- Can a sample tell you if a betting approach is profitable?
- Sample size… how much is enough?
You’ve started a new approach and 50 bets down the track, it’s showing a profit. You’re thinking about increasing the stakes but it’s just 50 bets and you’re not sure whether you’ve genuinely found the golden goose, or just been lucky.
Sample size is one of the trickiest issues in punting – how many bets is enough? There’s no simple solution but luckily, we have Monte Carlo simulations (essentially asking a computer to produce thousands of results). It’s the best way to work it out.
Before we dive into the numbers, there are some important home truths to recognise.
Research is important (required) but most of the time, there is no way to know whether your method is truly profitable (or not) other than real results bet with your own cold hard cash. This is one of the many reasons to keep an accurate record of your bets.
Variance is a key factor. Even when you know you have an edge (100% guaranteed), variance can produce a negative result, simply due to bad luck, randomness, etc. Vice versa is also true. A losing method can produce a positive result due to good luck.
And finally, the key question is not whether your method is profitable or not. It’s what is the CHANCE that your method is profitable. Your set of results is one set of 50, 100 or 1000 bets (however many it is). You might have been lucky, unlucky, or about where you should be. This data will help you work out the chance that your method is profitable.
I’ve run a stack of simulations to help answer the question on sample size: how many bets is enough? There’s a lot of data here but I’ll run you through what I’ve done.
If we look at Test 1 as an example, I’ve asked my computer to produce 50 random results (bets) under those conditions. I’ve then asked the computer to do that 10,000 times (10,000 simulations) and record what percentage of those simulations ended up in a profit (% Won, 76%) and what percent lost (% Lost, 24%).
Overall, I’ve tested six sample sizes: 50 bets, 100 bets, 200 bets, 500 bets and 1000 bets. I’ve tested three prices: $1.90, $3.00 and $10. These roughly align with line bettors ($1.90), favourite punters ($3.00) and roughie punters ($10). And I’ve tested five P.O.T’s: 10.0%, 5.0%, 0.0%, -5.0% and -10.0%. Each row is the data from 10,000 simulations. All bets are flat stakes. The results are below, so check them out.
As you can see, there’s a lot of data we could talk about! I’ll let you look at the results of individual tests, but there are some general principles we can conclude.
The larger the sample size, the more certain we can be that our method is profitable. There is always a chance that it is not profitable, but that chance becomes smaller the more bets you have. We can see that in some situations, it takes a very large sample size to be 95% confident your method is profitable.
The larger the P.O.T., the more certain we can be that our method is profitable. That makes sense.
The shorter the price, the more certain we can be that our method is profitable. The reason for that is that longer prices have a lower strike rate (less winners) and bigger returns when they win, which means that individual winners have a larger influence on the final result. We can be less confident our method is profitable at longer prices because just one winner’s difference (or a small difference in winners) is more likely to trigger a loss, whereas at shorter prices (where there are lots of winners), one winner’s difference is less likely to affect the final result.
In this article, I’ve focused on working out whether your method is profitable, but you could also use this data to work out the chance you’ve been unlucky and your method that is currently losing (negative P.O.T.) is actually profitable.
In conclusion, when it comes to making the decision about whether your method is profitable or not, there is no “yes” or “no” answer – it all comes down to chance and choosing the risk you are willing to accept. Do you want to be 95% or 99% confident your results are profitable before you ramp up the stakes? Or are you happy to take a punt on 90% or lower? That’s a personal choice no expert can tell you.
Rod’s High Low is a staggeringly profitable, specialist service that suits a certain type of punter.
With an average bet size of less than $50, you won't be breaking the bank.
To see if you might be able to take advantage of the unmatched profits it offers, get in touch with us for a chat.