Take the 2-minute tour ×
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

I was thinking about this today so I decided to ask it here. I know the rule of adding probabilities. As I was taught in grade school "OR" typically means add and "AND" typically means multiply.

Suppose there is a jar with a red, blue, green, and yellow ball. The probability of picking a red ball is 25%. The probability of picking a red ball, putting it back, AND then picking a green ball is 12.5% (25% * 25%). The probability of picking either a red OR a green ball on the first try is 50% (25% + 25%).

These are independent events. Now lets take another set of independent events.

  1. The weather man said there is an 80% chance of rain. This means it should rain 80% of the time I assume. If you looked back at the past 100 days with an 80% rain chance it should rain on ~80 of them.

  2. A girl hooked up with 5 of our 10 mutual friends. I have a 50% chance of hooking up with her too.

  3. Rolling an even number on a dice carries a 50% probability.

If it rains OR I hook up with the girl OR I roll an even number on the dice then I win. If any one of these things happen I win, just like if I pick a red or a green ball, it doesn't matter if its red or green. With that being said the probability that it rains or I hook up or I roll an even number is 180%. This is not true because it is remotely possible that none of those things happen.

share|improve this question
1  
Briefly, you only add exclusive probabilities. You can't pick a red ball and a green ball at the first try. (BTW your reasoning is hopelessly optimistic in #2: if she's already passed you over 5 times you've no chance.) –  Scortchi Jan 15 '13 at 14:23

1 Answer 1

Edit: Oh if you don't understand this notation feel free to ask then I will elaborate. I am assuming you are familiar with the set/event thing.

What you are learned in grade school may not always be correct

$$P(Rain) = 0,8 \\ P(Girl) = 0,5 \\ P(Dice) = 0,5$$

Also, since you assume independence

$$P(Rain \cap Girl \cap Dice) = P(Rain)*P(Girl)*P(Dice) = 0,2 \\ P(Rain \cap Girl) = P(Rain)*P(Girl) = 0,4 \\ P(Rain \cap Dice) = P(Rain)*P(Dice) = 0,4\\ P(Girl \cap Dice) = P(Girl)*P(Dice) = 0,25\\ $$

And with that we have

$$P(Rain \cup Girl \cup Dice) = P(Rain) + P(Girl) + P(Dice) - P(Rain \cap Girl) - P(Rain \cap Dice) - P(Girl \cap Dice) + P(Rain \cap Girl \cap Dice) = 0,95$$

I suggest you draw yourself a couple of Venn diagrams if this isn't clear.

I just recently posted about this topic here as well

share|improve this answer
    
I would like to invite you to draw those diagrams and include them in your answer: it would make it (and the one you reference) clearer and more accessible. –  whuber Jan 15 '13 at 14:24

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.