Suppose random variable X can take value x1 with probability p1, value x2 with probability p2, and so on, up to value xk with probability pk. Then the expectation of this random variable X is defined as E(X)= x1p1+ x2p2+ ... + xkpk.
My data is: A, AB, ABC, BC, B, C, CA ( 7 symbol sequences)
How can I compute probability of A (p(A)), B (p(B)), C (p(C))?
Also, how can I compute the mean and standard deviation for this data?
[edited: more detail]
My data is symbol sequence data.
For my data, I want to know the probability that A occurs in this data. I compute as P(A)=(number of occurrences of)/ (total number of occurrences) =4/7.
But P(A)+P(B)+P(C) will be greater than 1.
I need to calculate Mean and standard deviation too.
Dear all,
EX:
The possible values for X are 1, 2, 3, 4, 5, and 6, all equally likely (each having the probability of 1/6). The expectation of X is E(X)= 1*1/6+2*1/6+2*1/6+4*1/6+5*1/6+6*1/6=3.5
My data is symbol sequence data.
For my data, I want to know the probability that A occurs in this data. I compute as P(A)=(number of occurrences of)/ (total number of occurrences) =4/7.
But P(A)+P(B)+P(C) will be greater than 1.
I need to calculate Mean and standard deviation too.
Thank all.
Still not clear. Do you have the set of all possible such sequences from where your data is supposedly sampled?
Dear all,
I attach data file.
Ex: A+,B+,C+,C-,A-,B-,2
A,B,C are appliances in home.
2 is number of occurrences of this pattern sequence, or we can write this pattern 2 times as A+,B+,C+,C-,A-,B- ; A+,B+,C+,C-,A-,B-
I want to calculate the probability that A occurs in dataset.
there are 4 appliances in my dataset, A,B,C, and D. Since, all appliances are independent. So, P(A)=P(B)=P(C)=P(D)=1/4
Mean= 1*1/4+2*1/4+3*1/4+4/1/4
(https://answers.yahoo.com/question/index?qid=20090810075714AALWDiI)
May I do it?
Thanks all!!!!
If I am following your question correctly, I would suggest looking into a multinomial approach (baseline category logit model).
Attached are some class notes with examples of the baseline category logit model if you would like to try that approach. I'm not sure which statistical packages you use, but examples here are in SAS. Nevertheless, this should at least give you an idea as to whether it may be appropriate for your data.
"My data is symbol sequence data.
For my data, I want to know the probability that A occurs in this data. I compute as P(A)=(number of occurrences of)/ (total number of occurrences) =4/7.
But P(A)+P(B)+P(C) will be greater than 1."
Okay, I think I understand your problem. P(A)+P(B)+P(C) do not sum exactly to 1 because they are not mutually exclusive (you can have any combination of these). So, you have to consider when any combination of A,B, or C occurs simultaneously, or when they "intersect." If not, you would essentially be double counting overlapping areas... see "set theory."
Dear David Glover,
Thank for your answer. But I will explain more about this.
Ex:
1. A+,A-,65 // A occurs alone 65 times
2. A+,B+,A-,B-,12 // A and B occur together 12 times (A and B are turning on at the same period)
3. A+,B+,C+,C-,A-,B-,2 //A, B, and C occur together 2 times (A and B are turning on at the same period).
We see that:
* A and B occur together 14 times in this dataset (in 2 and 3)
* A occurs 79 times in 1,2 and 3.
*.................
* C occurs 2 times in 3.
let P(A and B) =P(X)
let P(A and B and C) =P(Y)
then P(A)+ P(X) + P(Y)=65/79+12/79+2/79=1
But I want to compute the probability of A occurs in this dataset. Can I say P(A)=1 because A occurs in all sequences or how can I say for this value?
Or P(B)=(12+2)/79, what is this value?it is not probability but I don't know what is it?
Thanks all!
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Probability