How can you calculate Pure IBNR and IBNER from the IBNR within 5 minutes?
 Get link
 Other Apps
Calculation of IBNER and Pure IBNR
This article gives a brief about the different
forms of IBNR component and its estimation that we generally come across in the
General Insurance industry.
Hopefully everyone is already familiar with
the other terms of GI before reading this article. It will be useful to familiarize
yourself with the following terms before reading this article any further
(Ultimate Claims, Reported Claims, Incurred, Accident/Underwriting/Reporting
Year Cohort, Chain Ladder Estimate, BF Estimate).
Before we get to the estimation, let us
first clear our understandings of the various terms.
Incurred but not reported (IBNR): For a particular year the actuaries estimate the Ultimate Cost
(generally referred as the Ultimate Claims) for all the business that has been written.
This ultimate cost can be divided into Incurred Claims (Reported claim amount)
and IBNR.
IBNR can be further split down to two
categories:
1)
Incurred but not enough reported
(IBNER): This portion of the IBNR refers to the not reported amount for the
already reported claims. To simply this let us take an example: A company
received a claim for Motor Insurance of Rs. 10,000 which will be recorded as
the Incurred Claim amount. However based on experience the Actuary estimates that
the final cost of the claim would be Rs. 15,000. Hence the difference of Rs.
5,000 is treated as the IBNER component of the claim.
2)
Pure IBNR: This portion of the
IBNR is the component that refers to the claims cost for the claims which have
not been reported till now. We can also understand this as new claims which are
not in the book but are expected to be experienced. For ex – A company has
written some business in an area against which it has received 10 claims.
However based on experience the Actuary estimates these claims to be 15 in
total. Hence the cost of the additional 5 claims is considered as Pure IBNR.
When we estimate the Ultimate Claims for
General Insurance classes on a Reporting Year cohort we will be estimating the
final cost of the Claims which have already been reported to the company. Hence
any IBNR suggested under this methodology would all be IBNER as we would not be
expecting to incur any further reported claims under this basis.
However, when we perform projections on an
Underwriting Year/Accident Year basis we face the issue of IBNER and Pure IBNR.
Please note that in general there is no need for the Actuary to split his
results between IBNER and Pure IBNR but we still need to have an understating
to explain the IBNR component in totally to other stakeholders.
A general method used to separate out the
IBNER and Pure IBNR component can be based on the Average Cost per Claim Method
(ACPC).
When we estimate the ultimate claims based on Incurred/Paid amount in general for a RunOff triangle we do not go into the separation of the Claims Cost by each Claim. We can also estimate the ultimate claims cost by the ACPC method. The estimation would require estimate the ultimate claim count to be the expected and also estimating the ultimate average claim cost expected.
When we estimate the ultimate claims based on Incurred/Paid amount in general for a RunOff triangle we do not go into the separation of the Claims Cost by each Claim. We can also estimate the ultimate claims cost by the ACPC method. The estimation would require estimate the ultimate claim count to be the expected and also estimating the ultimate average claim cost expected.
Let us understand this with an example.
Suppose we have the reported claims and
incurred amounts data for a few Accident Years. Using the standard techniques
we have estimated the ultimate number of claims for each of the AYs. These can
be seen below:
AY

Reported Claims

Ultimate Claims

Unreported claims

2015

140

140

0

2016

150

150

0

2017

140

145

5

2018

135

150

15

2019

100

155

55

Further, based on the Incurred Amounts we
have estimated the current Average Cost per Claim (Incurred Amounts/Reported
Claims). Again using the standard estimation techniques we will estimate the
ultimate ACPC for each of the AYs.
AY

ACPC

Ultimate ACPC

2015

1000

1000

2016

1100

1100

2017

1050

1100

2018

900

1150

2019

700

1145

Based on the above two tables we can
estimate the IBNR component for these claims.
AY

Incurred Amount

Ultimate Amount

IBNR

2015

₹ 1,40,000.00

₹ 1,40,000.00

₹ 

2016

₹ 1,65,000.00

₹ 1,65,000.00

₹ 

2017

₹ 1,47,000.00

₹ 1,59,500.00

₹ 12,500.00

2018

₹ 1,21,500.00

₹ 1,72,500.00

₹ 51,000.00

2019

₹ 70,000.00

₹ 1,77,475.00

₹ 1,07,475.00

Incurred
Amount = Reported Claims * ACPC
Ultimate Costs = Ultimate Claims * Ultimate ACPC
IBNR = Ultimate Costs – Incurred Amount
Ultimate Costs = Ultimate Claims * Ultimate ACPC
IBNR = Ultimate Costs – Incurred Amount
Please note that the IBNR estimated in the
table above is the total IBNR (IBNER + Pure IBNR). Based on the information
above we can estimate the IBNER and Pure IBNR components:
AY

IBNER

Pure IBNR

IBNR

2015

₹ 

₹ 

₹ 

2016

₹ 

₹ 

₹ 

2017

₹ 7,000.00

₹ 5,500.00

₹ 12,500.00

2018

₹ 33,750.00

₹ 17,250.00

₹ 51,000.00

2019

₹ 44,500.00

₹ 62,975.00

₹ 1,07,475.00

IBNER
= (Ultimate ACPC – ACPC) * Reported Claims
Pure IBNR = Ultimate ACPC * Unreported Claims
IBNR = IBNER + Pure IBNR
Pure IBNR = Ultimate ACPC * Unreported Claims
IBNR = IBNER + Pure IBNR
This is the most straightforward method to
estimate the IBNR components. There have been various researches and papers
written to estimate this using other statistical techniques as well. Interested
people can look at the papers available on CAS/IFoA websites or any other
Actuarial Forums.
Follow Writer of this article on LinkedIn : Ujjaval Agarwal
Note: On behalf of Actuary Sense, i would like to thank Ujjaval Agarwal for writing this article in a very easy language which is easily interpreted by our readers. Mr. Ujjaval is an Actuarial Consultant with RSA and prior to that associated with PwC
Follow me on LinkedIn: Kamal Sardana
Comments
Popular posts from this blog
Role of Generalised Linear Model in Non Life Pricing  Phase1
We will cover a series of topics relating to how Non Life Pricing is done through GLM.
But first let's see what is GLM
Generalised Linear Model Before Jumping on to what is GLM, let’s see what is Linear models 1.Linear Models:
Let’s take the example of Weight (Y) and Height (X). The aim of linear models is to find the line of best fit through the data points.
Here is your X axis is Height and Y axis is your Weight. Y = B0 + B1x
Line of Best Fit is B0 + B1x where B0 is intercept on Y axis and B1 is the gradient.
Now the question is how that line comes?
Well, line is chosen in such a way to minimize the sum of squared error terms where error terms are distances from data points to straight line, error terms are normally distributed with mean 0 and variance σ2.
2.Multiple Linear Regression:
We can extend our model to allow for other predictive variables. For example, we can decide that Weight can depend on height and calories consumed per day both. So here we cannot find the line of b…
But first let's see what is GLM
Generalised Linear Model Before Jumping on to what is GLM, let’s see what is Linear models 1.Linear Models:
Let’s take the example of Weight (Y) and Height (X). The aim of linear models is to find the line of best fit through the data points.
Here is your X axis is Height and Y axis is your Weight. Y = B0 + B1x
Line of Best Fit is B0 + B1x where B0 is intercept on Y axis and B1 is the gradient.
Now the question is how that line comes?
Well, line is chosen in such a way to minimize the sum of squared error terms where error terms are distances from data points to straight line, error terms are normally distributed with mean 0 and variance σ2.
2.Multiple Linear Regression:
We can extend our model to allow for other predictive variables. For example, we can decide that Weight can depend on height and calories consumed per day both. So here we cannot find the line of b…
CFM vs UDD vs Balducci
Life Tables: It is a computational tool based on a specific survival model. Our
task is to generate a survival model and our output will be a life table. Life
table is based on Unitary method. lx= Expected no. of lives at age x dx= Expected no. of deaths between exact age x and exact
age x+1 NOTE: We call it expected and not actual because most of the values
will be in decimal too, so how can it be actual.
But there is a limitation of Life Tables: It is defined only for integer ages. If we have to calculate probability of death/survival at any noninteger age we will use 3 assumptions: 1.CFM= Constant Force of Mortality 2.UDD= Uniform Distribution of death 3.Balducci assumption
1.CFM ·It assumes that the force of mortality is constant, i.e. ux+t = ux ·If the force of mortality of a newborn is constant, it means that the expected future lifetime of this life is 1/μ no matter what age he is in. ·Survival Function in this case will decrease exponentially. ·If 0<s<t<1 then tspx+s = tpx/spx …
But there is a limitation of Life Tables: It is defined only for integer ages. If we have to calculate probability of death/survival at any noninteger age we will use 3 assumptions: 1.CFM= Constant Force of Mortality 2.UDD= Uniform Distribution of death 3.Balducci assumption
1.CFM ·It assumes that the force of mortality is constant, i.e. ux+t = ux ·If the force of mortality of a newborn is constant, it means that the expected future lifetime of this life is 1/μ no matter what age he is in. ·Survival Function in this case will decrease exponentially. ·If 0<s<t<1 then tspx+s = tpx/spx …
MWRR vs TWRR which is better and Why ?
We can decide between various projects that which one
is better and which one is not on the basis of different criteria such as: NPV, IRR, DPP But how can we measure the investment performance?
Well, there are basically three measures of investment performance: 1.Money
Weighted rate of return (MWRR) 2.Time
Weighted rate of return (TWRR) 3.Linked
internal rate of return (LIRR)
Follow us on LinkedIn : Actuary Sense Follow me on LinkedIn: Kamal Sardana
It is necessary to measure the performance of a fund which can be a pension fund, funds of an insurance company or funds of an asset management company. It is important for those who are responsible for the investment funds for example: trustees in case of pension fund will monitor how fund is performing i.e. they find out the rate of return of the fund and then compare it with performance of other funds. Before looking at different measures, let’s see some definitions: a.)Income generate by fund: it includes interest payments, dividends received fr…
Follow us on LinkedIn : Actuary Sense Follow me on LinkedIn: Kamal Sardana
It is necessary to measure the performance of a fund which can be a pension fund, funds of an insurance company or funds of an asset management company. It is important for those who are responsible for the investment funds for example: trustees in case of pension fund will monitor how fund is performing i.e. they find out the rate of return of the fund and then compare it with performance of other funds. Before looking at different measures, let’s see some definitions: a.)Income generate by fund: it includes interest payments, dividends received fr…
Nice article, Ujjaval. Keep it up.
ReplyDelete