Finding conditional and joint probabilities from a table of data

user366312

Gold Member
63
2
Summary
Finding conditional and joint probabilities from a table of data generated by Markov Chain simulation.
Let,

Code:
    alpha <- c(1, 1) / 2
    mat <- matrix(c(1 / 2, 0, 1 / 2, 1), nrow = 2, ncol = 2)

    chainSim <- function(alpha, mat, n)
    {
      out <- numeric(n)
      out[1] <- sample(1:2, 1, prob = alpha)
      for(i in 2:n)
        out[i] <- sample(1:2, 1, prob = mat[out[i - 1], ])
      out
    }


Suppose the following is the result of a 5-step Markov Chain simulation repeated 10 times:

Code:
> sim
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,]    2    1    1    2    2    2    1    1    1     2
[2,]    2    1    2    2    2    2    2    1    1     2
[3,]    2    1    2    2    2    2    2    1    2     2
[4,]    2    2    2    2    2    2    2    1    2     2
[5,]    2    2    2    2    2    2    2    2    2     2
[6,]    2    2    2    2    2    2    2    2    2     2
What would be the values of the following?

  1. P(X1=1|X0=1)P(X1=1|X0=1)
  2. P(X2=1|X0=1)P(X2=1|X0=1)
  3. P(X5=2|X2=1)P(X5=2|X2=1)
  4. P(X1=1,X3=1)P(X1=1,X3=1)
  5. P(X5=2|X0=1,X2=1)P(X5=2|X0=1,X2=1)
  6. E(X2)E(X2)
I tried them as follows:

  1. mean(sim[2, sim[1, ] == 1] == 1)
  2. mean(sim[3, sim[1, ] == 1] == 1)
  3. mean(sim[6, sim[3, ] == 1] == 2)
  4. mean(sim[4, ] == 1 && sim[2, ]== 1)
  5. ?
  6. c(1,2) * mean(sim[2, ])
What would be the solution of (5)?

Am I correct withe the rest?
 
Last edited:

FactChecker

Science Advisor
Gold Member
2018 Award
4,730
1,614
Are you getting meaningful probabilities between 0 and 1 from your code?
I guess that I wasn't clear in a similar thread of yours Post #8 of similar thread
I think that your use of 'mean' is wrong here. It will give you the average of a lot of values of 1 and 2, which will be over 1. That can not be a probability. You must count the number of entries, not their values. You can do that by using the 'length' function as I showed in Post #8 of the other thread.

PS. I just noticed that this thread is several days old, so my answer here might already be known and understood by the OP.
 

Want to reply to this thread?

"Finding conditional and joint probabilities from a table of data" You must log in or register to reply here.

Physics Forums Values

We Value Quality
• Topics based on mainstream science
• Proper English grammar and spelling
We Value Civility
• Positive and compassionate attitudes
• Patience while debating
We Value Productivity
• Disciplined to remain on-topic
• Recognition of own weaknesses
• Solo and co-op problem solving
Top