Simple question about sets in statistics

  • Thread starter Thread starter Nikitin
  • Start date Start date
  • Tags Tags
    Sets Statistics
Click For Summary
The discussion centers on the equivalence of two probability scenarios involving tickets of types A and B, where type A has a higher probability of being drawn. It explores whether having 200 type A tickets and 100 type B tickets is mathematically equivalent to having 100 of each type with differing probabilities. While one participant agrees that for a single draw the scenarios can be considered equivalent, they acknowledge that mathematically, the events are distinct due to differences in total ticket counts. The conversation also touches on the implications for Bayes' rule, emphasizing that conditional probabilities refer to events in different probability spaces. Ultimately, the nuances of probability spaces and event definitions are critical to understanding the relationship between the two scenarios.
Nikitin
Messages
734
Reaction score
27
Let's say you have 100 tickets of type A, and 100 tickets of type B in a box. Let's also say the probability to draw ticket A, for whatever reason, is twice that to draw ticket B.

Is this problem, for all intents and purposes, mathematically equivalent to having 200 type A tickets and 100 type B tickets with the probability of drawing both ticket A and B being equal?

The reason I'm asking is that Bayes' rule and so on seems to be based on the thinking that every single element in the sample space ##S## has an equal probability to be "picked" to any other element in ##S##..
 
Physics news on Phys.org
Nikitin said:
Is this problem, for all intents and purposes, mathematically equivalent to having 200 type A tickets and 100 type B tickets with the probability of drawing both ticket A and B being equal?

I'd say yes, if you only draw one ticket. However, mathematically, my answer can be disputed. The event "The ticket is type A" in the probability space with a total of 200 tickets is technically not the same event as "The ticket is type A" in the probability space where there are 300 total tickets. They are two different events, which have the same probability.

The reason I'm asking is that Bayes' rule and so on seems to be based on the thinking that every single element in the sample space ##S## has an equal probability to be "picked" to any other element in ##S##..

It is true that the equation defining conditional probability refers to events in different probability spaces. Suppose the most detailed results that we can describe are called "outcomes" (e.g. the die lands with 5 up). The "events" in the sample space are sets whose elments of outcomes. They may a set of single outcomes (e.g. the die lands with 5 up) or a set of many outcomes (e.g. the die lands with a 3,4 or 5 up). If we consider the events involved in the expressions P(A|B) and P(A\cap B) they are the same as sets of outcomes. However they are events in two different probability spaces. The event whose probability is P(A|B) is in a probability space where the outcomes are only the outcomes in the set B. The event whose probability is P(A \cap B) is in a probability space that includes all the outcomes of A, all the outcomes of B and possibly other outcomes in addition.
 
  • Like
Likes Nikitin
The standard _A " operator" maps a Null Hypothesis Ho into a decision set { Do not reject:=1 and reject :=0}. In this sense ( HA)_A , makes no sense. Since H0, HA aren't exhaustive, can we find an alternative operator, _A' , so that ( H_A)_A' makes sense? Isn't Pearson Neyman related to this? Hope I'm making sense. Edit: I was motivated by a superficial similarity of the idea with double transposition of matrices M, with ## (M^{T})^{T}=M##, and just wanted to see if it made sense to talk...

Similar threads

  • · Replies 13 ·
Replies
13
Views
3K
  • · Replies 5 ·
Replies
5
Views
2K
  • · Replies 6 ·
Replies
6
Views
3K
  • · Replies 11 ·
Replies
11
Views
3K
  • · Replies 53 ·
2
Replies
53
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 20 ·
Replies
20
Views
4K
  • · Replies 16 ·
Replies
16
Views
2K
  • · Replies 28 ·
Replies
28
Views
6K