Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Actuarial Science Theory Questions > CT 6 Exam Questions > Flashcards

CT 6 Exam Questions Flashcards

You may prefer our related Brainscape-certified flashcards:
Biology 101 flashcards
1
Q

Simplifications usually made in the basic model for short term insurance contracts.

A
  • Model assumes that the mean and standard deviation of the claim amounts are known with certainty.
  • Model assumes that claims are settled as soon as the incident occurs, with no delays.
  • No allowance for expenses is made.
  • No allowance for interest.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

2 Examples of forms of insurance regarded as short term insurance contracts.

A
  • Car insurance

- Contents insurance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Under Quadratic loss we need the ….

A

mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Under All-or-nothing loss we use the…

A

mode

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

9 Characteristics of insurable risks

A
  • Policyholder has an interest in the risk
  • Risk is of a financial nature and reasonably quantifiable

Ideally:

  • Independence of risks
  • probability of event is relatively small
  • pool large numbers of potentially similar risks
  • ultimate limit on liability of insurer
  • moral hazards eliminated as far as possible
  • claim amount must bear some relationship to financial loss
  • sufficient data to reasonably estimate extent of risk / likelihood of occurence
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

6 Key characteristics of a short term insurance contract

A
  • policy lasts for a fixed term
  • option (but no obligation) to renew policy
  • claims are not of fixed amounts
  • the existence of a claim and its amount have to be proven before being settled
  • claim does not bring policy to an end
  • claims that take a long time to settle are known as long-tailed (& short -> short tailed)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Give an advantage of the Box-Muller algorithm relative to the Polar method

A
  • Generated a pair of u1 and u2 - no possibility of rejection
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Give a disadvantage of the Box-Muller algorithm relative to the polar method

A
  • Requires calculation of sin and cos functions which is computationally intensive
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Describe characteristics of Pearson and deviance residuals

A

Pearson residuals are often skewed for non-normal data which makes the interpretation of residual plots difficult.

Deviance residuals are usually more likely to be symmetrically distributed and are preferred for actuarial applications.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Why do insurance companies make use of run-off triangles?

A
  • There is normally a delay between incidents leading to claim and the insurance pay out.
  • Insurance companies need to estimate future claims for their reserve.
  • It makes sense to use historical data to infer future patterns of claims.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

3 Main components of a generalised linear model

A
  • Distribution for the data (Poisson, exponential, gamma, normal or binomial)
  • A linear predictor (function of the covariates that is linear in the parameters)
  • Link function (links the mean of the response variable to the linear predictor)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is meant by a saturated model?

Discuss if it is useful in practice.

A

Saturated model has as many parameters as there are data points and is therefore a perfect fit to the data.

It is not useful from a predictive point of view which is why it is not used in practice.

It is, however, a useful benchmark against which to compare the fit of other models.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

3 Common assumptions underlying a runoff triangle

A
  • Number of claims relating to each development year is a constant proportion of the total claim numbers from the relevant accident year.
  • Claim amounts for each development year are a constant proportion of the total claim amount for the relevant accident year.
  • Claims are fully run off after the last listed development year.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Disadvantage of using truly random numbers

A
  • Generating truly random numbers is not a trivial problem, and may require expensive hardware.
  • It may take a lot of memory to store a large set of randomly generated numbers.
  • The pseudo-random numbers generated by LCG are reproducible, one only need initialize the algorithm with the same seed. This is helpful for comparing the results of different models.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

4 Methods for generating random variates

A
  • Linear congruential generator
  • Inverse transform method
  • Acceptance-rejection method
  • Box-Muller algorithm or the Polar algorithm for generating normal variates.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q 
Bayesian estimator for the loss function:
squared error (quadratic loss)
A

Mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Bayesian estimator for the loss function:

absolute error

A

Median

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Bayesian estimator for the loss function:

Zero-one (all or nothing)

A

Mode

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Proportional reinsurance

A

Under proportional reinsurance, the insurer and reinsurer split the claim in pre-defined proportions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Individual excess of loss

A

The insurer will pay any claim in full up to amount M, the retention level.
Any amount above M will be met by the reinsurer.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Suitable prior for p, with data ~ Binomial(m,p)?

Posterior?

A

p ~ Beta(ɑ, β)

p | X ~ Beta(ɑ + Σx, β + mn - Σx)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Suitable prior for λ, with data ~ Poisson(λ)?

Posterior?

A

λ ~ Gamma(ɑ, β)

λ | X ~ Gamma(ɑ + Σx, β + n)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Suitable prior for p, with data ~ Binomial(m,p)?

Posterior?

A

p ~ Beta(ɑ, β)

p | X ~ Beta(ɑ + Σx, β + mn - Σx)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Assumptions of EBCT Model 1

A
  • For each risk i, the distribution of Xij depends on a parameter θi whose value is the same for each j but is unknown.
  • {Xij | θi} are i.i.d. random variables
  • {θi} are i.i.d. random variables
  • For i≠k, the pairs (Xij, θi) and (Xkm, θk) are i.i.d. random variables.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Advantages of pseudo-random numbers over truly random numbers:

A
  • reproducibility
  • storage (only a seed and a single routine is needed)
  • efficiency (it is very quick to generate several billions of random numbers).
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

Assumptions of EBCT Model 2

A
  • For each risk i, the distribution of Xij depends on a parameter θi whose value is the same for each j but is unknown.
  • {Xij | θi} are INDEPENDENT (not i.i.d. like M1) random variables
  • {θi} are i.i.d. random variables
  • For i≠k, the pairs (Xij, θi) and (Xkm, θk) are INDEPENDENT (not i.i.d. like M1) random variables.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

4 Methods for generating random variates

A
  • Linear congruential generator
  • Inverse transform method
  • Acceptance-rejection method
  • Box-Muller algorithm or the Polar algorithm for generating normal variates.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Disadvantage of using truly random numbers

A
  • Generating truly random numbers is not a trivial problem, and may require expensive hardware.
  • It may take a lot of memory to store a large set of randomly generated numbers.
  • The pseudo-random numbers generated by LCG are reproducible, one only need initialize the algorithm with the same seed. This is helpful for comparing the results of different models.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

4 Methods for generating random variates

A
  • Linear congruential generator
  • Inverse transform method
  • Acceptance-rejection method
  • Box-Muller algorithm or the Polar algorithm for generating normal variates.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Collective Risk Model

A

Aggregate claim amount S, is modelled as the sum of a random number of IID random variables,
S = X1 + X2 + … + XN,
where S is taken to be zero if N=0.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Assumptions underlying the collective risk model

A
  • The random variable N is independent of the random variables Xi.
  • The moments of N and Xi are known.
  • Claims are settled more or less as soon as they occur.
  • Expenses and investment returns are ignored.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Direct Data

A

Data from the risk under consideration

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

Collateral data

A

Data from other similar, but not necessarily identical, risks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Interpretation of E[X2(θ)] (EBCT)

A

Represents the average variability of claim numbers from year to year for a single risk.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

Interpretation of V[m(θ)] (EBCT)

A

Represents the variability of average claim numbers for different risks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

Explain how the value of the credibility factor Z depends on E[X2(θ)] and V[m(θ)].

A

If E[X2(θ)] is higher relative to V[m(θ)], this means there is more variability from year to year than from risk to risk.
More credibility can be placed on the data from other risks leading to a lower value of Z.

On the other hand, if V[m(θ)] is relatively higher this means there is greater variation from risk to risk, so that we can place less reliance on the data as a whole leading to a higher value of Z.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

Loss Function

A

A measure of the “loss” incurred when g(X) is used as an estimator of θ.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

Conjugate prior

A

For a given likelihood, a prior distribution yielding a posterior distribution of the same family as the prior distribution.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
39
Q

Uninformative prior

A

Assumes that the parameter is equally likely to take any possible value.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
40
Q

Prior distribution

A

The prior distribution of θ represents the knowledge available about the possible values of θ before the collection of any sample data.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
41
Q

Posterior distribution

A

The PDF of the prior distribution and the likelihood function combined.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
42
Q

Likelihood function

A

A likelihood function is the same as a joint density function of X1,X2,…Xn | θ.
It is however considered to be a function of θ | X, rather than X | θ.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
43
Q

Ruin Theory: Effect of changing λ

A

An increase in λ will NOT affect the probability of ultimate ruin since the expected aggregate claims, the variance of aggregate claims and the premium rate all increase proportionately in line with λ.

However, it will reduce the time it takes for ruin to occur.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
44
Q

Ruin Theory: Effect of changing var(X)

A

An increase in var(X) will INCREASE the probability of ruin.

It will increase the uncertainty associated with the aggregate claims process without any corresponding increase in premium.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
45
Q

Ruin Theory: Effect of changing E(X)

A

An increase in E(X) will INCREASE the probability of ruin.

The expected aggregate claims and the premium rate both increase proportionately in line with E(X), however, the variance of the aggregate claims amount increases disproportionately
(it increases proportional to E(X)^2).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
46
Q

Ruin Theory: Effect of changing θ

A

Probability of ultimate ruin DECREASES if θ, the premium loading, is increased.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
47
Q

Ruin Theory: Effect of changing U

A

Probability of ultimate ruin DECREASES if the initial surplus U is increased.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
48
Q

Time to the first claim & time between claims

A

If number of claims ~ Poisson( λ )

time between 2 successive claims ~ Exp(λ)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
49
Q

Variable

A

A variable is a type of covariate whose real numerical value enters the predictor directly. (e.g. age)

50
Q

Factor

A

A type of covariate that takes categorical values to which we need to assign numerical values for the purpose of the linear predictor. (e.g. sex)

51
Q

Residual

A

A measure of the difference between the observed values yi and the fitted values ˆµi.

52
Q

Monte Carlo method

A

Involves carrying out a large number of simulations of variates of a distribution, which can then be used to estimate probabilities and moments of the distribution.

53
Q

Explain the main differences between a pure Bayesian estimate and an estimate based on EBCT1

A
  • The pure Bayesian approach makes use of prior information about the distribution of θ1 and EBCT1 does not.
  • The pure Bayesian approach uses only information from the category itself to produce a posterior estimate, whereas the approach under EBCT1 assumes that information from the other categories can give some information about the category in question.
  • The pure Bayesian approach makes precise distributional assumptions about the number of claims, whereas the EBCT1 approach makes no such assumptions.
54
Q

Write down the general form of a statistical model for a claims run-off triangle.

A

C = r.s.x + e

  • r is the development factor for year j, independent of the origin year i, representing the proportion of claims paid by development year j.
  • s is a parameter varying by origin year, representing the exposure.
  • x is a parameter varying by calendar year representing inflation.
  • e is an error term.
55
Q

Explain what is meant by a sequence of independent, identically
distributed (I.I.D.) random variables.

A

Each realisation of the variable is unaffected by previous outcomes and
in turn does not affect future outcomes.
The variables all come from the same distribution with the same
parameters.

56
Q

Explain why an insurance company might purchase reinsurance

A

To protect itself from the risk of large claims.

57
Q

2 Types of reinsurance

A
  • Excess of loss

- Proportional

58
Q

Excess of loss reinsurance (short)

A

Reinsurer pays any amount of a claim above the retention.

59
Q

Proportional reinsurance (short)

A

Reinsurer pays a fixed proportion of any claim.

60
Q

3 steps in the Box-Jenkins approach to fitting an ARIMA time series

A
  • model identification
  • parameter estimation
  • diagnostic checking
61
Q

Explain what is meant by a two player zero-sum game

A

A game with 2 players where whatever one player loses in the game, the other player wins and vice versa

62
Q

Normal distribution:

Natural parameter

A

θ = μ

63
Q

Normal distribution:

Scale parameter

A

ϕ=σ²

64
Q

Poisson Distribution:

Natural parameter

A

θ = log(μ)

65
Q

Poisson Distribution:

Scale parameter

A

ϕ=1

66
Q

Poisson distribution:

b(θ)

A

b(θ) = exp(θ)

67
Q

Binomial Distribution:

Transform to exponential family

A

Z ~ Bin
Let Y = Z/n
So that Z =Yn

68
Q

Binomial Distribution:

Natural parameter

A

θ = log{ μ/(1-μ) }

69
Q

Binomial Distribution:

Scale parameter

A

ϕ=n

70
Q

Binomial Distribution:

b(θ)

A

b(θ) = log{ 1 + exp(θ) }

71
Q

Gamma Distribution:

Natural parameter

A

θ = -1/μ

Where μ = α/λ

72
Q

Gamma Distribution:

Scale parameter

A

ϕ= α

73
Q

Gamma Distribution:

Transform to exponential family

A

Change the parameters from
α and λ to:

α and μ = α/λ

74
Q

Scaled deviance for a particular model M

A

Let ls be the log-likelihood for the saturated model.
Let lm be the log-likelihood for the model

SD = 2(ls - lm)

75
Q

The deviance for the current model

A

Dm, defined such that:

Scaled deviance = Dm / ϕ

Where ϕ is the scale parameter.

76
Q

Lundberg’s Inequality

A

ψ(U) <= exp{ -RU }

77
Q

Adjustment coefficient, R

A

Defined as the unique positive root of:

λ Mx(r) - λ - cr = 0

Where

  • c is the rate of premium income,
  • M is the moment generating function of the of individual claim amounts
  • λ is the parameter of the Poisson process for the claims process
78
Q

2 equations for solving the adjustment coefficient, R

A

λ Mx(r) = λ + cr

Or:
Mx(r) = 1 + (1+θ)m1r

Notice we’ve written c = (1+θ)λm1

79
Q

3 main components of a generalised linear model

A
  • Distribution of the response variable
  • a linear predictor of the covariates
  • link function between the response variable and the linear predictor
80
Q

3 Conditions in order to model aggregate claims as a Binomial(n,p)

A
  • The risk is a constant p for each policy
  • there can only be one claim per policy per year
  • the risk of flood damage is independent from building to building
81
Q

3 Possible causes of non-stationarity

A
  • a deterministic trend (eg exponential or linear growth)
  • a deterministic cycle (eg seasonal effects)
  • a time series is integrated
82
Q

Condition for stationarity using the characteristic polynomial of the autoregression

A

the roots of the characteristic polynomial are all greater than 1.

83
Q

Define the surplus process U(t)

A

Let S(t) denote the total claims up to time t and suppose individual claim amounts follow a distribution X.

The U(t) = U + λt(1 + θ) E(X) − S(t)

84
Q

Define ψ(U, t)

A

ψ(U, t) = P( U(s) < 0 for some s ∈ [0, t])

85
Q

Define ψ(U)

A

ψ(U) = P( U(t) < 0 for some t > 0)

86
Q

Explain how ψ(U, t) depends on λ

A

The probability of ruin by time t will increase as λ increases.

This is because claims and premiums arrive at a faster rate, so that if ruin occurs, it will occur earlier, which leads to an increase in ψ(U, t).

87
Q

Explain how ψ(U) depends on λ

A

The probability of ultimate ruin does not depend on how quickly the claims arrive.

We are not interested in the time when ruin occurs as we are looking over an infinite time horizon.

88
Q

Give 2 examples of exercises where Monte-Carlo simulation should be performed using the same choice of random numbers, explaining your reasoning in each case.

A
  • Testing sensitivity to parameter estimation

- Performance evaluation

89
Q

Why should
[testing sensitivity to parameter estimation]
using Monte-Carlo simulation be performed using the same set of random numbers?

A

We want the results to change as a result of changes to the parameter, not as a result of variations in the random numbers.

90
Q

Why should
[Performance evaluation]
using Monte-Carlo simulation be performed using the same set of random numbers?

A

When comparing two or more schemes which might be adopted we want differences in results to arise from differences between the schemes rather than as a result of variations in the random numbers.

91
Q

Under EBCT1, give a brief interpretation of:

E[S2(θ)]

A

E[S2(θ)] represents the average variability of claim numbers from year to year for a single risk.

92
Q

Under EBCT1, give a brief interpretation of:

V(m(θ))

A

V(m(θ)) represents the variability of the average claim numbers for different risks, i.e. the variability of the means from risk to risk.

93
Q

Essential characteristic of liability insurance

A

To provide indemnity, where the insured - owing to some form of negligence - is legally liable to pay compensation to a 3rd party.

94
Q

5 Examples of liability insurance

A
  • Employer’s liability
  • Motor 3rd party liability
  • Public liability
  • Product liability
  • Professional liability
95
Q

3 Typical perils under Employer’s liability insurance

A
  • Accidents caused by employer negligence
  • Exposure to harmful substances
  • Exposure to harmful working conditions
96
Q

Typical peril under Motor 3rd party liability insurance

A

Road traffic accidents

97
Q

2 Typical perils under product liability insurance

A
  • Faulty design, manufacture or packaging of product

- Incorrect or misleading instructions

98
Q

Typical peril under professional indemnity insurance

A

Wrong medical diagnosis, error in medical operation, etc.

99
Q

Describe the difference between STRICTLY stationary processes and WEAKLY stationary processes

A

Strictly stationary processes have the property that the distribution of (Xt+1, …, Xt+k) is the same as that of (Xt+s+1, …, Xt+s+k) for each t, s and k.

For weak stationarity, only the first 2 moments are needed to satisfy:
E(Xt) =  μ ∀t 
and
cov(Xt
X(t+s) = γ(s) ∀t, s.
100
Q

List 3 statistical tests that you should apply to the residuals after fitting a model to time series data

A
  • the turning point’s test
  • the “portmanteau” Ljung-Box χ2 test
  • inspection of the values of the SACF based on their 95% confidence intervals under the white noise null hypothesis.
101
Q

2 CONDITIONS for a risk to be insurable

A
  • The policyholder must have an interest in the risk being insured, to distinguish between insurance and a wager
  • The risk must be of a financial and reasonably quantifiable nature.
102
Q

X ~ Pareto(α,λ)
What’s the distribution of:
Z = X - M | X > M
(where M is a constant)

A

Z ~ Pareto( α, λ+M )

Prove by using g(z) = fx(z + M)/Fx(M)

103
Q

X ~ Pareto(α,λ)
What’s the distribution of:
Z = kX
(with k >1)

A

Z ~ Pareto( α, λk )

104
Q

The acceptance-rejection method:

C

A

C = max{ h(x)/f(x) }

h(x) being the distribution you want to simulate from.

105
Q

The acceptance-rejection method:

w(x)

A

W(x) = h(x) / { C f(x) }

h(x) being the distribution you want to simulate from.

106
Q

The acceptance-rejection method:

Steps

A

1: Generate u ~ U(0,1)
2: Set x = F-1(u)
3: Generate v ~ U(0,1)
4: If v > w(x) return to step 1 else return x.

107
Q

The acceptance-rejection method:

The proportion of pseudo-random numbers we accept.

A

We accept a proportion 1/C

108
Q

PDF of the reinsurer’s conditional claims distribution

A

W = X - M | X > M

g(w) = fx(w+M) / { 1 - Fx(M) }

109
Q

Coefficient of skewness

A

coeff of skew(Y) = skew(Y) / [Var(Y)]^1.5

110
Q

Credibility factor for the Poisson/Gamma model

A

Z = n/(n+β)

111
Q

Credibility factor for the Normal/Normal model

A

Z = n/{ n + σ²/σ²_0 }

112
Q

Credibility factor for the Binomial/Beta model

A

Z = mn/(ɑ + β + mn)

113
Q

Explain what is meant by a randomised strategy

A

A randomised strategy is where the player randomly chooses between different strategies, rather than adopting a fixed approach.

114
Q

Positive Skew

A

Mean > Median

115
Q

4 factors that affect ψ(U, t) for a given t

A

θ, μ, λ, σ² and initial surplus U

116
Q

Advantage of using discrete, rather than continuous time in probability of ruin

A

Easier to measure, more useful for reporting

117
Q

Disadvantage of using discrete, rather than continuous time in probability of ruin

A

Less information, artificial, can miss time when ruin occurs.

118
Q

Effect of θ on ψ(U, t)

A

Higher θ reduces ψ(U, t) as premiums increase at a quicker rate, so more of a buffer

119
Q

Effect of μ on ψ(U, t)

A

Higher μ increases ψ(U, t) as claims are larger relative to the surplus held.

120
Q

Effect of λ on ψ(U, t)

A

Higher λ increases ψ(U, t) as the process is faster - claims and premiums come in quicker

121
Q

Effect of σ² on ψ(U, t)

A

Higher σ² will typically increase ψ(U, t), assuming that expected premiums are higher than expected claims, since the likelihood of more extreme claims increase.
[but may reduce ψ(U, t) if expected claims are higher than expected returns]

122
Q

Effect of U on ψ(U, t)

A

Higher U reduces ψ(U, t) as there is more of a buffer to withstand claims.

Actuarial Science Theory Questions (2 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions