Need help with a probability problem

  • Context: Undergrad 
  • Thread starter Thread starter sdclaw
  • Start date Start date
  • Tags Tags
    Probability
Click For Summary
SUMMARY

The discussion focuses on calculating the probability of a specific event, A, occurring at least 75% of the time over the next 24 trials, given that A has occurred 25% of the time in a previous sample of 200 events. Participants are advised to use the binomial distribution with p(A) set at 0.25. The conversation emphasizes the need to update the probability of A after each trial based on outcomes, illustrating how to calculate the expected probability after subsequent trials while maintaining an average probability of 0.25.

PREREQUISITES
  • Understanding of basic probability concepts
  • Familiarity with binomial distribution
  • Knowledge of updating probabilities based on new data
  • Ability to perform calculations involving fractions and averages
NEXT STEPS
  • Study the properties of binomial distribution in depth
  • Learn how to calculate cumulative probabilities using binomial distribution
  • Explore Bayesian updating techniques for probability
  • Investigate real-world applications of probability in decision-making
USEFUL FOR

Students, educators, and professionals in statistics, data science, and any field requiring probability analysis will benefit from this discussion.

sdclaw
Messages
2
Reaction score
0
Guys and girls, I need help calculating the probability of the following event happening (or feel free to just tell me the answer :smile: )

I know an event has two possible outcomes, let's call the outcome A and outcome B. I know that the desired outcome (let's call it A) has occurred 25% of the time over a sample size of 200 events.

What is the probability that A will occur 75% (or greater) of the time over the next 24 occurances of the event happening?

I have a basic understanding of probability but I'm having trouble wrapping my head around this.
 
Last edited:
Physics news on Phys.org
Use the binomial distribution with p(A)=1/4. Although you don't know p(A) exactly, 200 trials gives you a good estimate.
 
mathman said:
Use the binomial distribution with p(A)=1/4. Although you don't know p(A) exactly, 200 trials gives you a good estimate.

How do we account for the fact that after each additional trial p(A) changes. In this instance let's say trials 201-210 all yield the desired result. That being the case p(A) will increase after each of these trials.
 
Let's say you're wondering about the next 2 trials. For the next trial you predict "Heads" with probability 0.25, "Tails" with prob. 0.75. Let's say you have Heads. So you'd need to update 0.25 up to 51/201. But, let's say you have Tails. Then you'd need to update 0.25 down to 50/201.

Since you don't know whether you'll get Heads or Tails, you decide to calculate the "average" probability of Heads that you expect to have after the next trial, using the probabilities that you have currently (0.25 for Heads and 0.75 for Tails). The average probability that you can expect to have after your next trial is (51/201) x 0.25 + (50/201) x 0.75 = 50.25/201 = 0.25 exactly.

The interpretation is that before you run the next trial, all you can say is that you expect the probability of Heads to stay constant at 0.25. The same logic applies to the second-next trial, and so on...
 

Similar threads

  • · Replies 6 ·
Replies
6
Views
3K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 13 ·
Replies
13
Views
2K
  • · Replies 11 ·
Replies
11
Views
3K
  • · Replies 6 ·
Replies
6
Views
2K
Replies
147
Views
10K
  • · Replies 9 ·
Replies
9
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
Replies
7
Views
2K
  • · Replies 9 ·
Replies
9
Views
5K