Conditional probability is the probability of some event A, given the occurrence of some other event B.
Conditional probability is written P(A|B), and is read "the (conditional) probability of A, given B" or "the probability of A under the condition B". When in a random experiment the event B is known to have occurred, the possible outcomes of the experiment are reduced to B, and hence the probability of the occurrence of A is changed from the unconditional probability into the conditional probability given B.
In the notation P(A | B) the symbol P is used, only as a reference to the original probability. It should not be read as the probability P of some event A|B. Sometimes the more accurate notation PB(A) is used, but the use of complex events as index of the symbol P is cumbersome. Notice that the line separating the two events A and B is a vertical line. Joint probability is the probability of two events in conjunction. That is, it is the probability of both events together. The joint probability of A and B is written or Marginal probability is then the unconditional probability P(A) of the event A; that is, the probability of A, regardless of whether event B did or did not occur. If B can be thought of as the event of a random variable X having a given outcome, the marginal probability of A can be obtained by summing (or integrating, more generally) the joint probabilities over all outcomes for X. For example, if there are two possible outcomes for X with corresponding events B and B', this means that . This is called marginalization.
Consider the simple scenario of rolling two fair six-sided dice, labelled die 1 and die 2. Define the following three events (not assumed to occur simultaneously):
A: Die 1 lands on 3. B: Die 2 lands on 1. C: The dice sum to 8.
The prior probability of each event describes how likely the outcome is before the dice are rolled, without any knowledge of the roll's outcome. For example, die 1 is equally likely to fall on each of its 6 sides, so P(A) = 1/6. Similarly P(B) = 1/6. Likewise, of the 6 × 6 = 36 possible ways that a pair of dice can land, just 5 result in a sum of 8 (namely 2 and 6, 3 and 5, 4 and 4, 5 and 3, 6 and 2), so P(C) = 5/36. Some of these events can both occur at the same time; for example events A and C can happen at the same time, in the case where die 1 lands on 3 and die 2 lands on 5. This is the only one of the 36 outcomes where both A and C occur, so its probability is 1/36. The probability of both A and C occurring is called the joint probability of A and C and is written , so
Now suppose we roll the dice and cover up die 2. the dice cannot sum to 8. because it is the probability of C under the condition that A is observed. we already know the dice can't sum to 8. On the other hand. and is written P(C | A). we have:
As noted above. if we roll the dice and cover up die 2. which only depends on die 2.
. Intersection events and conditional events are related by the formula:
In this example. so . Given this partial information. On the other hand. so by this formula:
On multiplying across by P(A). if two events are independent. This is called the conditional probability. which is read "the probability of C given A. and observe die 1." Similarly. instead it is 1/6. and observe that die 1 landed on 3.
In other words. if die 2 lands on 1. regardless of what the other die landed on. the probability that the dice sum to 8 is no longer 5/36. the probability of B occurring after observing that die 1 landed on 3 is the same as before we observed die 1. since die 2 must land on 5 to achieve this result. this has no impact on the probability of event B. P(C | B) = 0.
. their joint probability is the product of the prior probabilities of each event occurring by itself. We say events A and B are statistically independent or just independent and in this case
In other words. so we can only see die 1.. since if we observe die 2 landed on 1.
What is the probability of a randomly selected individual smoking? Again.. so 19/60 = 0. So the old rule about being the number in the event divided by the number in the sample space still applies. What is the probability that the male smokes? Well. we have a reduced sample space.31.think of stratified sampling.
The question. this is a marginal probability. you're told that you have a male . The number of "Male and Smoke" divided by the total = 19/100 = 0. it includes all the cases. What is the probability of a randomly selected male smoking? This time. Results are shown in the table. If you then divided numerator and denominator of the right hand side by the number in the sample space S.
.Recall that the probability of an event occurring given that another event has already occurred is called a conditional probability. we now have a sample space of A since we know A has occurred. then you have the probability of A and B divided by the probability of A. It is the number in A and B (must be in A since A has occurred) divided by the number in A.19 What is the probability of a randomly selected individual being a male? This is the total for male divided by the total = 60/100 = 0. given that event A has already occurred is
P(B|A) = P(A and B) / P(A)
This formula comes from the general multiplication principle and a little bit of algebra. Instead of the entire sample space S. 19 males smoke out of 60 males.31666. Male Female Total Yes 19 12 31 No 41 28 69 Total 60 40 100
What is the probability of a randomly selected individual being a male who smokes? This is just a joint probability. Since no mention is made of smoking or not smoking. since no mention is made of gender.60. "Do you smoke?" was asked of 100 people. the total who smoke divided by the total = 31/100 = 0.
. The probability that event B occurs.. Since we are given that event A has occurred.
30) = 0.20 1.025 = 0.020 = 0. the 7% is not P(Defective).30)=0. 0.021 = 0.05(0. Brochmailians.10(0.20-0.50 0.50) = 0. and Chompielians. or by multiplication using conditional probabilities. Aberations has a 50% market share.180 0.025 0.066 Total 0. There are 19 male smokers out of 31 total smokers.30-0.
There are three major manufacturing companies that make a product: Aberations.30 0. and 10% of Chompieliens' product is defective. they have a 20% market share. and Brochmailians has a 30% market share. This information can be placed into a joint probability distribution
Company Aberations Brochmailians Chompieliens Total Good 0. That is.6129 (approx)
After that last part.279.00. then 93% is good. The joint probability P(Defective and Brochmailians) = P(Defective|Brochmailians) * P(Brochmailians).that's the beauty of it.07(0. A Bayes' problem can be set up so it appears to be just another conditional probability.50-0.
What is the probability a randomly selected product is defective? P(Defective) = 0.
What is the probability that a randomly selected smoker is male? This time. but P(Defective|Brochmailians). 5% of Aberations' product is defective.20) = 0. but since the marginals must add to be 1. and 10% defective rates don't go into the table directly.475 0. 7%.020 0. These defective probabilities are conditional upon which company was given. This is because they are conditional probabilities and the table is a joint probability table. I know you didn't realize it . you're told that you have a smoker and asked to find the probability that the smoker is also male.279 0. 7% of Brochmailians' product is defective.021 0.066
. so 19/31 = 0. Notice that the 5%. In this class we will treat Bayes' problems as another conditional probability and not involve the large messy formula given in the text (and every other text). you have just worked a Bayes' Theorem problem.93(0.934 Defective 0. If 7% of Brochmailians' product is defective.00
The percent of the market share for Chompieliens wasn't given. The "good" probabilities can be found by subtraction as shown above.
along with all blondes and all blond people who wear glasses. Over the last 70 days. As the process is not perfect. let's assume we have an operational process like widget production. where X is some event.033. For example. where X and Y are two events. Union Probability: A union probability is denoted by P(X or Y). Marginal probability is denoted P(X).318 (approx). 2. All people wearing glasses are included in the union. On any given day.
Types of Probability: Three types of probabilities are discussed in this lecture note: 1.066 = 7/22 = 0. the P(Aberations and Defective)=0. these terms are reviewed in Chapter Two of Gujarati's Essentials of Econometrics). we are careful to distinguish between marginal. P(X or Y) is the probability that X will occur or that Y will occur or that both X and Y will occur.021/0. and the errors are either technical or human. Are these events independent? No.066=0. To become eligible for the joint probability. The frequency distribution looks like this:
What is the probability that a defective product came from Brochmailians? P(Brochmailian|Defective) = P(Brochmailian and Defective) / P(Defective) = 0. conditional and joint probabilities (for the FRM candidate. Also.50*0.318 would have to equal the P(Brochmailians)=0.025 would have to be P(Aberations)*P(Defective) = 0. errors sometimes happen. the probability of a person wearing glasses is calculated by dividing the number of people wearing glasses by the total number of people. and it doesn't. but it doesn't. Marginal Probability: A marginal probability is usually calculated by dividing some subtotal by the whole. Joint Probability: A joint probability is denoted by P(X and Y). then P(Brochmailians|Defective)=0. The probability of a person wearing glasses or having blond hair is an example of union probability. we observe the errors. If they were. To illustrate.
In finance.30. both events X and Y must occur. there occurred zero to three (0 to 3) human errors and zero to three (0 to 3) technical errors. The probability that a person is a blondhead and wears glasses is an example of joint probability.
It is the probability of a human or technical error rate without any prior information (unconditional on any information). they are discrete.
The marginal probability is the unconditional probability. for example.14)
Note the interior cells sum to 1. it's either 0 or 1 or 2 or 3) and cumulatively exhaustive (0 to 3 captures all of the possibilities).3% (rounded below to .2).0 as these are discrete variables (one way to remember this: if we can count the errors. they are likely continuous) and they are mutually exclusive (you can't have both 1 and 2 errors on the same day. then the joint probability is P(Human Error =3.Joint probability
Each cell contains a joint probability.04 + 0.09 + 0. If we must measure the errors on a scale.06 + 0. Technical Error = 3) = 10/70 = 14. If 10 out of the 70 days were days that saw three human errors and three technical errors.
. In the case. the unconditional probability of one (1) Human error is the sum of a column: P(Human Error =1) = (0.01) = (0.
. P(Human = x). Technical = y). Conditional means "we have some prior information.g. Without prior information.
A conditional probability is typically more realistic. But instead we know that zero technical errors occurred (the orange column below).. The other is the unconditional probability of one outcome. e. e. P(Technical = y). The probability of zero technical errors given zero human errors is about 55% (0. Rounding creates some error). P(Human = x. we understood the unconditional probability of zero technical errors to be 20% (see end of first row above). they are unconditional.Both the joint probability and the marginal probability lack prior information." Assume we already know (or expect) zero human errors for a given day.. One is the unconditional probability of two outcomes.16.g.09/0.
Notice that the prior knowledge of zero human errors changes the probability of zero technical errors from an unconditional 20% to a conditional 55%."
. We express this as: P (Technical Errors = 0 | Human Errors = 0) = 9%/16%. Where the pipe "|" means "given that" or "conditional on.