ACTEX Learning | Learn Today. Lead Tomorrow. ACTEX SOA Exam LTAM Study Manual Study Plus + gives you digital access* to: • Actuarial Exam & Career Strategy Guides • Technical Skill eLearning Tools • Samples of Supplemental Textbooks • And more! *See inside for keycode access and login instructions With Study Plus + Johnny Li, P.h.D., FSA | Andrew Ng, Ph.D., FSA Fall 2018 Edition | Volume I
62
Embed
ACTEX(Please provide this information in case clarification is needed.) Send to: Stephen Camilli ACTEX Learning P.O. Box 715 ... Chapter 6 Net Premium Reserves C6-1 . 6.1 The Prospective
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
ACTEX Learning | Learn Today. Lead Tomorrow.
ACTEX SOA Exam LTAM Study Manual
StudyPlus+ gives you digital access* to:• Actuarial Exam & Career Strategy Guides
• Technical Skill eLearning Tools
• Samples of Supplemental Textbooks
• And more!
*See inside for keycode access and login instructions
No portion of this ACTEX Study Manual may bereproduced or transmitted in any part or by any means
without the permission of the publisher.
Actuarial & Financial Risk Resource Materials
Since 1972
Learn Today. Lead Tomorrow. ACTEX Learning
ACTEX LTAM Study Manual, Fall 2018 Edition
ACTEX is eager to provide you with helpful study material to assist you in gaining the necessary knowledge to become a successful actuary. In turn we would like your help in evaluating our manuals so we can help you meet that end. We invite you to provide us with a critique of this manual by sending this form to us at
your convenience. We appreciate your time and value your input.
Your opinion is important to us
Publication:
Very Good
A Professor
Good
School/Internship Program
Satisfactory
Employer
Unsatisfactory
Friend Facebook/Twitter
In preparing for my exam I found this manual: (Check one)
I found Actex by: (Check one)
I found the following helpful:
I found the following problems: (Please be specific as to area, i.e., section, specific item, and/or page number.)
To improve this manual I would:
Or visit our website at www.ActexMadRiver.com to complete the survey on-line. Click on the “Send Us Feedback” link to access the online version. You can also e-mail your comments to [email protected].
Name:Address:
Phone: E-mail:
(Please provide this information in case clarification is needed.)
Send to: Stephen Camilli ACTEX Learning
P.O. Box 715 New Hartford, CT 06057
NOT FOR PRINT: ADD KEYCODE TEMPLATE PAGE HERE
NOT FOR PRINT: ADD KEYCODE TEMPLATE PAGE HERE
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-1 Preface
Contents
Preface P-7
Syllabus Reference P-10
Flow Chart P-13 Chapter 0 Some Factual Information C0-1
0.1 Traditional Life Insurance Contracts C0-1 0.2 Modern Life Insurance Contracts C0-3 0.3 Underwriting C0-3 0.4 Life Annuities C0-4 0.5 Pensions C0-6 Chapter 1 Survival Distributions C1-1
1.1 Age-at-death Random Variables C1-1 1.2 Future Lifetime Random Variable C1-4 1.3 Actuarial Notation C1-6 1.4 Curtate Future Lifetime Random Variable C1-10 1.5 Force of Mortality C1-12
Exercise 1 C1-20 Solutions to Exercise 1 C1-26 Chapter 2 Life Tables C2-1
2.1 Life Table Functions C2-1 2.2 Fractional Age Assumptions C2-6 2.3 Select-and-Ultimate Tables C2-17 2.4 Moments of Future Lifetime Random Variables C2-28 2.5 Useful Shortcuts C2-38
Exercise 2 C2-42 Solutions to Exercise 2 C2-51 Chapter 3 Life Insurances C3-1
3.1 Continuous Life Insurances C3-2 3.2 Discrete Life Insurances C3-17 3.3 mthly Life Insurances C3-26 3.4 Relating Different Policies C3-29 3.5 Recursions C3-36 3.6 Relating Continuous, Discrete and mthly Insurance C3-42 3.7 Useful Shortcuts C3-45
Exercise 3 C3-48 Solutions to Exercise 3 C3-61
Preface
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-2
Chapter 4 Life Annuities C4-1
4.1 Continuous Life Annuities C4-1 4.2 Discrete Life Annuities (Due) C4-18 4.3 Discrete Life Annuities (Immediate) C4-25 4.4 mthly Life Annuities C4-29 4.5 Relating Different Policies C4-30 4.6 Recursions C4-34 4.7 Relating Continuous, Discrete and mthly Life Annuities C4-37 4.8 Useful Shortcuts C4-43
5.1 Traditional Insurance Policies C5-1 5.2 Net Premium and Equivalence Principle C5-3 5.3 Net Premiums for Special Policies C5-12 5.4 The Loss-at-issue Random Variable C5-18 5.5 Percentile Premium and Profit C5-27 5.6 The Portfolio Percentile Premium Principle C5-38
Exercise 5 C5-40 Solutions to Exercise 5 C5-63 Chapter 6 Net Premium Reserves C6-1
6.1 The Prospective Approach C6-2 6.2 The Recursive Approach: Basic Idea C6-15 6.3 The Recursive Approach: Further Applications C6-24
Exercise 6 C6-33 Solutions to Exercise 6 C6-50 Chapter 7 Insurance Models Including Expenses C7-1
7.1 Gross Premium C7-1 7.2 Gross Premium Reserve C7-5 7.3 Expense Reserve and Modified Reserve C7-13 7.4 Premium and Reserve Basis C7-23 7.5 Actual and Expected Profit C7-28
Exercise 7 C7-34 Solutions to Exercise 7 C7-52
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-3 Preface
Chapter 8 Multiple Decrement Models: Theory C8-1
8.1 Multiple Decrement Table C8-1 8.2 Forces of Decrement C8-5 8.3 Associated Single Decrement C8-10 8.4 Discrete Jumps C8-22
Exercise 10 C10-50 Solutions to Exercise 10 C10-67 Chapter 11 Multiple Life Functions C11-1
11.1 Multiple Life Statuses C11-2 11.2 Insurances and Annuities C11-17 11.3 Dependent Life Models C11-31
Exercise 11 C11-44 Solutions to Exercise 11 C11-64
Preface
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-4
Chapter 12 Pension Plans and Retirement Benefits C12-1
12.1 The Salary Scale Function C12-1 12.2 Pension Plans C12-11 12.3 Setting the DC Contribution Rate C12-14 12.4 DB Plans and Service Table C12-18 12.5 Funding of DB Plans C12-38 12.6 Retiree Health Benefits C12-46
13.1 Profit Vector and Profit Signature C13-1 13.2 Profit Measures C13-12 13.3 Using Profit Test to Compute Premiums and Reserves C13-16
Exercise 13 C13-24 Solutions to Exercise 13 C13-32 Chapter 14 Life Table Estimation C14-1
14.1 Complete and Grouped Data C14-1 14.2 The Kaplan-Meier Estimator C14-5 14.3 The Nelson-Aalen Estimator C14-12 14.4 Parametric Estimation of Death Probabilities C14-14 14.5 Calendar- and Anniversary-based Studies C14-18 14.6 Interval-based Study C14-23 14.7 Parametric Estimation of Q Matrix C14-25
1.1 Numerical Integration A1-1 1.2 Euler’s Method A1-7 1.3 Solving Systems of ODEs with Euler’s Method A1-12 Appendix 2 Review of Probability A2-1
2.1 Probability Laws A2-1 2.2 Random Variables and Expectations A2-2 2.3 Special Univariate Probability Distributions A2-6 2.4 Joint Distribution A2-9 2.5 Conditional and Double Expectation A2-10 2.6 The Central Limit Theorem A2-12 Appendix 3 Illustrative Life Table A3-1
Preface
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-6
Exam LTAM: General Information T0-1 Mock Test 1 T1-1
Solution T1-29 Mock Test 2 T2-1
Solution T2-28 Mock Test 3 T3-1
Solution T3-29 Mock Test 4 T4-1
Solution T4-30 Mock Test 5 T5-1
Solution T5-29 Mock Test 6 T6-1
Solution T6-29 Mock Test 7 T7-1
Solution T7-29 Mock Test 8 T8-1
Solution T8-29
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-7 Preface
Suggested Solutions to MLC May 2012 S-1 Suggested Solutions to MLC Nov 2012 S-17 Suggested Solutions to MLC May 2013 S-29 Suggested Solutions to MLC Nov 2013 S-45 Suggested Solutions to MLC April 2014 S-55 Suggested Solutions to MLC Oct 2014 S-69 Suggested Solutions to MLC April 2015 S-81 Suggested Solutions to MLC Oct 2015 S-97 Suggested Solutions to MLC May 2016 S-109 Suggested Solutions to MLC Oct 2016 S-123 Suggested Solutions to MLC April 2017 S-133 Suggested Solutions to MLC Oct 2017 S-145 Suggested Solutions to MLC April 2018 S-157 Suggested Solutions to Sample Structural Questions S-169
Preface
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-8
Preface
Thank you for choosing ACTEX. In 2018, the SoA launched Exam LTAM (Long-Term Actuarial Mathematics) to replace Exam MLC (Models for Life Contingencies). Compared to its predecessor, Exam LTAM has a much broader coverage. Topics that are newly introduced include the following: (1) Structural settlement and health insurance
You are required to know the calculations involved in structural settlements, which are often used in settling personal injury claims arising from motor vehicle accidents and medical malpractice. You also need to understand various types of health insurance, and know how to price them using complex multiple-state models.
(2) Mortality modeling
You are required to know several sophisticated mortality models, including the Lee-Carter model, the Cairns-Blake-Dowd model, the CBD M7 model, and MP-2014. You also need to know how to apply them in life insurance pricing and valuation.
(3) Retirement benefits
You are required to know how to value retiree health benefits. Although the set-up covered in Exam LTAM is a “simplified” one, the calculations are still quite involved.
(4) Estimation of life tables
You are required to know how life tables (and multiple state models) are estimated using advanced statistical methods. Previously, in Exam MLC, candidates were required to know how to apply them only.
In this brand new study manual, four chapters (Chapters 12, 14, 15 and 16; 216 pages in total) are written to cover these new (and very advanced) topics, ensuring you are best prepared for the exam! As a fact, one author (Professor Johnny Li) of this study manual has strong expertise in many of these exam topics. Professor Li published some 60 papers on mortality modeling and 2 books on personal injury claims. He also taught mortality modeling in a SoA live webcast. Some of his previous work has been adopted into the SoA’s study note (LTAM-21-18) for this exam. Exam LTAM has a very unique format. Among all preliminary exams, Exam LTAM is the only one that includes both multiple-choice and written-answer questions. We know very well that you may be worried about written-answer questions. To help you score the highest mark you can in the written-answer section, this manual contains more than 150 written-answer questions for you to practice. Eight full-length mock exams, written in exactly the same format as that announced in the SoA’s Exam LTAM Introductory Note, are also provided. Many of the written-answer questions in this study manual are highly challenging! We are sorry for giving you a hard time, but we do want you to succeed in the real exam.
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-9 Preface
The learning outcomes stated in the syllabus of Exam LTAM require candidates to be able to interpret a lot of actuarial concepts. This skill is drilled extensively in our practice problems, which often ask you to interpret a certain actuarial formula or to explain your calculation. Also, in Exam LTAM you may be asked to define or describe a certain product, model or terminology. To help you prepare for this type of questions, Chapters 0 and 16 of this study manual provide you summaries of the definitions and descriptions of various products and terminologies. The summaries are written in a “fact sheet” style so that you can remember the key points more easily. Proofs and derivations are another key challenge. In Exam LTAM, you are highly likely to be asked to prove or derive something. You are expected to know, for example, how to derive the Kolmogorov forward differential equations for a certain transition probability. In this new study manual, we do teach (and drill) you how to prove or derive important formulas. This is in stark contrast to some other exam prep products in which proofs and derivations are downplayed, if not omitted. Besides the topics specified in the exam syllabus, you also need to know a range of numerical techniques, for example, Euler’s method and Simpson’s rule, in order to succeed. We know that you may not have even seen these techniques before, so we have prepared a special chapter (Appendix 1) to teach you all of the numerical techniques required for Exam LTAM. In addition, whenever a numerical technique is used, we clearly point out which technique it is, letting you follow our examples and exercises more easily. We have made our best effort to ensure that all topics in the syllabus are explained and practiced in sufficient depth. For your reference, a detailed mapping between this study manual and the readings in the exam syllabus is provided on pages P-11 to P-14. Other distinguishing features of this study manual include:
− All topics in the newest release (as of June 6, 2018) of LTAM-21-18 “Supplementary Note on Long Term Actuarial Mathematics” are fully incorporated into this study manual.
− We use graphics extensively. Graphical illustrations are probably the most effective way to explain formulas involved in Exam LTAM. The extensive use of graphics can also help you remember various concepts and equations.
− A sleek layout is used. The font size and spacing are chosen to let you feel more comfortable in reading. Important equations are displayed in eye-catching boxes.
− Rather than splitting the manual into tiny units, each of which tells you a couple of formulas only, we have carefully grouped the exam topics into 17 chapters and 3 appendices. Such a grouping allows you to more easily identify the linkages between different concepts, which are essential for your success as multiple learning outcomes can be examined in one single exam question.
− Instead of giving you a long list of formulas, we point out which formulas are the most important. Having read this study manual, you will be able to identify the formulas you must remember and the formulas that are just variants of the key ones.
Preface
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-10
− We do not want to overwhelm you with verbose explanations. Whenever possible, concepts and techniques are demonstrated with examples and integrated into the practice problems.
− We explain multiple-state models in great depth. A solid understanding of multiple-state models is crucially important, because many of the learning objectives in Exam LTAM are related to multiple-state models.
− We teach you how to make tedious retiree health benefit calculations more manageable by using a tabular approach. Also, whenever possible, multiple methods (direct methods and computationally efficient algorithms) are presented.
− We write practice problems and mock exam questions in a similar format to the released exam questions. This arrangement helps you comprehend questions more quickly in the real exam.
− All mock exams in this study manual are based on the newest set of examination tables (the Standard Ultimate Life Table), so in the real exam, you can retrieve values from these tables more quickly.
On page P-15, you will find a flow chart showing how different chapters of this manual are connected to one another. You should first study Chapters 0 to 10 in order. Chapter 0 will give you some background factual information; Chapters 1 to 4 will build you a solid foundation; and Chapters 5 to 10 will get you to the core of the exam. You should then study Chapters 11 to 16 in any order you wish. Immediately after reading a chapter, do all practice problems we provide for that chapter. Make sure that you understand every single practice problem. Finally, work on the mock exams. Before you begin your study, please download the exam syllabus from the SoA’s website:
On the last page of the exam syllabus, you will find a link to Exam LTAM Tables, which are frequently used in the exam. You should keep a copy of the tables, as we are going to refer to them from time to time. You should also check the exam home page periodically for updates, corrections or notices. If you find a possible error in this manual, please let us know at the “Customer Feedback” link on the ACTEX homepage (www.actexmadriver.com). Any confirmed errata will be posted on the ACTEX website under the “Errata & Updates” link. Enjoy your study!
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
P-11 Preface
Syllabus Reference
Our Manual AMLCR / SN Chapter 0: Some Factual Information
From the probability function for W, we obtain E(W) and E(W 2
) as follows:
E(W) 0 0.1 1 0.18 2 0.216 3 0.5042.124
E(W 2 ) 02 0.1 12 0.18 22 0.216 32 0.5045.58
This gives Var(W) E(W 2
) – [E(W)]2 5.58 – 2.1242 1.07. Hence, the answer is (A).
[ END ]
In Exam FM, you learnt a concept called the force of interest, which measures the amount of
interest credited in a very small time interval. By using this concept, you valued, for example,
annuities that make payouts continuously. In this exam, you will encounter continuous life
contingent cash flows. To value such cash flows, you need a function that measures the probability
of death over a very small time interval. This function is called the force of mortality.
Consider an individual age x now. The force of mortality for this individual t years from now is
denoted by xt or x(t). At time t, the (approximate) probability that this individual dies within a
very small period of time t is xt t. The definition of xt can be seen from the following
diagram.
1. 5 Force of Mortality
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-13 Chapter 1: Survival Distributions
From the diagram, we can also tell that fx(t) t Sx(t)xtt. It follows that
fx(t) Sx(t)xt t pxxt .
This is an extremely important relation, which will be used throughout this study manual.
Recall that )()()( tStFtf xxx . This yields the following equation:
)(
)(
tS
tS
x
xtx
,
which allows us to find the force of mortality when the survival function is known.
Recall that d ln 1
d
x
x x , and that by chain rule,
)(
)(
d
)(lnd
xg
xg
x
xg for a real-valued function g. We
can rewrite the previous equation as follows:
)].(lnd[dd
)](lnd[
)(
)(
tStt
tS
tS
tS
xtx
xtx
x
xtx
Replacing t by u,
.dexp)(
)0(ln)(lnd
)](ln[dd
)](lnd[d
0
0
0
0
t
uxx
xx
t
ux
x
tt
ux
xux
utS
StSu
uSu
uSu
This allows us to find the survival function when the force of mortality is known.
Time from now
0 t t t
Survive from time 0 to time t: Prob. Sx(t)
Death occurs during t to t t:
Prob. xt t
Death between time t and t t: Prob. (measured at time 0) fx(t)t
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-14
Not all functions can be used for the force of mortality. We require the force of mortality to satisfy
the following two criteria:
(i) xt 0 for all x 0 and t 0.
(ii)
0 duux .
Criterion (i) follows from the fact that xt t is a measure of probability, while Criterion (ii)
follows from the fact that )(lim tS xt
0.
Note that the subscript x t indicates the age at which death occurs. So you may use x to denote
the force of mortality at age x. For example, 20 refers to the force of mortality at age 20. The two
criteria above can then be written alternatively as follows:
(i) x 0 for all x 0.
(ii)
0 dxx .
The following two specifications of the force of mortality are often used in practice.
Gompertz’ law
x Bcx
Makeham’s law
x A Bcx
In the above, A, B and c are constants such that A B, B 0 and c 1.
F O R M U L A
Relations between xt, fx(t) and Sx(t)
fx(t) Sx(t)xt t pxxt, (1.9)
, (1.10)
(1.11)
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-15 Chapter 1: Survival Distributions
Let us study a few examples now.
For a life age x now, you are given that 2(10 )
( )100x
tS t
for 0 t 10.
(a) Find xt .
(b) Find fx(t).
Solution
(a) tt
t
tS
tS
x
xtx
10
2
100
)10(100
)10(2
)(
)(2
.
(b) You may work directly from Sx(t), but since we have found xt already, it would be quicker
to find fx(t) as follows:
fx(t) Sx(t)xt 2(10 ) 2 10
100 10 50
t t
t
.
[ END ]
For a life age x now, you are given
xt 0.002t, t 0.
(a) Is xt a valid function for the force of mortality of (x)?
(b) Find Sx(t).
(c) Find fx(t).
Solution
(a) First, it is obvious that xt 0 for all x and t.
Second, 2
00 0d 0.002 d 0.001x u u u u u
.
Hence, it is a valid function for the force of mortality of (x).
Example 1.6 [Structural Question]
Example 1.7 [Structural Question]
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-16
(b) Sx(t) )001.0exp(d002.0expdexp 2
0
0 tuuu
tt
ux
.
(c) fx(t) Sx(t)xt 0.002texp(0.001t2).
[ END ]
You are given:
(i)
1
0 dexp1 tR tx
(ii)
1
0 d)(exp1 tkS tx
(iii) k is a constant such that S 0.75R.
Determine an expression for k.
(A) ln((1 – qx) / (1 0.75qx))
(B) ln((1 – 0.75qx) / (1 px))
(C) ln((1 – 0.75px) / (1 px))
(D) ln((1 – px) / (1 0.75qx))
(E) ln((1 – 0.75qx) / (1 qx))
Solution
First, R 1 – Sx(1) 1 px qx.
Second,
xk
xkt
txkt
tx peSeueukS
1)1(1dexp1d)(exp1
0
0 .
Since S 0.75R, we have
1 0.75
.1 0.75
kx x
k x
x
e p q
pe
q
Hence, 1
ln ln1 0.75 1 0.75
x x
x x
p qk
q q
and the answer is (A).
[ END ]
Example 1.8 [Course 3 Fall 2002 #35]
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-17 Chapter 1: Survival Distributions
(a) Show that when x Bcx, we have
)1( tx cc
xt gp ,
where g is a constant that you should identify.
(b) For a mortality table constructed using the above force of mortality, you are given that 10p50
0.861716 and 20p50 0.718743. Calculate the values of B and c.
Solution
(a) To prove the equation, we should make use of the relationship between the force of mortality
and tpx.
)1(ln
expdexpdexp00
txt sxt
sxxt ccc
BsBcsp .
This gives g exp(B/lnc).
(b) From (a), we have )1( 1050
861786.0 ccg and )1( 2050
718743.0 tccg . This gives
)861716.0ln(
)718743.0ln(
1
110
20
c
c.
Solving this equation, we obtain c = 1.02000. Substituting back, we obtain g 0.776856 and
B 0.00500.
[ END ]
Now, let us study a longer structural question that integrates different concepts in this chapter.
The function
18000
11018000 2xx
has been proposed for the survival function for a mortality model.
(a) State the implied limiting age .
(b) Verify that the function satisfies the conditions for the survival function S0(x).
Example 1.9 [Structural Question]
Example 1.10 [Structural Question]
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-18
(c) Calculate 20p0.
(d) Calculate the survival function for a life age 20.
(e) Calculate the probability that a life aged 20 will die between ages 30 and 40.
(f) Calculate the force of mortality at age 50.
Solution
(a) Since
018000
11018000)(
2
0
S ,
We have 2 110 – 18000 0 ( – 90)( 200) 0 90 or 200 (rejected).
Hence, the implied limiting age is 90.
(b) We need to check the following three conditions:
(i) 118000
0011018000)0(
2
0
S
(ii) 018000
11018000)(
2
0
S
(iii) 018000
1102)(
d
d0
xxS
x
Therefore, the function satisfies the conditions for the survival function S0(x).
(c) 85556.018000
202011018000)20(
2
0020
Sp
(d)
.15400
15015400
15400
)220)(70(
18000
)20020)(2090(18000
)20020)(2090(
)20(
)20()(
2
0
020
xxxx
xx
S
xSxS
(e) The required probability is
10|10q20 10p20 – 20p20
11688.077922.089610.015400
)22020)(2070(
15400
)22010)(1070(
(d)
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-19 Chapter 1: Survival Distributions
(f) First, we find an expression for x.
)200)(90(
1102
18000
)200)(90(18000
2110
)(
)(
0
0
xx
xxx
x
xS
xSx .
Hence, 50 )20050)(5090(
110502
0.021.
[ END ]
You may be asked to prove some formulas in the structural questions of Exam LTAM. Please
study the following example, which involves several proofs.
Prove the following equations:
(a) xt ptd
d t pxx+t
(b) t
sxxsxt spq
0 d
(c) 1d
0
x
txxt tp
Solution
(a) LHS )(dd
d)dexp()dexp(
d
d
d
d
0
0
0 txxt
t
sx
t
sx
t
sxxt pst
sst
pt
RHS
(b) LHS t qx Pr(Tx t) spssft
sxxs
t
x dd)(
0
0 RHS
(c) LHS ttftpx
xtx
x
xt d)(d
0
0
xqx 1 RHS
[ END ]
Example 1.11 [Structural Question]
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-20
1. [Structural Question] You are given:
0
1( )
1S t
t
, t 0.
(a) Find F0(t).
(b) Find f0(t).
(c) Find Sx(t).
(d) Calculate p20.
(e) Calculate 10|5q30. 2. You are given:
2
0
(30 )( )
9000
tf t
, for 0 t 30
Find an expression for t p5. 3. You are given:
0
20( )
200
tf t
, 0 t 20.
Find 10. 4. [Structural Question] You are given:
1
100x x
, 0 x 100.
(a) Find S20(t) for 0 t 80.
(b) Compute 40p20.
(c) Find f20(t) for 0 t 80. 5. You are given:
2
100x x
, for 0 x 100.
Find the probability that the age at death is in between 20 and 50. 6. You are given:
(i) S0(t)
t1 0 t , 0.
(ii) 40 220.
Find .
Exercise 1
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-21 Chapter 1: Survival Distributions
7. Express the probabilities associated with the following events in actuarial notation.
(a) A new born infant dies no later than age 35.
(b) A person age 10 now survives to age 25.
(c) A person age 40 now survives to age 50 but dies before attaining age 55.
Assuming that S0(t) e0.005t for t ≥ 0, evaluate the probabilities. 8. You are given:
2
0 ( ) 1100
tS t
, 0 t 100.
Find the probability that a person aged 20 will die between the ages of 50 and 60. 9. You are given:
(i) 2px 0.98
(ii) px2 0.985
(iii) 5qx0.0775
Calculate the following:
(a) 3px
(b) 2px3
(c) 2|3qx 10. You are given:
qxk 0.1(k 1), k 0, 1, 2, …, 9.
Calculate the following:
(a) Pr(Kx 1)
(b) Pr(Kx 2) 11. [Structural Question] You are given x for all x 0.
(a) Find an expression for Pr(Kx k), for k 0, 1, 2, …, in terms of and k.
(b) Find an expression for Pr(Kx k), for k 0, 1, 2, …, in terms of and k.
Suppose that 0.01.
(c) Find Pr(Kx 10).
(d) Find Pr(Kx 10).
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-22
12. Which of the following is equivalent to
t
uxxu up
0 d ?
(A) t px
(B) t qx
(C) fx(t)
(D) – fx(t)
(E) fx(t)xt
13. Which of the following is equivalent to d
d t xpt
?
(A) –t px xt
(B) xt
(C) fx(t)
(D) –xt
(E) fx(t)xt 14. (2000 Nov #36) Given:
(i) x F e2x, x 0
(ii) 0.4p0 0.50
Calculate F.
(A) –0.20
(B) –0.09
(C) 0.00
(D) 0.09
(E) 0.20 15. (CAS 2004 Fall #7) Which of the following formulas could serve as a force of mortality?
(I) x Bcx, B 0, C 1
(II) x a(b x)1, a 0, b 0
(III) x (1 x)3, x 0
(A) (I) only
(B) (II) only
(C) (III) only
(D) (I) and (II) only
(E) (I) and (III) only
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-23 Chapter 1: Survival Distributions
16 (2002 Nov #1) You are given the survival function S0(t), where
(i) S0(t) 1, 0 t 1
(ii) S0(t)100
1te
, 1 t 4.5
(iii) S0(t) 0, 4.5 t
Calculate 4.
(A) 0.45
(B) 0.55
(C) 0.80
(D) 1.00
(E) 1.20
17. (CAS 2004 Fall #8) Given 1/ 2
0 ( ) 1100
tS t
, for 0 t 100, calculate the probability that
a life age 36 will die between ages 51 and 64. (A) Less than 0.15
(B) At least 0.15, but less than 0.20
(C) At least 0.20, but less than 0.25
(D) At least 0.25, but less than 0.30
(E) At least 0.30 18. (2007 May #1) You are given:
(i) 3p70 0.95
(ii) 2p71 0.96
(iii) 107.0d 75
71 xx
Calculate 5p70.
(A) 0.85
(B) 0.86
(C) 0.87
(D) 0.88
(E) 0.89
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-24
19. (2005 May #33) You are given:
0.05 50 60
0.04 60 70x
x
x
Calculate 4|14q50 .
(A) 0.38
(B) 0.39
(C) 0.41
(D) 0.43
(E) 0.44 20. (2004 Nov #4) For a population which contains equal numbers of males and females at birth:
(i) For males, mx 0.10, x 0
(ii) For females, fx 0.08, x 0
Calculate q60 for this population. (A) 0.076
(B) 0.081
(C) 0.086
(D) 0.091
(E) 0.096 21. (2001 May #28) For a population of individuals, you are given:
(i) Each individual has a constant force of mortality.
(ii) The forces of mortality are uniformly distributed over the interval (0, 2).
Calculate the probability that an individual drawn at random from this population dies within one year. (A) 0.37
(B) 0.43
(C) 0.50
(D) 0.57
(E) 0.63
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-25 Chapter 1: Survival Distributions
22. [Structural Question] The mortality of a certain population follows the De Moivre’s Law; that is
xx
1, x .
(a) Show that the survival function for the age-at-death random variable T0 is
x
xS 1)(0 , 0 x .
(b) Verify that the function in (a) is a valid survival function.
(c) Show that
xpxt
11 , 0 t – x, x .
23. [Structural Question] The probability density function for the future lifetime of a life age 0
is given by
10 )()(
xxf , , 0
(a) Show that the survival function for a life age 0, S0(x), is
xxS )(0 .
(b) Derive an expression for x.
(c) Derive an expression for Sx(t).
(d) Using (b) and (c), or otherwise, find an expression for fx(t). 24. [Structural Question] For each of the following equations, determine if it is correct or not.
If it is correct, prove it.
(a) t|uqx tpx uqxt
(b) tuqx tqx × uqxt
(c) )(d
dtxxxtxt pp
x
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-27 Chapter 1: Survival Distributions
5. Our goal is to find Pr(20 T0 50) S0(20) – S0(50).
Given the force of mortality, we can find the survival function as follows:
2
0
0
0 0
1001)
100
100ln2exp())]100[ln(2exp(
d100
2expdexp)(
ttu
uu
utS
t
tt
u
So, the required probability is (1 – 20/100)2 – (1 – 50/100)2 0.82 – 0.52 0.39.
6. xx
x
xS
xSx
1
11
)(
)(
1
0
0 .
We are given that 40 220. This implies 2
40 20
, which gives 60.
7. (a) The probability that a new born infant dies no later than age 35 can be expressed as 35q0.
[Here we have “q” for a death probability, x 0 and t 35.]
Further, 35q0 F0(35) 1 – S0(35) 0.1605.
(b) The probability that a person age 10 now survives to age 25 can be expressed as 15p10. [Here we have “p” for a survival probability, x 10 and t 25 – 10 15.]
Further, we have 15p10 S10(15) )15(
)25(
0
0
S
S0.9277.
(c) The probability that a person age 40 now survives to age 50 but dies before attaining age 55 can be expressed as 10|5q40. [Here, we have “q” for a (deferred) death probability, x 40, t 50 – 40 10, and u 55 – 50 5.]
Further, we have 10|5q40 S40(10) – S40(15) 0
0
(50)
(40)
S
S 0
0
(55)
(40)
S
S = 0.0235.
8. The probability that a person aged 20 will die between the ages of 50 and 60 is given by
30|10q20 30p20 – 40p20 S20(30) – S20(40).
2
2
2
0
020 80
1
100
201
100
201
)20(
)20()(
t
t
S
tStS .
So, S20(30) 64
25
80
301
2
, S20(40)
64
16
80
401
2
. As a result, 30|10q20 9/64.
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
Hence, Pr(Kx 2) 0.1 0.18 0.216 0.496. 11. (a) Given that x for all x 0, we have t px et, px e and qx 1 – e.
Pr(Kx k) k|qx kpx qxk e k (1 – e).
(b) Pr(Kx k) k1qx 1 k1px 1 e(k 1).
(c) When 0.01, Pr(Kx 10) e10 0.01(1 – e0.01) 0.0090.
(d) When 0.01, Pr(Kx 10) 1 – e(10 + 1) 0.01 0.1042. 12. First of all, note that upx xu in the integral is simply fx(u).
)Pr(d)(d
0
0 tTuufup x
t
x
t
uxxu Fx(t) t qx.
Hence, the answer is (B).
13. Method I: We use t px = 1 t qx. Differentiating both sides with respect to t,
)()(d
d
d
d
d
dtftF
tq
tp
t xxxtxt .
Noting that fx(t) t px x+t, the answer is (A).
Method II: We differentiate t px with respect to t as follows:
.dd
ddexp
dexpd
d)(
d
d
d
d
0
0
0
t
ux
t
ux
t
uxxxt
ut
u
ut
tSt
pt
Recall the fundamental theorem of calculus, which says that )(d)(d
d
tguug
t
t
c . Thus
txxttx
t
uxxt pupt
)(dexp
d
d
0 .
Hence, the answer is (A).
(b)
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-29 Chapter 1: Survival Distributions
14. First, note that
0.4 0.4 20.4 0 0 0
0.5 exp d exp ( )duup u F e u .
The exponent in the above is 0.4
0.4 2 2
00
1( )d
2
0.4 1.11277 0.5
0.4 0.61277
u uF e u Fu e
F
F
As a result, 0.5 e0.4F0.61277, which gives F 0.2. Hence, the answer is (E). 15. Recall that we require the force of mortality to satisfy the following two criteria:
(i) x 0 for all x 0, (ii) 0
dx x
.
All three specifications of x satisfy Criterion (i). We need to check Criterion (ii).
We have
00
dln
xx Bc
Bc xc
,
00d ln( )
ax a b x
b x
,
and
3 200
1 1 1d
(1 ) 2(1 ) 2x
x x
.
Only the first two specifications can satisfy Criterion (ii). Hence, the answer is (D).
[Note: x Bcx is actually the Gompertz’ law. If you knew that you could have identified that x Bcx can serve as a force of mortality without doing the integration.]
16. Recall that )(
)(
tS
tS
x
xtx
.
Since we need 4, we use the definition of S0(t) for 1 t 4.5:
0 ( ) 1100
teS t ,
100)(0
tetS .
As a result,
4
4
4 4 4100 1.203
1001
100
ee
e e
. Hence, the answer is (E).
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-30
17. The probability that a life age 36 will die between ages 51 and 64 is given by
S36(15) – S36(28).
We have 8
64
64
64
100
361
100
361
)36(
)36()(
2/1
2/1
2/1
0
036
tt
t
S
tStS
.
This gives S36(15)8
7 and S36(28)
8
6 . As a result, the required probability is
S36(15) – S36(28) 1/8 0.125. Hence, the answer is (A). 18. The computation of 5p70 involves three steps.
First, 3 7070
2 71
0.950.9896
0.96
pp
p .
Second, 75
71 d 0.107
4 71 0.8985x x
p e e .
Finally, 5p70 0.9896 0.8985 0.889. Hence, the answer is (E). 19. 4p50 e0.05 4 0.8187
10p50 e0.05 10 0.6065
8p60 e0.04 8 0.7261
18p50 10p50 8p60 0.6065 0.7261 0.4404
Finally, 4|14q50 4p50 – 18p50 0.8187 – 0.4404 0.3783. Hence, the answer is (A). 20. For males, we have
0 0d 0.10d 0.10
0 ( )t tm
u u um tS t e e e .
For females, we have
0 0d 0.08d 0.08
0 ( )t tf
u u uf tS t e e e .
For the overall population,
0.1 60 0.08 60
0 (60) 0.0053542
e eS
,
and
0.1 61 0.08 61
0 (61) 0.004922
e eS
.
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-31 Chapter 1: Survival Distributions
Finally, 060 60
0
(61)1 1 0.081
(60)
Sq p
S . Hence, the answer is (B).
21. Let M be the force of mortality of an individual drawn at random, and T be the future lifetime
of the individual. We are given that M is uniformly distributed over (0, 2). So the density function for M is fM() 1/2 for 0 2 and 0 otherwise.
This gives
0
2
0
2
2
Pr( 1)
E[Pr( 1| )]
Pr( 1| ) ( )d
1(1 ) d
21
(2 1)21
(1 )20.56767.
M
T
T M
T M f
e
e
e
Hence, the answer is (D). 22. (a) We have, for 0 x ,
x
esss
sxSx
xxx
s
1)]exp([ln()d1
exp()dexp()()1ln(
0
0
0 0 .
(b) We need to check the following three conditions:
(i) S0(0) 1 – 0/ 1
(ii) S0() 1 – / 0
(iii) S 0() 1/ 0 for all 0 ≤ x < , which implies S0(x) is non-increasing.
Hence, the function in (a) is a valid survival function.
(c) x
t
x
txx
tx
xS
txSpxt
11
1
)(
)(
0
0 , for 0 t – x, x .
23. (a)
x x
xs
sssfxFxS
0 0 1000 )(d
)(1d)(1)(1)(
.
(b) xxS
xfx
)(
)(
0
0 .
Chapter 1: Survival Distributions
Actex Learning | Johnny Li and Andrew Ng | SoA Exam LTAM
C1-32
(c) .)(
)()(
0
0
tx
x
x
txxS
txStS x
(d) txtx
xtStf txxx
)()( .
24. (a) No, the equation is not correct. The correct equation should be t|uqx tpx × uqxt. (b) No, the equation is not correct. The correct equation should be tupx tpx × upxt. (c) Yes, the equation is correct. The proof is as follows: