MASTER’S NOTEBOOK
Statistics in the Insurance Industry
Mani Lakshminarayanan, Committee on Applied Statisticians Chair
T
he insurance industry, like the pharmaceutical industry, is one
More About the Insurance-Statistics Connection
of a multitude of occupational destinations for statisticians
with a master’s degree. In fact, the job “actuary” has been con-
Society of Actuaries,
www.soa.org
sistently rated as one of the top four best jobs in the United States by
Casualty Actuarial Society,
www.casact.org
the Jobs Rated Almanac.
Statistics and Insurance Careers,
www.amstat.org/careers/copss/index.
cfm?fuseaction=insurance
Actuarial science requires knowledge of mathematics, probability,
statistical methods, and risk theory in solving real-life financial prob-
lems that involve uncertainty. There are at least four tracks a candi-
Actuaries provide technical expertise when developing insurance
date can pursue: life insurance, consulting, property and casualty, and
products, but informal discussions with colleagues reveal there is an
nontraditional. In all these tracks, actuaries play diverse roles and have
unmet need for statistical expertise, especially in topics such as predic-
varied responsibilities.
tive modeling and data mining. Though several of the big insurance
There are several academic institutions that offer graduate degrees
companies hire statistical analysts (advanced degree not required),
in actuarial science. In general, the core curriculum includes cours-
most approach statistical consulting firms for projects requiring in-
es in statistical methods, actuarial science, economics, and finance.
depth statistical expertise. As a result, opportunities are abundant for
Additionally, statistical software such as SAS has made an inroad to the
statisticians both within the insurance industry and as part of consult-
insurance field. Though Excel spreadsheets and database skills are gen-
ing firms providing statistical expertise.
erally required, it is common for clients to expect (especially in health
According to the SOA web site,
www.soa.org, there is a need for
and property/casualty areas) knowledge of SQL, C++, R, or SAS.
applications of predictive modeling and data mining in areas such as
Actuaries achieve the professional status of fellow of the Society
studying mortality trends, analysis of various claim distributions, and
of Actuaries (SOA) or Casualty Actuarial Society (CAS) as part
market research for policyholder behavior. The use of Bayesian statis-
of their career by passing a required set of exams over a period of
tics in areas such as credibility theory is also getting a lot of attention
years. Most employers provide study time during regular working
because it provides ways of assigning full or partial credibility to a poli-
hours and reimburse the cost of these exams as incentives during full-
cyholder’s experience. The use of generalized linear and mixed models
time employment.
also has been proposed in the field of credibility theory. n
AUGUST 2008 AMSTAT NEWS 29
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68