We'd like to remind Forumites to please avoid political debate on the Forum... Read More »
We're aware that some users are experiencing technical issues which the team are working to resolve. See the Community Noticeboard for more info. Thank you for your patience.
📨 Have you signed up to the Forum's new Email Digest yet? Get a selection of trending threads sent straight to your inbox daily, weekly or monthly!
Premium Bonds Calculator Discussion Area
Options

Former_MSE_Dan
Posts: 1,593 Forumite

To discuss premium bonds themselves see the
Premium Bonds: Are they worth it? Discussion
linked from the
Premium Bonds: Are they worth it? Article
Premium Bonds: Are they worth it? Discussion
linked from the
Premium Bonds: Are they worth it? Article
To take part in this discusison
click reply.
click reply.
Former MSE team member
0
Comments
-
This article appeared just as I was looking at Premium Bonds attracted by their tax position for higher rate tax payers and the ability to buy them in regular instalments unlike their index-linked savings certificates.
I've posted another thread as I am now completely puzzled on what to do with my £500/month that I intend to invest. Being a higher rate tax payer is a pain.0 -
I read this piece in the Sunday Times with interest. I have no doubt that the clever maths may well be needed to create the database you have outlined but I think there is a far simpler method which requires only the distribution probability of winning a prize for a given stake and the actual average prize awarded - both obtainable from Ernie. Calculating the expectation value is then very straightforward.
Take my own case: I have a £30k stake which should yield 1.15 prizes a month. My own average prize over the last couple of years has been £60 which therefore gives 1.15*60*12= 828 for the year - or 4.6% equivalent for higher rate tax payer. In practice my prize rate has been 1.25 and that brings the higher rate equivalent up to 5%.
For the general case we need the actual average prize - I haven't had time to go and get that but it should be a simple calculation.
As to the odds of winning a million: surely if there is a total of £36bn staked then by simple division for a £30k stake I have 1 in 1.2m chance each month.
Or maybe I'm just lucky? :beer:0 -
By the way....
Putting that last bit another way....
Statistically speaking I am certain to win a million once if I keep my £30k in there for 100000 years.
Maybe I should sup up...0 -
OK I pushed myself - using the numbers available from Ernie's website for the prize distibution the forecast average prize for September is almost exactly £76 - so for a £30k stake the expectation value for the year is 1.15 * 76 *12 = £1048 or 3.5% or 5.83% for a higher rate taxpayer.
NB this is the expectation value - what you actually get won't equate to this in practice due to the scarcity of the higher prizes you will likely make a bit less than this unless of course you hit a big one.
In my book that means this is a worthwhile bet despite the impression given in the Sunday Times.
btw I forgot there are 2 prizes of £1m each month so that means I only have to wait 50000 years to be statistically sure I get my prize.0 -
The_Bleurk wrote: »By the way....
Putting that last bit another way....
Statistically speaking I am certain to win a million once if I keep my £30k in there for 100000 years.
Maybe I should sup up...
The reason that this is the case can be modelled with, say, dice. You have a 1 in 6 chance of rolling a 6 each time, which means you have a 5/6 chance of not rolling a 6. The chance of rolling 2 dice and getting no 6 is (5/6)^2, and this extends to the general case of:
P(No 6 in N dice) = (5/6)^N
Or, to rephrase:
P(1 or more 6s in N dice) = 1 - (5/6)^N
Now, the Limit of (5/6)^N as N tends to infinity is 1, but the value itself is never actually 1 for any finite value of N. As such, there is a slim chance that even if you rolled billions of dice you might not roll a single 6. A very small chance, but a chance anyway.
For the specific situation you mentioned, the probability boils down to:
P(winning the big prize if playing for N months) = 1 - ((1-1/1.2E6))^N
So if N = 1200000 then we have:
P = 63%
So, playing for 100000 years only gets you a 63% chance of winning the jackpot if your figures are right!I am a Chartered Financial Planner
Anything I say on the forum is for discussion purposes only and should not be construed as personal financial advice. It is vitally important to do your own research before acting on information gathered from any users on this forum.0 -
why doesn't the calculator give me a chance of winning the million? I thought every number has an equal chance of winning.0
-
maths isn't my best point and now it's gone over my head0
-
The_Bleurk wrote: »Statistically speaking I am certain to win a million once if I keep my £30k in there for 100000 years.
Nope - You are never certain to win a million or in fact any prize.
Each draw is independent so you have the same chance of winning in each draw - it makes no difference if you haven't won anything in the previous 100000 years.
To calculate probabilities in this sort of scenario multiply the probabilities of not winning and subtract from 1 - obviously this can never result in 1 (certainty). It becomes increasingly les likely to not win as you consider more draws - but the probability for the next draw doesn't change.0 -
maybe I should have said:
on average I should win a million once in 50000 years...
In any event it seems like a good bet to me given that I get my stake back whenever I want. I would like to retrieve it in 50000 years...
Not too much to ask?0
This discussion has been closed.
Confirm your email address to Create Threads and Reply

Categories
- All Categories
- 350.8K Banking & Borrowing
- 253K Reduce Debt & Boost Income
- 453.5K Spending & Discounts
- 243.8K Work, Benefits & Business
- 598.6K Mortgages, Homes & Bills
- 176.8K Life & Family
- 257K Travel & Transport
- 1.5M Hobbies & Leisure
- 16.1K Discuss & Feedback
- 37.6K Read-Only Boards