the breakthroughs in Statistics. It is interesting
to note that a version of this bound is used in the derivation of Weyl-Heisenberg
uncertainty principle in Physics. Score test, one of the breakthroughs in Statistics,
has found applications in econometrics and survival analysis. He was the first to
introduce differential geometric methods in statistical estimation. He was also one
of the first to discuss problems in cluster analysis and graphical representation of
multi-dimensional data in reduced dimensions.
Most of Rao’s theoretical work was not just motivated by applications, but
actually grew out of applied problems. According to Rao, he would not have thought
of Score test if he had not worked on a particular practical problem in genetics
which Fisher asked him to investigate. Rao arrived at the g-inverse, while studying
the long term effects of radiation on the survivors of the atom bomb attack. His
work on shape analysis has origins in a problem posed by a cardiologist on
constructing the shape of the human left ventricle from a pair of X-ray projection
images taken from two perpendicular camera sets.
Rao is author of 14 books, more than 350 research publications and nearly
30 edited volumes. Watching Rao lecture is like watching a skilled artist at work
with every statistical function and procedure at his command.
He is recipient of several awards and honours. He received the S.S.Bhatnagar
award in 1963, elected Fellow of the Royal Society in 1967. He received Padma
Bhushan in 1968 and the second highest honour, Padma Vibhushan in 2001 from
the Government of India. He received the Wilks Medal of the American Statistical
Association in 1979 and U.S. National Medal of Science in 2002. He is a member of
several scientific academies, including the National Academy of Sciences of U.S.A.
He has received honorary doctorates from several universities and institutes from
all the continents, including the Indian Statistical Institute.
Professor Rao delivered the 21st Convocation Address of Indian Statistical
Institute held on March 5, 1987 entitled as “ Uncertinity Randomness and
Creativity” and the 24th Convocation Address held on December 29, 1989 entitled
as “Taming of Uncertainty”.
Article by: Bhamidi V. Rao, Professor, Statistics and Mathematics Unit, Indian Statistical Institute,
Kolkata, India.
