Note There should be navigation links on the left. If you got here directly from the outside world and see nothing on the left, press here to bring up the frames that will allow you to properly navigate this tutorial and site.

Emprical Probability The empirical probability, or probability, P(E), of an event E is the fraction of times we expect E to occur. Relationship to Estimated Probability The estimated probability approaches the empirical probability as the number of trials gets larger and larger. Thus, Estimated probability is an approximation, or estimate, of empirical probability. The larger the number of trials, the more accurate we expect this approximation to be. If E consists of a single outcome s, we refer to P(E) as the probability of the outcome s, and write P(s) for P(E). The collection of the probabilities of all the outcomes is the probability distribution. Determining Empirical Probability Empirical probability is determined analytically, that is, by using our knowledge about the nature of the experiment rather than through actual experimentation. The best we can obtain through actual experimentation is an estimate of the empirical probability (hence the term "estimated probability"). Examples 1. Toss a fair coin and observe the uppermost side. Since we expect that heads is as likely to come up as tails, we conclude that the empirical probability distribution is P(H) = 1/2, P(T) = 1/2. 2. Roll a fair die. Since we expect to roll a "1" one sixth of the time, P(1) = 1/6. Similarly, P(2) = 1/6, P(3) = 1/6, . . . , P(6) = 1/6. 3. Roll a pair of fair dice (recall that there are a total of 36 outcomes if the dice are distinguishable). If E is the event that the sum of the uppermost numbers is 5, then E = {(1, 4), (2, 3), (3, 2), (4, 1)}. Since all 36 outcomes are equally likely, P(E) =

 
Note From now on, "probability," we will refer to either estimated or empirical probability, depending on the context.

Calcuating empirical proability requires a detailed knowledge of the experiment you are considering. A simple kind of experiment is one where the outcomes are equally likely. That is, where each outcome is as likely to occur as any other.

Calculating Empirical Probability When Outcomes Are Equally Likely In an experiment in which all outcomes are equally likely, the empirical probability of an event E is P(E) = Number of favorable outcomes Total number of outcomes = n(E) n(S) . (The "favorable outcomes" are the outcomes in E.)

Example A pair of dice (one red, one green) is cast. We find the empirical probability that the sum of the numbers facing up is 7. S = sample space = set of all pairs of numbers 1 through 6 n(S) = 36 (Go back to the beginning of the previous tutorial if you need a refresher on this...) E = set of favorable outcomes = {(1,6), (2,5), (3,4), (4,3), (5,2), (6,1)} n(E) = 6 P(E) = n(E) n(S) = 6 36 = 1 6 Now go back to the Java simulation of this experiment to see how closely the estimated probability approximates this number after a large number of trials.

Some advice from the Math Nerd...

You are dealt a hand of five cards from a standard deck of playing cards. The number of possible hands is 2,598,960. The number of possible hands consisting entirely of red cards (diamonds and hearts) is 65,780, and the number of possible hands consisting entirely of diamonds is 1,287.

Q The probability of being dealt a hand that does not consist entirely of red cards is approximately:

	0.0253			0.50			2,533,180
	0.9747

Q If you are dealt a hand of five red cards from a standard deck of playing cards, the probability of having a hand consisting entirely of diamonds is approximately:

	0.000495			0.02531			0.01957
	0.5

You toss a fair coin 3 times, and note the number of heads that comes up.

Q Fill in the following empirical probability table and press "Check."

Outcome (Number of Heads)	0	1	2	3
Probability

Q The probability that either one or two heads will come up is.

 

Just as with estimated probability, the following rules hold for empirical probability Which one did you use in answering the last question?

Thus, estimated and empirical probability satisfy the same general properties. They are both examples of abstract probability, the subject of the next tutorial.

A Note on Populations and Samples

Q Last year, 450 of my 500 customers purchased one or more of my on-line video clips. Thus, the probability that a randomly selected customer purchased an on-line video clip is 450/500 = 0.9. Is this estimated probability or empirical probability?
A We are given all the information we need to calculate the "actual" or empirical probability, since we know the actual proportion of customers who purchased the video clips. On the other hand, if the scenario was

"Last year, 450 of 500 surveyed customers purchased one or more of my on-line video clips,"

then we would not know thte actual proportion, since there may be more customers than were surveyed. Thus, the probability would be estimated (being based on a sample, rather than the entire population).,

For more practice, try some of the questions in the chapter quiz (warning: it covers the whole of Chapter 7) by pressing the button on the sidebar. Then try the exercises in Section 7.3 of Finite Mathematics, or Finite Mathematics and Applied Calculus.