• We are pleased to announce that the winner of our Feedback Prize Draw for the Winter 2024-25 session and winning £150 of gift vouchers is Zhao Liang Tay. Congratulations to Zhao Liang. If you fancy winning £150 worth of gift vouchers (from a major UK store) for the Summer 2025 exam sitting for just a few minutes of your time throughout the session, please see our website at https://www.acted.co.uk/further-info.html?pat=feedback#feedback-prize for more information on how you can make sure your name is included in the draw at the end of the session.
  • Please be advised that the SP1, SP5 and SP7 X1 deadline is the 14th July and not the 17th June as first stated. Please accept out apologies for any confusion caused.

Chapter 10 queries

R

rinishj28

Member
1.Why does the poisson model not allow increments?

2. Chapter 10:page 17-Please explain this part:
Under the observational plan described above, the poisson model is not an exact model, since it allows a non zero probability of more than N deaths. But it is often a good approximation, since the probability of more than N deaths is usually negligible

3. Can I say that the reason why the two state model can consider the time at which a transition takes place is cause it uses mu whereas the binomial cannot as it uses a moment estimate to calculate qx?
 
Last edited by a moderator:
(1) I'm not quite sure what you're asking here, sorry.

(2) The Poisson model says that the number of deaths is Poisson distributed. A Poisson distribution can in theory be any positive integer. Since you only have N people that can die, obviously it's impossible to actually get more than N deaths. However, if you actually look at P(deaths>N) it's clear the probability is very low.

(3) The difference is how you estimate the parameters, which comes from the likelihood functions. For binomial, you just need to know in which time interval the life died; for the two state model you need the exact time spent alive so you need the exact time of death.
 
Calum said:
(1) I'm not quite sure what you're asking here, sorry.

(2) The Poisson model says that the number of deaths is Poisson distributed. A Poisson distribution can in theory be any positive integer. Since you only have N people that can die, obviously it's impossible to actually get more than N deaths. However, if you actually look at P(deaths>N) it's clear the probability is very low.

(3) The difference is how you estimate the parameters, which comes from the likelihood functions. For binomial, you just need to know in which time interval the life died; for the two state model you need the exact time spent alive so you need the exact time of death.
Click to expand...

Thank you very much.
 
I think there might be a bit of confusion here over the original Question (1)

Regarding the Poisson model of mortality studied in Chapter 10

While the two state model can be specified so as to allow for increments (ie lives entering the population), this is not possible for the Poisson model.

Regarding a Poisson process as introduced in the earlier chapters

A Poisson process has independent increments by definition.

The independent increments of a Poisson process have nothing to do with the fact that the Poisson model of mortality does not allow for increments,

Good luck!
John
 
You must log in or register to reply here.
Back
Top