This action might not be possible to undo. Are you sure you want to continue?

Welcome to Scribd! Start your free trial and access books, documents and more.Find out more

**Attributes of a Poisson Experiment
**

A Poisson experiment is a statistical experiment that has the following properties: • • • • The experiment results in outcomes that can be classified as successes or failures. The average number of successes (μ) that occurs in a specified region is known. The probability that a success will occur is proportional to the size of the region. The probability that a success will occur in an extremely small region is virtually zero.

Note that the specified region could take many forms. For instance, it could be a length, an area, a volume, a period of time, etc.

Notation

The following notation is helpful, when we talk about the Poisson distribution. • • • • • e: A constant equal to approximately 2.71828. (Actually, e is the base of the natural logarithm system.) μ: The mean number of successes that occur in a specified region. x: The actual number of successes that occur in a specified region. P(x; μ): The Poisson probability that exactly x successes occur in a Poisson experiment, when the mean number of successes is μ.

Poisson Distribution

A Poisson random variable is the number of successes that result from a Poisson experiment. The probability distribution of a Poisson random variable is called a Poisson distribution. Given the mean number of successes (μ) that occur in a specified region, we can compute the Poisson probability based on the following formula: Poisson Formula. Suppose we conduct a Poisson experiment, in which the average number of successes within a given region is μ. Then, the Poisson probability is: P(x; μ) = (e-μ) (μx) / x! where x is the actual number of successes that result from the experiment, and e is approximately equal to 2.71828.

e = 2.71828.71828.180 . 2) = (0. The variance is also equal to μ .Properties Of Poisson Distribution The Poisson distribution has the following properties: • • The mean of the distribution is equal to μ .13534) (8) / 6 P(3. since 5 lions are seen per safari.71828.71828. since we want to find the likelihood that 3 homes will be sold tomorrow. Cumulative Poisson Probability A cumulative Poisson probability refers to the probability that the Poisson random variable is greater than some specified lower limit and less than some specified upper limit. 2. 2) = 0.71828-2) (23) / 3! P(3. e = 2. 1. What is the probability that exactly 3 homes will be sold tomorrow? Solution: This is a Poisson experiment in which we know the following: • • • μ = 2. we want the probability that they will see 0. since e is a constant equal to approximately 2. 1. Example 1 The average number of homes sold by the Acme Realty company is 2 homes per day. x = 3. What is the probability that tourists will see fewer than four lions on the next 1-day safari? Solution: This is a Poisson experiment in which we know the following: • • • μ = 5. x = 0. or 3. on average. on average. 2. μ) = (e-μ) (μx) / x! P(3. Example 2 Suppose the average number of lions seen on a 1-day safari is 5.180 Thus. since 2 homes are sold per day. the probability of selling 3 homes tomorrow is 0. or 3 lions. 2) = (2. . We plug these values into the Poisson formula as follows: P(x. that is. since we want to find the likelihood that tourists will see fewer than 4 lions. since e is a constant equal to approximately 2.

If you choose a popular number. The formula for the probability of observing k of whatever is being counted when the expected number is m is p(k) = mk e− m ⁄ k ! where e is the base of the natural logarithms and k ! indicates the factorial function (use the ex key on a scientific calculator to calculate e− m and the x! key to calculate k !). or 3 lions. 5) + P(1. but other players choose some number they think is lucky and that's not random. it is not quite right.006738)(25) / 2 ] + [ (0. .006738)(125) /6] P(x < 3. but the probability of large counts falls off very rapidly.To solve this problem. In a lottery.140375 ] P(x < 3.0067 ] + [ 0. whereas the Poisson distribution gives nonzero probability to arbitrarily large numbers of winners. if you can figure out a number no one else likes and play that. Since they don't. The Poisson distribution assumes every player chooses lottery numbers completely at random.2650 The Poisson Distribution The Poisson Distribution arises in a number of contexts as the distribution of a random number of points. 5). Theoretically any count between zero and infinity (including zero) is possible. 5) + P(3. the number of winners cannot have an exact Poisson distribution for two reasons. The choice of lottery numbers by the players is not completely random. you are guaranteed not to have to share the jackpot if you win. we need to calculate the sum of four probabilities: P(0. • • The number of winners cannot be more than the number of tickets sold. 2. 5) = 0. you will have to share with many other winners if you win. Conversely. we need to find the probability that tourists will see 0. 5) + P(2. 5) = [ (e-5)(50) / 0! ] + [ (e-5)(51) / 1! ] + [ (e-5)(52) / 2! ] + [ (e-5)(53) / 3! ] P(x < 3. Thus. 5) = [ (0. we will assume the Poisson distribution is correct to keep things simple.084224 ] + [ 0. 5) + P(1. 5) + P(3. we use the Poisson formula: P(x < 3.006738)(5) / 1 ] + [ (0.006738)(1) / 1 ] + [ (0. To compute this sum. 5) = P(0.03369 ] + [ 0. The Poisson distribution would be an extremely good approximation if it were not for the other issue. Many players (about 70%) buy quick picks which are completely random. 5) + P(2. the number of raisins in a box of raisin bran. If every player choose a quick pick the Poisson distribution would be an almost perfect approximation. However. 1. 5) = [ 0. and so forth. The second is more serious. The first issue is not a serious problem. for example the number of clicks of a Geiger counter in one second. the number of blades of grass in a randomly chosen square inch of lawn. 5) P(x < 3.

The terms in the infinite sum are ak = J ⁄ (k + 1) × mk e− m ⁄ k ! = J mk e− m / (k + 1) ! Let W denote the sum of the ak as k runs from zero to infinity. there is a trick that allows us to see what the expectation is without doing the infinite sum. which is mk e− m ⁄ k !. then the jackpot gets split k we win is J ⁄ (k + 1). so it appears to require calculus to sum this infinite series. the series would sum to J (because the probabilities sum to one). If we multiply each term by m we get m ak = J mk + 1 e− m ⁄ (k + 1) ! = J p(k + 1) where p(k) is the Poisson probability defined above. If we were to add an additional term J p(0). and sum. and the amount Our expected winnings are calculated just like any other expectation: multiply the amount we win in each case. which is required for the correctness of the Poisson distribution. + 1 ways. and their ticket choice had nothing to do with yours. the probability of seeing at no more than 3 lions is 0. The sum runs over k from zero to infinity. Thus the series sums to J [1 − p(0)] = m W (Recall that we multiplied by m so the sum is m W rather than W). where J is the size of the jackpot. the first term is J p(1).1 million chance of winning. Everyone has the same 1 in 146. Because of the k + 1 above. Fortunately. The probabilities p(k) must sum to one as k goes from zero to infinity by the properties of probability. by the probability of that case. which is the expectation we are trying to calculate. which is J ⁄ (k + 1). . Our Expected Winnings If we win and there are k other winners. Then whether you you win or not doesn't change the probability of anyone else winning.The reason why the unconditional distribution of the number of winners of the jackpot and the conditional distribution of the number of other winners given you win are the same has to do with the assumption of completely random choices of numbers by all the players.2650. Solving for W gives W = J [1 − p(0)] / m = J (1 − e− m) ⁄ m Thus.

then X + Y ~ Po(l + m) Random Events The Poisson distribution is useful because many random events follow it. l of the distribution is equal to 0. Sums of Poisson Suppose X and Y are independent Poisson random variables with parameters l and m respectively. Example There are 50 misprints in a book which has 250 pages. X will follow a Poisson distribution with parameter 0.f. Var(X) = l.2. Then X + Y has a Poisson distribution with parameter l + m. Therefore. For example. if we let X be the random variable denoting the number of misprints on a page. The average number of misprints on a page is 50/250 = 0. the occurrence of earthquakes could be considered to be a random event. then the number of occurrences within that time period will follow a Poisson distribution. the parameter.2 . If a random event has a mean number of occurrences l in a given time period. Since the average number of misprints on a page is 0.2 .d. If there are 5 major earthquakes each year.) of the form: is said to be a Poisson random variable with parameter l. . then the number of earthquakes in any given year will have a Poisson distribution with parameter 5. then: · · E(X) = l. If X ~ Po(l). We write X ~ Po(l) Expectation and Variance. Find the probability that page 100 has no misprints.A discrete random variable X with a probability distribution function (p.2 . In other words: • If X ~ Po(l) and Y ~ Po(m).

The Probability Density Function We have shown that the k th arrival time in the Poisson process has the gamma probability density function with shape parameter k and rate parameter r : f *k (t) = r k tk −1 (k − 1)! e −r t .k∈ 2. run the experiment 1000 times with an update frequency of 10 and watch the apparent convergence of the relative frequency function to the density function. t] if and only if the k th arrival occurs by time t: ( N t ≥ k) ⇔ (T k ≤ t) 1. 3.2)(0.819 (3sf) Binomial Approximation The Poisson distribution can be used as an approximation to the binomial distribution. t ≥ 0 Recall also that at least k arrivals come in the interval (0. Use integration by parts to show that ( N t ≥ k) =⌠⌡ t f *k (s)ds = 1 − Σj =0 k −1 e −r t (r t) j j! . Use the result of Exercise 1 to show that the probability density function of the number of arrivals in the interval (0. vary r and t with the scroll bars and note the shape of the density function. • A Binomial distribution with parameters n and p can be approximated by a Poisson distribution with parameter np.P(X = 0) = (e-0. Now with r = 2 and t = 3. the distribution is named after Simeon Poisson. In the Poisson experiment. . t] is ( N t = k) = e −r t (r t)k k ! . k ∈ The corresponding distribution is called the Poisson distribution with parameter r t.20) 0! = 0.

Nt − Ns has the same distribution as Nt −s namely Poisson with parameter r (t − s). on the Poisson process. variance. The following exercises give the mean. 5. Find the probability that there will be at least 8 requests in a 2 minute period. b. and thus the distribution is unimodal c. Suppose that requests to a web server follow the Poisson model with rate r = 5. then N t − N s is the number of arrivals in the interval (s. we expect about r t arrivals. If c is an integer there are two modes at c − 1 and c.5 per meter. Recall that our basic assumption is that the process essentially starts over at time s and the behavior after time s is independent of the behavior before time s. a discrete random variable N in an experiment is said to have the Poisson distribution with parameter c > 0 if it has the probability density function g(k) = e −c c k k ! . Show that ( N ) = c. based a. . Give a probabilistic proof. we see that r can be interpreted as the average arrival rate. Suppose that N and M are independent random variables. Nt − Ns and Ns are independent. run the experiment 1000 times with an update frequency of 10 and watch the apparent convergence of the sample mean and standard deviation to the distribution mean and standard deviation. Suppose that customers arrive at a service station according to the Poisson model. 11. In general. Independent Increments Let us see what the basic regenerative assumption of the Poisson process means in terms of the counting variables {N t : t ≥ 0}. b. 6. t]. there is a single mode at ⌊c⌋. 8. Show directly that g is a valid probability density function. per minute. Find the mean and standard deviation of the number of customers in an 8 hour period. and probability generating function of N . and that N has the Poisson distribution with parameter c and M has the Poisson distribution with parameter d.The Poisson distribution is one of the most important in probability. 10. it follows that ( N t ) = r t and var( N t ) = r t for t ≥ 0. Show that (u N ) = e c (u −1) . 9. k ∈ 4. Show that N + M has the Poisson distribution with parameter c + d. 15. Moments Suppose that N has the Poisson distribution with parameter c. Argue that: a. Now with r = 3 and t = 4. 7. Show that if s < t. Show that var( N ) = c. If c is not an integer. Stationary. Once again. Defects in a certain type of wire follow the Poisson model with rate 1. vary r and t with the scroll bars and note the location and size of the mean/standard deviation bar. Show that a. Find the probability that there will be no more than 4 defects in a 2 meter piece of the wire. g at first increases and then decreases. 14. In an interval of length t. g(n − 1) < g(n) if and only if n < c. 13. 12. at a rate of r = 4. respectively. for u ∈ Returning to the Poisson process {N t : t ≥ 0} with rate parameter r . In the Poisson experiment.

the same result is true with the integer k replaced by the positive real number c.. . select r = 1 and t = 3. we should remember to use the continuity correction. Conditional Distributions Consider again the Poisson model with arrival time sequence (T 1. Normal Approximation Now note that for k ∈ ℕ+.. since the Poisson is a discrete distribution.) and counting process {N t : t ≥ 0}. set r = 1 and t = 1. 17. Give an analytic proof using probability density functions. 22. Increase r and t and note how the graph of the probability density function becomes more bell-shaped. 21. Show that the conditional distribution of T 1 given N t = 1 is uniform on the interval (0. Let t > 0. if N has the Poisson distribution with parameter c. Interpret the result. 19. The relative frequency of the event {15 ≤ N4 ≤ 22} . updating after each run.. Suppose that requests to a web server follow the Poisson model with rate r = 5. Compute and compare the following: a. c.. set r = 5 and t = 4. ℙ(15 ≤ N4 ≤ 22) b. N k = N 1 + ( N 2 − N 1) + ··· + ( N k − N k −1) The random variables in the sum on the right are independent and each has the Poisson distribution with parameter r . More generally. Give an analytic proof using probability generating functions.. . In the Poisson experiment. then the distribution of N is approximately normal with mean c and standard deviation √c. 20. 16. By computing the appropriate relative frequency functions. investigate empirically the independence of the random variables N 1 and N 3 − N 1. Use the central limit theorem to show that the distribution of the standardized variable below converges to the standard normal distribution as k → ∞. When using the normal approximation. and c is “large”. t). c. t). Note that the conditional distribution in the last exercise is independent of the rate r . Z k = N k − k r √k r A bit more generally. Thus. The normal approximation to ℙ(15 ≤ N4 ≤ 22). This result means that. the Poisson model gives the most “random” distribution of points in time. Run the experiment 1000 times with an update frequency of 100. In the Poisson experiment. Compute the normal approximation to the probability that there will be at least 280 requests in a 1 hour period. T 2. Run the experiment 1000 times. In the Poisson experiment. . T n) is the same as the distribution of the order statistics of a random sample of size n from the uniform distribution on the interval (0. 18. the conditional distribution of (T 1. show that given N t = n. in a sense.b.

27. Over the 100 runs. Suppose that requests to a web server follow the Poisson model with unknown rate r per minute. compute the estimate of r based on Nt . Suppose that requests to a web server follow the Poisson model. Run the experiment 100 times. Find the probability that the request came during the first 3 minutes of the period. Estimate r . b. Interpret the result. the rate r of the process in unknown and must be estimated based on observing the number of arrivals in an interval. a. the server receives 342 requests. 24. 26. In the Poisson experiment. .23. c. Compare the result in (b) with the variance in Exercise 28. compute the average of the squares of the errors. set r = 1 and t = 2. 25. Compute the appropriate relative frequency functions and investigate empirically the theoretical result in Exercise 23. Note that the conditional distribution is independent of the rate r . Find the probability that at least 4 requests came during the first 3 minutes of the period. Estimating the Rate In many practical situations. updating after each run. Suppose that requests to a web server follow the Poisson model. In the Poisson experiment. Run the experiment 1000 times. and that 1 request comes in a five minute period. For each run. 29 . and that 10 requests come during a 5 minute period. set r = 3 and t = 5. Show that the conditional distribution of N s given N t = n is binomial with trial parameter n and success parameter p = st. updating after each run. In a one hour period. Suppose that 0 < s < t and that n is a positive integer.

- Rate of Convergence
- Complex Analysis
- EM Algorithm
- Assignment Math Power Point (1)
- smmmmmmmmmmmmmmmmm
- Discrete Random Variables Collection
- The Feynman-Kac Theorem
- Fried Gut
- RitzMethod.paper
- hma13_Chapter12
- svm
- probreview.pdf
- OD Nonlinear Programming 2010
- Approximation
- Levyprocessesinfinance
- EDO Riccati
- Scribd Upload_6th Math Power Standards_holt Text
- Kuan C.-m. Introduction to Econometric Theory (LN, Taipei, 2002)(202s)_GL
- QDM Intro Complete
- Study Guide
- Introduction to Matlab Vector and Matrix
- Practice Exam Sol 20101116
- JAM MS Syllabus
- 3 - 8 - Lecture 14 BONUS
- On High-Order Discrete Derivatives of Stochastic Variables
- DM-Ch3
- 0779
- 22 Slides
- Workbook 06
- lec5_DFT

Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

We've moved you to where you read on your other device.

Get the full title to continue

Get the full title to continue listening from where you left off, or restart the preview.

scribd