Professional Documents
Culture Documents
Resource Guide
Module 2
2014/2015
November 2014
Disclaimer: This Module 2 Resource Guide has been prepared by and/or on behalf of the Institute
and Faculty of Actuaries (IFoA). The IFoA does not accept any responsibility and/or liability
whatsoever for the content or use of this resource guide. This resource guide does not constitute
advice and should not be relied upon as such. The IFoA does not guarantee any outcome or result
from the application of this resource guide and no warranty as to the accuracy or correctness of this
resource guide is provided.
Copyright: All material in this resource guide is the copyright material of the IFoA, unless otherwise
stated. Use may be made of these pages for non-commercial and study/research purposes without
permission from the IFoA. Commercial use of this material may only be made with the express, prior
written permission of the IFoA. Material provided by any third party and incorporated into this resource
guide, is likely to be the copyright material of that author. Permission to copy or otherwise use such
material must be obtained from the author.
Institute and Faculty of Actuaries (RC 000243)
Module 2
Statistics and Models
Certified Actuarial Analyst
Resource Guide
Version 4 Updated 10 November 2014
2014 Edition V4
2014 Edition V4
Welcome to the Resource Guide for Module 2 Statistics and Models the entry test
module for the Institute and Faculty of Actuaries Certified Actuarial Analyst qualification
launched in 2014. The purpose of this Resource Guide is to provide you with a one stop
shop virtual guide to all there is to know about this module: registration, contact us details;
the syllabus, assessment, learning resources, and questions and answers.
1.0
2.0
Module Reference
Assessment
Fundamental
Mathematics & Statistics
CAA (0)
CAA (1)
CAA (2)
CAA (3)
CAA (4)
CAA (5)
3 hour examination.
Online Professional
Awareness Test (OPAT)
OPAT
90 minute examination
*An additional 15 minutes will be allowed before the start of the exam for
administrative purposes which include agreeing to a statement of confidentiality,
reading instructions and working through basic sample questions which will enable
you to become familiar with the format of the exam.
In addition to passing the above exams, students must complete at least one year of
relevant work experience (Work Based Skills), comply with the IFoAs ethical code
and adhere to the IFoAs Continuing Professional Development (CPD) requirements.
Page 3
2014 Edition V4
The Syllabus
The Module 2 syllabus can found in Appendix One attached to this Resource Guide
4.0
Module 0 - 4
Module 5
5.0
5.1
50 hours
At the present time, there is no face to face tuition of which the IFoA is aware. Please
see Section 5.2 for online tuition provision.
5.2
Online Learning
There is one learning provider based in the UK that will be offering online learning
resources for the CAA qualification.
BPP Actuarial Education
www.bppacted.com
Email: ActEd@bpp.com
Tel: +44 (0)1235 550005
5.3
Page 4
2014 Edition V4
5.3.1
Page 5
2014 Edition V4
http://onlinecourses.science.psu.edu/stat414
[See Stat 415, Section 6]
https://en.wikipedia.org
[Search: Estimation Theory]
5.3.5 TOPIC 6 Confidence intervals for unknown parameters
http://onlinecourses.science.psu.edu/stat414
[See Stat 415, Section 6, Lessons 30-33]
https://en.wikipedia.org
[Search: Confidence Intervals]
5.3.6 TOPIC 7 Testing hypotheses
http://onlinecourses.science.psu.edu/stat414
[See Stat 415, Section 7]
https://en.wikipedia.org
[Search: Statistical hypothesis testing]
5.3.7 TOPIC 8 Linear relationships between variables using correlation
analysis and regression analysis
http://onlinecourses.science.psu.edu/stat414
[See Stat 414, Section 4]
https://en.wikipedia.org
[Search: bivariate data + other learning objectives]
5.3.8 TOPIC 9 The principles of actuarial modelling
https://www:qub.ac.uk/elearning/public/PrinciplesofActuarialModelling
https://en.wikipedia.org
[Search: stochastic modelling]
5.3.9 TOPIC 10 The general principles of stochastic processes, and their
classification into different types
https://en.wikipedia.org
[Search: stochastic processes; Markov]
5.3.10 TOPIC 11 Markov chain processes
https://en.wikipedia.org
[Search: stochastic processes; Markov chain]
Page 6
2014 Edition V4
Pass standards Pass standards are set by the IFoA Examinations Board.
Details of pass standards for CAA Exams will be published as soon as
possible.
All exams will be administered through Pearson VUE test centres located in
regions across the globe. Please visit our Pearson VUE website and click on
Locate a test centre to find your nearest Pearson VUE testing centre.
7.0
7.1
Approved Calculator
The IFoA approved calculator for the Certified Actuarial Analyst exams is the Texas
Instruments TI-30 Multiview (with or without suffix). An example of this model is
shown below:
This will be the only physical calculator allowed into the exam. Please expect your
calculator to be checked by the proctors at the exam centre. This process will include
deleting any information stored on the memory of your calculator.
Page 7
2014 Edition V4
Please note: Pearson VUE staff will not be issuing physical calculators should you
fail to bring your own IFoA approved calculator to the examination. In the instance
that you fail to bring your own IFoA approved calculator, an on-screen scientific
calculator will be available during the exam [see 7.2 below for details].
The approved Certified Actuarial Analyst calculator is available to purchase from our
eShop.
7.2
On-screen Calculator
An on-screen scientific calculator will be accessible from all examination screens
during the entirety of the examination. Please find an example below of an on-screen
scientific calculator.
7.3
It is strongly recommended that you make yourself familiar with the Formulae and Tables
before sitting the CAA exams. The Formulae and Tables book is available to purchase from
our eShop.
Page 8
7.4
2014 Edition V4
Making notes
Scrap paper, for use in the examinations, will be provided by Pearson VUE staff. This
will consist of a notebook that contains multiple erasable note boards or individual
erasable note boards, as well as an erasable fine tip marker pen. You will have
access to as many note boards as required and will be able to use the note boards,
as well as the marker pen, for the duration of the exam.
Please note, for security reasons, Pearson VUE do not provide erasers for the note
board and pens.
Both the note board and pen will be collected by Pearson VUE staff upon completion
of the exam.
8.0
Sample Questions
A Module 2 Specimen Examination Paper with sample examination questions is
provided in Appendix Two attached to this Resource Guide. Only 20 sample
questions are listed in the Module 2 Specimen Examination Paper, although there will
be a total of 65 questions in the actual Module 2 examination. The questions found in
the specimen paper will not be included in the actual Module 2 examination.
9.0
To give you an idea of what you can expect when sitting your exam at a
Pearson VUE test centre, watch the short video on our website.
Before beginning your exam, 15 minutes will be allocated at the start in which
you will be required to agree to a Non-Disclosure and General Terms of Use
Agreement. You will also have the option to participate in an exam tutorial in
this time.
Please note that you must agree to the Non-Disclosure and General Terms of
Use Agreement in order to sit your exam. Failure to do so will result in your not
being permitted to sit your exam.
Please make yourself familiar with the IFoA and Pearson VUE testing policies.
These can be found in the Guide to Module 0 and the Student Handbook as
well as by logging in to your Pearson VUE online account.
Page 9
2014 Edition V4
Page 10
2014 Edition V4
APPENDIX ONE
Module 2
Statistics and Models
Certified Actuarial Analyst
Syllabus
Version 2 updated 29 May 2014
Page 11
2014 Edition V4
Aim
The aim of the Statistics and Models syllabus is to provide grounding in the aspects of
statistics that are of relevance to actuarial work and in stochastic processes and survival
models.
TOPIC 1
The main features of the principal discrete and continuous distributions
Indicative study and assessment weighting 15%
Learning objectives
(i)
(ii)
(iii)
(iv)
Learning objectives
(i)
(ii)
Determine the cumulant generating function and the cumulants for random variables
(iii)
(iv)
(v)
State the reasons why moment generating functions, cumulant generating functions
and cumulants are used
Page 12
2014 Edition V4
TOPIC 3
The concepts of independence, jointly distributed random variables and
conditional distributions. The use of generating functions to establish
the distribution of linear combinations of independent random variables
Indicative study and assessment weighting 5%
Learning objectives
(i)
(ii)
(iii)
(iv)
State and calculate the mean and variance of a function of two jointly distributed
random variables, and the covariance and correlation coefficient between two such
variables
(v)
(vi)
State the mean and variance of linear function of independent random variables
Page 13
2014 Edition V4
TOPIC 4
The central limit theorem
The concepts of random sampling, statistical inference and sampling
distribution
Indicative study and assessment weighting 10%
Learning objectives
(i)
State the central limit theorem for a sequence of independent, identically distributed
random variables
(ii)
(iii)
(iv)
(v)
(vi)
(vii)
(viii)
Determine the mean and variance of a sample mean and the mean of a sample
variance in terms of the population mean, variance and sample size
(ix)
Page 14
2014 Edition V4
TOPIC 5
The main methods of estimation, the main properties of estimators, and
their application
Indicative study and assessment weighting 10%
Learning objectives
(i)
(ii)
(iii)
(iv)
(v)
Define the terms: efficiency, bias, consistency and mean squared error
(vi)
Calculate the bias and mean square error of an estimator and use them to compare
estimators
TOPIC 6
Confidence intervals for unknown parameters
Indicative study and assessment weighting 5%
Learning objectives
(i)
(ii)
(iii)
Calculate confidence intervals for a binomial probability and a Poisson mean, using
the normal approximation in both cases
(iv)
Calculate confidence intervals for two-sample situations involving either the normal
distribution, or the normal approximation to the binomial and Poisson distributions
Page 15
2014 Edition V4
TOPIC 7
Testing hypotheses
Indicative study and assessment weighting 10%
Learning objectives
(i)
Explain what is meant by the terms null and alternative hypotheses, simple and
composite hypotheses, critical region, level of significance and probability-value of a
test
(ii)
Apply basic tests for the one-sample and two-sample situations involving the
normal, binomial and Poisson distributions
(iii)
(iv)
2
Apply a test to test the hypothesis that a random sample is from a particular
distribution, including cases where parameters are unknown
TOPIC 8
Linear relationships between variables using correlation analysis and
regression analysis
Indicative study and assessment weighting 5%
Learning objectives
(i)
(ii)
(iii)
Explain the interpretation of the correlation coefficient for bivariate data and perform
statistical inference as appropriate
(iv)
(v)
(vi)
Define the usual simple regression model (with a single explanatory variable)
(vii)
2
Calculate R (coefficient of determination)
(viii)
2
Describe the use of R to measure the goodness of fit of a linear regression model
(ix)
Page 16
2014 Edition V4
TOPIC 9
The principles of actuarial modelling
Indicative study and assessment weighting 5%
Learning objectives
(i)
(ii)
(iii)
Explain the difference between a stochastic and a deterministic model, and identify
the advantages/disadvantages of each
(iv)
Describe, in general terms, how to decide whether a model is suitable for any
particular application
(v)
Explain the difference between the short-run and long-run properties of a model, and
how this may be relevant in deciding whether a model is suitable for any particular
application
(vi)
Describe, in general terms, how to analyse the potential output from a model, and
explain why this is relevant to the choice of model
(vii)
Describe the process of sensitivity testing of assumptions and explain why this forms
an important part of the modelling process
(viii)
Explain the factors that must be considered when communicating the results
following the application of a model
Page 17
2014 Edition V4
TOPIC 10
The general principles of stochastic processes, and their classification
into different types
Stochastic interest rate models
Indicative study and assessment weighting 5%
Learning objectives
(i)
(ii)
(iv)
Explain what is meant by the Markov property in the context of a stochastic process
(v)
Explain the concept of a stochastic interest rate model and the fundamental
distinction between this and a deterministic model
(vi)
Derive algebraically, for the model in which the annual rates of return are
independently and identically distributed and for other simple models, expressions for
the mean value and the variance of the accumulated amount of a single premium
Page 18
2014 Edition V4
TOPIC 11
Markov chain processes
Indicative study and assessment weighting 10%
Learning objectives
(i)
(ii)
Calculate the stationary distribution for a Markov chain model in simple cases
(iii)
(iv)
TOPIC 12
The Markov jump process
Indicative study and assessment weighting 10%
Learning objectives
(i)
(ii)
(iii)
Define the Poisson process, state the distribution of the number of events in a given
time interval, state the distribution of inter-event times, and apply these results
(iv)
Define the two-state survival model, sickness models and other example multiple
state models in terms of Markov jump processes
(v)
Define the jump chain model associated with a Markov jump process model, and
apply the results
(vi)
Demonstrate how Markov jump processes can be used as a tool for modelling
Page 19
CAA Module 2 Re
esource Gu
uide
2014 Edition
E
V4
TO
OPIC 13
The
e random liifetime surv
rvival mode
el
Indicatiive study an
nd assessm
ment weightiing 5%
ng objectiv
ves
Learnin
(i)
Describe th
he model of lifetime or ffailure time from age x as a randoom variable
(ii)
(iii)
(iv)
a
sy
ymbols p
Define the actuarial
(v)
(vi)
t x
and q an
nd state inte
egral formulaae for them
m
t
andd state an
Compare th
he random lifetime survvival model with the tw
wo state Marrkov jump process
p
survival mo
odel
END O
OF SYLL
LABUS
Disclaim
mer: This sylllabus has be
een prepared
d by and/or on
o behalf of the
t Institute aand Faculty of
Actuarie
es (IFoA). Th
he IFoA does
s not accept any respons
sibility and/orr liability whaatsoever for the
t
content or use of thiss syllabus. This
T
syllabuss does not co
onstitute adviice and shouuld not be rellied upon
as such.. The IFoA does not guarrantee any o
outcome or re
esult from the
e applicationn of this syllabus and
no warra
anty as to the
e accuracy or
o correctnesss of this sylla
abus is provided.
Copyrig
ght: All mate
erial in this syllabus
s
is th e copyright material
m
of th
he IFoA, unleess otherwis
se stated.
Use ma
ay be made
e of these pages for non-comme
ercial and study/researcch purposes
s without
permission from the IFoA. Commercial use of this material may only
y be made w
with the expre
ess, prior
written p
permission off the IFoA. Material
M
proviided by any third
t
party an
nd incorporaated into this syllabus,
is likely to be the copyright mate
erial of that a
author. Permission to cop
py or otherwiise use such
h material
om the autho
or.
must be obtained fro
Institu
ute and Faculty of Actuaries (RC 0002
243)
Page 20
2014 Edition V4
APPENDIX TWO
Module 2
Statistics and Models
Certified Actuarial Analyst
Specimen Examination Paper
Page 21
2014 Edition V4
x 1 k
x k
,
(1 )
k 1
Negative Binomial
Binomial
Poisson
Uniform (discrete version)
Answer: A
2
Answer: D
3
[2xexp(-x)]2
8x3exp(-2x)
x1exp(-x)
4x2exp(-3x)
Answer: A
4
(et + )n
[1 + (et -1)]n
exp[(et -1)]
exp(t + 2t2)
Answer: B
Page 22
2014 Edition V4
9
15
18
90
Answer: D
6
0.12
0.14
0.86
0.88
Answer: C
7
A random sample of size 16 is taken from a Normal distribution with mean =25 and
variance 2=4.
The sample mean is denoted .
Calculate the probability that is greater than 26, correct to two decimal places.
A
B
C
D
0.02
0.15
0.31
0.98
Answer: A
Page 23
2014 Edition V4
0.212
0.300
0.700
0.788
Answer: A
9
A statistical model is being considered for the observed amount of claims, X, which
occur in one year on a class of policies. Only policies on which claims actually arise
are considered.
One of the possible models for X, based on the parameter , is:
P X x
1
x
,
log(1 ) x
Answer: C
10
(0.797, 0.923)
(0.812, 0.908)
(0.858, 0.862)
(0.859, 0.861)
Answer: B
Institute and Faculty of Actuaries
Page 24
11
2014 Edition V4
Past data for two household claims assessors, A and B, is being investigated. The
following table shows the assessors initial estimates of the cost (in units of 100) of
meeting each flood damage claim:
A:
B:
4.6
5.7
6.6
3.4
2.8
4.7
5.8
3.6
2.1
6.5
5.2
3.3
5.9
3.8
3.4
2.4
7.8
7.0
3.5
4.0
1.6
4.4
8.6
2.7
Answer: C
12
A random sample of size 10 is taken from a Normal population with standard deviation
=15 and the sample standard deviation, s, is calculated.
Calculate the value k such that P(S > k) = 0.95, correct to two decimal places.
A
B
C
6.59
9.12
9.92
20.57
Answer: B
Page 25
13
2014 Edition V4
As part of an investigation into whether mortality rates can be used to predict sickness
rates, data on standardised mortality rates and standardised sickness rates were
collected for a sample of 10 regions. The results are shown in the table below:
Region
1
2
3
4
5
6
7
8
9
10
125.2
119.3
125.3
111.7
117.3
100.7
108.8
102.0
104.7
121.1
206.8
213.8
197.2
200.6
189.1
183.6
181.2
168.2
165.2
228.5
Data summaries:
m = 1136.1, m2 = 129,853.03, s = 1934.2, s2 = 377,700.62, ms = 221,022.58
Calculate the value of the correlation coefficient between the mortality rates and the
sickness
rates, correct to three decimal places.
A
B
C
D
0.236
0.365
0.583
0.764
Answer: D
14
Answer: D
15
Identify which of the following correctly describes the nature of the state space and
time space of a Poisson process.
A
B
C
D
Answer: A
Institute and Faculty of Actuaries
Page 26
16
2014 Edition V4
Answer: A
17
Consider the time-homogeneous two-state Markov chain with the following transition
matrix:
1 a a
b 1 b
It is required that this is a valid Markov chain that is both irreducible and periodic.
Identify the values that a and b can take for these conditions to be satisfied.
A
B
C
D
0 a 1 and 0 b 1
0 a 1 and b = 1
a =1 and 0 b 1
a = 1 and b = 1
Answer: D
18
A firm hires out cars and operates from three locations the Airport, the Beach and
the City. Customers may return vehicles to any of the three locations.
The company estimates that the probability of a car being returned to each location,
based on the location where it was hired from, behaves according to the following
matrix:
Car returned to
Car hired from
Airport
Beach City
Airport
0.50
0.25
0.25
Beach
0.25
0.75
0.00
City
0.25
0.25
0.50
Calculate the value of the stationary distribution in this case.
A
B
C
D
Answer: A
Institute and Faculty of Actuaries
Page 27
19
2014 Edition V4
At a certain airport, taxis for the city centre depart from a single terminus. The taxis are
all of the same make and model, and each can seat four passengers (not including the
driver). The terminus is arranged so that empty taxis queue in a single line, and
passengers must join the front taxi in the line. As soon as it is full, each taxi departs.
A strict environmental law forbids any taxi from departing unless it is full. Taxis are so
numerous that there is always at least one taxi waiting in line.
Passengers arrive at the terminus according to a Poisson process with a rate per
minute.
Calculate the expected time a passenger arriving at the terminus will have to wait until
his or her taxi departs.
A
B
C
D
1/ minutes
1.5/ minutes
2.5/ minutes
3/ minutes
Answer: B
20
The mortality of a certain species of fish has been studied. It is known that at ages over
five years the force of mortality for the fish, , is constant. However the variation in
mortality for fish below five years of age is not well understood. The proportion of the
fish that survive to exact age five years, from birth, is denoted as 5P0.
Derive the expression for the proportion of all newly born fish that are expected to die
between exact ages 10 and 15 years.
A
B
C
D
5P0 e
5P0 e
-10
-5
5P0 (e
5P0 (e
-5
- e-10)
- e-5)
-10
Answer: C
Page 28
2014 Edition V4
DISCLAIMER The views expressed in this publication are those of invited contributors and not necessarily those
of the Institute and Faculty of Actuaries. The Institute and Faculty of Actuaries do not endorse any of the views
stated, nor any claims or representations made in this publication and accept no responsibility or liability to any
person for loss or damage suffered as a consequence of their placing reliance upon any view, claim or
representation made in this publication. The information and expressions of opinion contained in this publication
are not intended to be a comprehensive study, nor to provide actuarial advice or advice of any nature and
should not be treated as a substitute for specific advice concerning individual situations. On no account may any
part of this publication be reproduced without the written permission of the Institute and Faculty of Actuaries.
London
7th Floor Holborn Gate 326-330 High Holborn London WC1V 7PP
Tel: +44 (0) 20 7632 2100 Fax: +44 (0) 20 7632 2111
Edinburgh
Maclaurin House 18 Dublin Street Edinburgh EH1 3PP
Tel: +44 (0) 131 240 1300 Fax: +44 (0) 131 240 1313
Oxford
1st Floor Park Central 40/41 Park End Street Oxford OX1 1JD
Tel: +44 (0) 1865 268 200 Fax: +44 (0) 1865 268 211
Hong Kong
2202 Tower Two Lippo Centre 89 Queensway Hong Kong
Tel: +11 (0) 852 2147 9418 Fax: +11 (0) 852 2147 2497
www.actuaries.org.uk
2014 Institute and Faculty of Actuaries
Page 1