Probability density function : An arbitrary continuous random variable X is similarly described by its probability density function f x = f X

Size: px
Start display at page:

Download "Probability density function : An arbitrary continuous random variable X is similarly described by its probability density function f x = f X"

Transcription

1 Week 6 notes : Continuous random variables and their probability densities WEEK 6 page 1 uniform, normal, gamma, exponential,chi-squared distributions, normal approx'n to the binomial Uniform [,1] random variable : For a simple example of a continuous random variable we consider choosing a value between and 1 (hence lying in the interval [,1] ) in which any real number in this interval is equally likely to be chosen. To obtain such a uniform [,1] random variable we define the probability P a X b that X lies between the values a and b with ab 1 to be the portion of the area lying between the values x = a and x = b under the curve having constant height 1 for x between and 1 and height elsewhere f x=1 if x 1 ( f x= elsewhere ). In this way the probability only depends on the length b a of the sub-interval [a,b] hence is uniformly spread over the interval [,1]. Uniform [a,b] random variable : Generalizing this we can next consider a uniform [a,b] random variable as one having density which is constant on the interval [a,b] and elsewhere. The constant density f x= 1 b a for axb is determined from the condition that the total area under the density curve y= f x (= total probability) equals 1. ( rectangle of width b a having area 1 determines the height f x of the rectangle ) Probability density function : An arbitrary continuous random variable X is similarly described by its probability density function f x= f X x meaning again that the probability that X lies between two values a and b is the integral of the density f x on this interval which is the area under the density curve. In symbols b P a X b= f xdx = area under the curve y = f x between a and b. a We can regard this as the probability measure of the set (event) which is the interval [a,b]. There will in general be certain sets which can not be obtained as countable unions or intersections of intervals for which one is not able to define a probability. However in practice this rarely comes up. (Technically the sample space can be abstract and what we have really defined is the probability (acting on the actual sample space ) of the inverse of the function X. This inverse maps from the reals back to the sample space. This induces a probability measure P X 1 defined on sets of reals and so for all practical purposes we can view events as sets of real numbers without loss of generality. ) For a continuous random variable the probability that X equals any particular value is since according to our above definition this is P X =a= P a X a which is given by the integral of the density f x from a to a which is. Consequently for a continuous random variable, whether we include an endpoint of an interval or not in calculating the probability makes no difference : P a X b= P ax b. Since probabilities are determined by densities and visa versa, from our axioms of probability we must require that 1) f x (the density is non-negative) 2) f xdx=1 The first requirement is to insure that we don't get negative probabilities which are forbidden, and the second just says that the total probability is 1. The interpretation of the density is that it gives the local probability per unit length along the x-axis in the sense that for x lying in a small enough interval say [a, a x] of width x provided the

2 density is a continuous function at x=a, the probability is approximately WEEK 6 page 2 f a x f x x that the random variable X lies in this interval : a x P ax a x= f xdx f x x for x near a. a Said differently, if we define the (cumulative) distribution function (cdf ) F x=f X x=p X x= f t dt (Johnson just calls it the distribution function) for which one easily verifies that F b F a=p a X b (i.e. area to the left of b under the density curve minus area to the left of a equals area between a and b) then by the fundamental theorem of calculus, the derivative of the cdf F x is just the density f x : d dx F x= f x F a x F a P a X a x = lim = lim x x x x where we have recalled the definition of the derivative of F x. We see that the above approximation for the probability holds exactly in the limit x. Definition of expected value of X : The main change in passing from discrete to continuous random variables is the replacement of the discrete sum by the continuous integral. For a continuous random variable X with density f x, the expected value is defined as =E [ X ]= x x f x dx and one can show that for any random variable which is a measurable function h X of the random variable X (which we won't define precisely here but which will be the case for almost any function occurring in practice) the expected value is E [h X ]= In particular this gives for the variance the formula V X =E[X 2 ]=E [ X 2 ] 2 since E[ X 2 ]= hx f xdx. x 2 f xdx= x 2 f x dx 2 =E[ X 2 ] 2 EXAMPLE 1 : (like HW problems 5.2, 5.3, 5.13 ) : Consider a random variable X having the density function f x=k x 5 for x1 ( f x= else ). a) Find the constant k which makes this a density and then find P 1 3 X 2 3 : The requirement that the total probability is 1 translates as 1=k x 5 dx= k 6 P 1 3 X 2 2/3 3 = 6 x 5 dx= 2 6 1/ = b) Find the mean and variance of X : Thus 1 E [ X ]= x 6x 5 dx= 6 x 6 dx= E [ X 2 ]= 1 6 x 7 dx= which gives k=6.

3 gives the variance. 2 =E [ X 2 ] 2 = = WEEK 6 page 3 c) Find the cumulative distribution function of X : F x= 6t 5 dt = x 6 for x1 ( F x= for x and F x=1 for x 1 ) d) Using this distribution function find P.3 X.5 : P.3 X.5=F.5 F.3= = Also find P X.9 : x P X.9=1 P X.9=1 F.9= = A Standard Normal random variable Z is one with mean and variance 1 having density given by the symmetric bell-shaped curve : f x ;,1= e x /2 For such a normally distributed random variable we write Z ~ N(,1). It is common to use the letter Z to indicate a standard normal. Normal random variable : A random variable X has normal distribution with parameters mean and variance 2, in symbols X ~ N, 2 if its density is of the form f x ;, 2 = e x /2 2 One can show by the definition of expected value that the parameters and 2 really do give the mean and variance of this density. It is a fact that if X ~ N, 2 is normally distributed with parameters and 2 then the standardized random variable Z = X ~ N,1 has a standard normal distribution with mean and variance 1. That we get the stated mean and variance is because constants factor outside expectations and the expected value of a sum or difference is the sum or difference of the expected value so that E [ X ]= 1 E [ X ] = since E [ X ]=. Also using the definition of the variance, we find that when computing the variance of a constant times.

4 a random variable, the constant gets squared before pulling it outside the variance WEEK 6 page 4 so that V [ X ]= 1 V [ X ]=1 2 as claimed ( since V [ X ]=V [ X ]= 2 ) To see that the distribution is still in fact normally distributed, observe that the cumulative distributions of the random variables Z and X are related by : F Z z=p X z=p X z=f z=f x X X where x= z. Then by the chain rule, and noting that x 2 /2 2 = z 2 /2 one has f Z z= d dz F z= d Z dx F dx X x dz = e z / 2 = e z / 2 which is the standard normal density. There is a trick used to show that the constant density. Writing 1 2 is the correct one to use in the standard normal I = e x 2 / 2 dx One notes that this integral stays the same when one changes the dummy variable of integration from x to y so that one has I 2 = e x2 /2 dx e y 2 /2 dy = e x2 y 2 / 2 dy dx Re-arranging the order of integration can be done since the y integral is a constant with respect to x. But now if we change to polar coordinates for the radius r going from to one has x 2 y 2 =r 2 and after breaking up the plane into circular donut shaped annulus regions of radius r and infinitesimal thickness dr and integrating out the angle the area element dx dy turns into 2 r dr so we find the above integral becomes I 2 = 2 e r2 /2 r dr = 2 which verifies the claim since we must choose the constant k so that ki = 1. That the mean of the standard normal is is a consequence of symmetry since 2 E [ X ]= xe x 2 / 2 dx=lim R R R xe x2 / 2 dx x e x2 / 2 dx = (To see that the first integral on the right is minus the second we change variable from x to -x in that integral yielding the product of 3 minus signs which is an overall minus the 2 nd integral : the first minus comes from replacing x by -x, the second by replacing dx by dx and the third because the limits of integration for -x have changed from -R to for x to R to for -x which requires the interpretation that we must add a minus sign when flipping the limits from R to back to to R. ) To see that the variance of the standard normal really is 1, since the mean is the variance is just

5 I =E [ X 2 ] where 2 I= x 2 e x2 /2 dx & we can either do a polar coordinate trick WEEK 6 page 5 2 I 2 = x 2 e x 2 / 2 dx y 2 e y2 / 2 dx= 2 x 2 y 2 e x2 y 2 / 2 dy dx= rcos 2 rsin 2 e r2 /2 r dr d like we did before { but this now involves an integration over the angle and requires the trig identities sin 2=2sin cos and sin 2 2=1 cos 4/2 This cos 4 term vanishes (gives ) after doing the integration. One changes variables to u=r 2 /2 so du=r dr. This is a good exercise in integration. } or : However it is considerably easier to simply integrate by parts, namely 2 2 = x 2 e x 2 / 2 dx= x d e x 2 /2 is of the form for which integration by parts applies with u=x and v= e x2 / 2 so that using u dv=uv v du now the uv term vanishes at the limits of integration so the integral reduces to 2 = e x 2 / 2 dx/2=1 since this is just the total area under the standard normal curve which we know equals 1. (This integral was evaluated earlier by the polar coordinate trick above.) To see the mean of the normal distribution is really we have E [ X ]= x e x 2 /2 2 dx /2 which by the change of variables z= x / hence dx= dz becomes = ze z2 / 2 dz /2 = z e z 2 / 2 dz /2 e z2 / 2 dz / 2 = 1= which proves the claim since we already saw that the first integral on the right vanishes by symmetry and the second is just the total area under the standard normal curve which is 1. To see that the variance of the normal distribution really is 2, we have V [ X ]= x 2 e x 2 / 2 2 dx /2 which by the same change of variable as above becomes = z 2 e z2 / 2 dz /2 = 2 z 2 e z2 /2 dz /2 = 2 since the rightmost integral is just the variance of the standard normal which we have seen is 1. EXAMPLE 2 : a) Problem 5.31 from the text : The specifications for a certain job calls for washers with an inside diameter of.3±.5 inch. If the inside diameter is normally distributed with mean =.32 and standard deviation =.3 what percentage of the washers will meet the specifications? Let X = inside diameter of a randomly selected washer Then the standardized variable Z = X.32 will be standard normal N(,1).3 The question translates into what is the probability P.3.5 X.3.5

6 WEEK 6 page 6 = P Z = X = P 7/3Z 1= F 1 F 2.333= =.8315=83.15% Note that in using the cumulative distribution function for the standard normal given in table 3 of Appendix B at the back of the book, the more accurate value.98 for F(-2.333) is obtained by linear interpolation of the values F( ) =.99 and F( ) =.96 since it lies one third of the way between these two and one third of.3 is.1 which we subtract from.99. b) For the above problem, for what value of the inside diameter is the probability 98% that the washer's inside diameter will exceed this value? We wish to find the diameter x say for which P X x =.98 or equivalently we first find the standardized value z = x.32 for which the standardized variable Z = X.32 satisfies.3.3 P Zz =.98. Then we have P Z z =1.98=.2 which from table 3 of Appendix B is the linear interpolation between P Z 2.5=.22 and P Z 2.6=.197 The value.2 is.2 less than the first value which lies.5 above the 2 nd value so we want to go 2/5 or 4 tenths of the way between the two values or z = 2.54 which says x =.3 z.32= = =.2958 inch c) What is the probability that the inside diameter is at least.35? P X.35=P Z = X =1 = P Z 1 = 1 P Z = =.1586 or Note that by the symmetry of the standard normal curve, we could have also obtained the answer via P Z1=P Z 1=.1586 which can be found directly from table 3. Had we asked what is the probability that the inside diameter is at most.35 we would have wanted P X.35=1 P X.35= P Z 1=.8413 Note that the event that a standard normal lies at least 1 standard deviation from the mean has double the probability that the inside diameter is at least.35, namely P Z 1 or Z1=2PZ 1=2.1586=.3172 Review question : For a Poisson random variable with parameter deviation? =5 what is the standard The parameter for a Poisson equals both the mean= 5 and the variance =5 so the standard deviation of this is by definition just the square root of the variance which is 5. Recall the above Poisson random variable has distribution P X =k= 5k k! e 5. The z-critical value z is the 11 percentile of the standard normal distribution defined by =P Z z

7 so that 1 =P Z z. That is is the area under the standard normal curve WEEK 6 page 7 to the right of z and 1 gives the area to the left of z. By symmetry of the standard normal curve the z-value for which the area to the left of this value is (hence the area to the right is 1 ) is z 1 = z From table 3 of Appendix B we find z.1 =2.33 and z.5 = Note this says that there is a 98% chance that a standard normal random variable lies within 2.33 standard deviations from (the mean) which is to say that Z lies between z.1 = 2.33 and z.1 =2.33 since.2 is the probability of the complementary event that Z is either greater than 2.33 or that Z is less than by symmetry since both of these disjoint events have the same probability.1. Note that to say that roughly 95% of the area under the standard normal lies within two standard deviations of the mean is to say that z.25 is close to 2 or equivalently that the cumulative distribution function F(-2) is close to.25 ( table 3 of Appendix B gives this as F(-1.96 )) From this table it would thus be more accurate to say that 95.44% lies within two standard deviations and that 95% lies within 1.96 standard deviations of (the mean). Normal Approximation to the Binomial distribution We have already encountered the Poisson approximation to the binomial distribution which was derived in the regime for which the number of trials or sample size n is large (exactly Poisson in limit n ) while success probability p is small so that the mean number of successes in n trials np= is fixed. The normal approximation works in the different regime where both np15 and n1 p15. For n sufficiently large it is possible that both regimes overlap so that both approximations are valid and yield approximately the same answer.. Recall that for a binomial random variable with parameters n and p X = the number of successes in n Bernoulli trials we can regard X as a sum of n independent identically distributed (i.i.d.) Bernoulli ( or 1 valued) random variables each having expected value the success probability p. Since the mean and standard deviation of this binomial random variable we know are E [ X ]=np and X =n p1 p one then has Theorem 5.1 of the text (normal approximation to the binomial distribution) : The standardized variable Z= X np is approximately standard normal and becomes exactly np 1 p so in the limit as n. This will generally be a good approximation provided both np15 and n1 p15 so that implicitly n3 (Jay Devore's Statistics for Engineers book uses 1 instead of > 15 ) This is a special case of the n Central Limit Theorem (Theorem 6.2 of the text). Any sum S n = i =1 X i of a large number of i.i.d. (independent identically distributed) random variables X i each having mean =E [ X i ] and finite variance V [ X i ]= 2 ( n > 3 in practice is usually large enough ) is approximately normally distributed. As we have seen the standardized variable will then be (approximately) standard normal.

8 Specifically WEEK 6 page 8 Z= S n n n = x /n is approximately standard normal for large n. To get the second expression on the right we have divided numerator and denominator of the quotient on the left by n. Here x= S n is the sample mean. Since x is a sum it is approximately normal for n large n. Since constants factor outside expectations and the expected value of a sum is the sum of the n expected values we have E [x]= 1 E [ X n i ]= 1 n = which says that i=1 n the expected value of the sample mean is the population mean : E [x]= (said differently the sample mean is an unbiased estimator for the population mean). Similarly since the variance of a sum of independent random variables is the sum of the variances but constants get squared before being pulled outside the variance we have V [x]= 1 2 V [S n n ]= 1 2 n n 2 = 2 n so that the standard deviation of the sample mean x is x = / n The continuity correction is typically used when approximating a discrete count random variable like the binomial random variable X by a continuous random variable as in the standard normally distributed Z in the above normal approximation to the binomial. That is we view the discrete event say { X =14 } as equivalent to the continuous event {13.5 X 14.5}. for purposes of approximating the standardized variable by a standard normal one by Theorem 5.1. Similarly for the events { X 14}={ X 14.5} and for { X 14 }={ X 13.5 } We would have for example the approximation that a standard normal random variable Z satisfies P X =14=P 13.5 np np 1 p Z = X np np 1 p 14.5 np np 1 p To see that some kind of continuity correction is needed, note since continuous random variables take specific values with probability, there is probability that a standard normal takes the specific value 14 np corresponding to the single value X =14. However, the density function of the np1 p standard normal evaluated at this value in the middle of the above interval does make sense and when this function value is multiplied by the length of the small interval 1/np1 p (proportional to 1/n ) we get an approximation to the integral of the nearly constant density. The central limit theorem applied to discrete integer valued random variables possibly re-scaled (or lattice valued ) is usually stated in this way by evaluating the density at a specific location and multiplying by the length

9 of the interval. Higher order corrections involving a polynomial times the standard WEEK 6 page 9 normal density are at times used. EXAMPLE 3 Thus when flip a fair coin 36 times so n = 36 and p = 1/2 we'd have the chances of seeing 14 heads is approximately (with np=36 /2=18 and np 1 p =3 ) using table 3 of Appendix B for the standard normal cumulative distribution function F (x) which is the area to the left of x under the standard normal curve : P X =14=P Z = X = P 3/ 2Z 7/6=F 7/6 F 3 /2=F F 1.5 = =.548 where we have used linear interpolation to arrive at F( ) which is 2/3 of the way between the two values F( -1.16) =.123 and F(-1.167) =.121 whose difference.2 is roughly.21 so 2/3 of this is.14 less than.123 equals Note again that the probability P az b=f b F a equals the difference of the cumulative distribution function F for these values since the probability that the standard normal variable Z lies between a and b is just the area under the standard normal curve between a and b which is the area F(b) to the left of b minus F(a) ( the area to the left of a ) EXAMPLE 4 Problem 5.37 of the text : The probability that an electronic component will fail in less than 1 hours of continuous use is.25. Use the normal approximation to find the probability that among 2 such components, fewer than 45 will fail in less than 1 hours of continuous use. We have the probability of failure in less than 1 hours of continuous use is the binomial parameter p =.25 while the the sample size parameter is n = 2. Our binomial random variable is then X = The number of the 2 components which fail in less than 1 hours of continuous use which has mean E [ X ]=np=5 and standard deviation X = np1 p=5 3/4=5/ 26 We want to find (using the continuity correction ) P X 45=P X 44.5= P Z = X 5 5/ / 26 = 11/2 5/2 6 =.8981 (Be careful here to use 44.5 and not 45.5! ) From table 3 of Appendix B, P Z.8981 P Z.9=.1841 The mean and variance of a uniform [a,b] random variable X : To see that the mean of a uniform [a,b] is = ab 2 and the variance of a uniform [a,b] is 2 = 1 12 b a2, recall such a uniform random variable has constant density on the interval of x values from a to b of width b-a so since the total probability = 1 is just the area under this rectangle, the constant density which is the height f x of the rectangle must equal 1/(b-a). Since the density is outside of the interval [a,b], we have for the mean

10 b =E [ X ]= x f xdx= 1 b a b a a the variance we have b E [ X 2 ]= a 2 = ab2 4 x 2 f xdx= 1 b a a b x dx= 1 b a b2 2 a2 2 = ab 2 x 2 dx= 1 b a b3 3 a3 3 = a2 abb 2 3 and simplifying gives the result (since 2 =E [ X 2 ] 2 ). and to compute WEEK 6 page 1. Subtracting off EXAMPLE 5 problem 5.47 of text : From experience Mr. Harris has found that the low bid on a construction job can be regarded as a random variable X having the uniform density f x= 3 4C for 2C 3 x2c and f x= elsewhere, where C is his own estimate of the cost of the job (what it will cost him). What percentage z should Mr. Harris add to his cost estimate to maximize his expected profit? If Mr. Harris bids (1+z) C, if the low bid X is less than his bid he will make no profit (and have no costs) but he will be paid (1+z) C if the low bid is greater than his bid of (1+z) C so that he wins the job but it will cost him C so his net profit is then z C. Thus his expected profit is just his profit zc times the probability of obtaining that profit (which is the probability that the low bid exceeds his own) or zc P 1 zc X 2C= zc 3 4C 2C 1zC = 3 4 z 1 zc. This will be maximized when z(1-z) is maximized so when he charges a z =1/2 = 5% mark up over his actual cost estimate. The log-normal distribution arises when we have a random variable X whose logarithm log X has a log X normal distribution with mean and variance 2 so that the standardized variable Z = is standard normal. Note that for such a random variable X > since otherwise the log would not exist. The density of a log-normal random variable X is = 1 2 x 1 e log x 2 /2 2 for x, and is elsewhere. To see this note that the cumulative distribution function of X is related to the cdf of a standard normal random variable Z by log X log x log x F X x=p X x=p Z = =F Z =F Z z where log x z= of the cumulative distribution function so. Recall that by the fundamental theorem of calculus the density is the derivative f X x= d dx F x= d X dx F log x Z = d dz F z dz Z dx = f Z z dz dx = 1 2 e z 2 /2 1 x since by the chain rule we first compute the derivative of F Z z with respect to z which gives the

11 log x standard normal density in the variable z= multiplied by the WEEK 6 page 11 derivative of z with respect to x. Plugging in the expression for z in terms of x gives the result. The Gamma distribution and its special cases the exponential and chi-squared distributions : This distribution has density f x= 1 x 1 e x/ for x,, and is elsewhere. Here is the gamma function defined by = x 1 e x dx which satisfies = 1 1 and hence = 1! when is a positive integer which can be seen by integration by parts. The mean of the gamma distribution is = and the variance of the gamma distribution is 2 = 2. The exponential distribution corresponds to the special case where =1 which gives for the density of an exponential random variable : f x= 1 e x/ for x, and f(x) = elsewhere. The mean and variance of an exponential random variable are then = and 2 = 2. Alternate form of the density of an exponential random variable in terms of the parameter =1/ f x= e x for x, so that the mean and variance are then =1/ and 2 =1/ 2. The cumulative distribution function for an exponentially distributed random variable : x F X x=p X x= e t dt = 1 e x =1 e x/ Note this says that P X x = 1 F X x = e x To good approximation the lifetime T of a tungsten filament light bulb is exponentially distributed. There we would replace x above by a time t in which case P T t = e t gives the probability that the lifetime of the bulb exceeds the time t. The exponential distribution is the only one which has the Memoryless Property : an exponentially distributed lifetime random variable T is the only distribution which has the property that for positive times t and s P T ts Ts= P T s ( memoryless property ) This says for example that if the light bulb has lived for 1 years, the distribution of the remaining lifetime left is the same as if the bulb were brand new!

12 We won't show the only part but the memoryless property itself is a simple WEEK 6 page 12 consequence of the definition of conditional probability since ts PT ts e P T ts T s= = =e t =P T t PT s e s Note above that the intersection event {T ts and Ts} is the same as the event {T ts} since the latter implies {T s} as well. Relationship between Poisson process and exponential random variables : Recall a Poisson process X(t) = number of events occurring in a time interval of length t with mean arrival rate ( = the expected number of events occurring per unit time) is one with t k P X t=k= e t k! Then the waiting time until the first arrival (first event) or the time between successive arrivals (events) has an exponential distribution with parameter =1/ =. Again waiting times until the first event or Waiting times between events in a Poisson process are exponentially distributed. To see this note that for the waiting time T =T 1 until the first event, saying that T exceeds time t is the same as saying that events have occurred in the Poisson process : P T t=p X t==e t but this is exactly the tail probability of an exponential random variable with parameter =1/ = ( The complementary event is exactly the cumulative distribution function of an exponential. ) Similarly for the waiting time T =T 2 between the first and second events we have P T 2 t T 1 =s=p events in (s, s+t] T 1 =s = P events in (s, s+t] =e t The last two equations follow by the independence and the stationarity (i.e identical distribution) of disjoint equal time increments assumptions of the Poisson process. But then by the law of total probability P T 2 t= s (The first sum is a kind of conditional expectation P T 1 =s P T 2 t T 1 =s=e t s P T 1 =s=e t = E [ P T 2 t T 1 ] ) Similarly one sees that all the inter-arrival times (waiting times between two successive events) are independent and identically distributed exponential random variables. The Poisson assumptions are often satisfied hence Poisson processes arise naturally in the real world and so exponential random variables often occur as waiting times between Poisson events. Recall the Assumptions used to obtain Poisson distribution as a limit of Binomial probabilities were : 1) Probability of 1 event occurring in a small time interval proportional to the length t=t /n of the time interval, with constant but does not depend on when the interval starts so : 2) identically distributed on each time sub-interval (1 event happens with probability p= t ) (A process not depending on time is called a stationary or time homogeneous process), 3) events in disjoint time intervals are independent, 4) Probability of more than one event occurring in a small time interval is negligible : This is what

13 insures only two possible outcomes (either events happen or 1 happens) WEEK 6 page 13 in a small enough time interval hence Bernoulli or 1 valued trials in the small sub-intervals of time but the sum of a large number of Bernoulli r.v.'s gives a Binomial number of events in the large time interval. Interpretation of the parameter of an exponential random variable : We can view the parameter of an exponential random variable as the rate per unit time at which events happen (in the light bulb case the event that the light bulb dies) whereas =1/ gives the mean time until the event. This is similar to the situation for geometric random variables where the probability 1/6 that a roll of a six sided fair die produces a 3 (success) we can regard as the rate at which successes (3's) happen per roll of the die while the expected time 6 until a 3 is rolled corresponds to the mean time until the event. EXAMPLE 6 : A skillful typist has a low probability of making a typo on a typed page of text. There are a large number n of characters on a page n =25 say. Assuming typo errors occur independently for each character with the same small probability p, the binomial (25 t, p) number of typos on t pages is then well approximated by a Poisson process with parameter t giving the mean number of errors for t pages and =np=25 p the mean number of errors in a single page. The waiting time T (measured in number of pages typed which may be a fraction of a page) until the first error occurs or between two successive errors is then approximately exponential with parameter. Note that if =3 gives the mean of the Poisson number of errors on a page then we expect to wait for time 1/3=1/ of a page until the first error occurs which agrees with the formula for the mean of an exponential, in this case the exponential waiting time until the first Poisson event (a typo) occurs. We are viewing time as continuous when in fact the smallest fraction of a page here is 1 character or 1/25 of (the number of characters making up) a page. In reality the time we have to wait in units of number of characters typed or 1/25 of a page is a geometric random variable with small parameter p and is only approximately exponential. P X =k =P T =t=p t 1/ 2tT T 1/2t (<--continuity correction) = the probability we ' ll wait for k characters to be typed until the first error with X a geometric random variable, T = X /n is the waiting time with t=k /n measured in pages P X =k=1 p k 1 p where p=/n=/25. By the same approximations used to approximate a binomial by a Poisson random variable, n large, p small, np= fixed, for time t pages typed the number of characters typed is k=n t=25t so that with t=1/n=1 /25 of a page giving the time to type one character t = k /25 = k /n and P X =k=1 /n nt 1 /n =P T =t e t t Relationship between exponential and geometric r.v.'s : The geometric random variable is the discrete analogue of the exponential and becomes exponential in the limit in which we take k=[nt] is the greatest integer less than or equal to nt so that time is then approximately t k n and t= 1 n gives the time interval between successive values of k and probability per unit time scales as in the Poisson process as p= n (same assumptions and same approximations used ) so that P X =k =1 p k 1 p = 1 n [nt ] 1 n e t / n = e t t = P k 1/2/n X /nk1/ 2/ n = P t t/ 2T =X / ntt /2

14 using the continuity correction. In the limit as n with np= fixed, WEEK 6 page 14 we see the geometric random variable X re-scaled by 1/n is then approximated by an exponential r.v. T with parameter EXAMPLE 7 Suppose calls arrive at a telephone switchboard according to a Poisson process with rate one call every four minutes on average (so mean number of calls per minute is.25) Then X = the number of minutes between successive calls is an exponential random variable with mean rate =.25 (or equivalently =4 ) so a) the probability that more than 4 minutes elapse between successive calls is P X 4=e.254 =e 1 =.368 We could also have obtained this via the complementary event : P X 4 = 1 P X 4=1 F X x=1 1 e.254 =e 1 b) The mean time between successive calls is E [ X ] = 1 = 4 minutes. For exponential random variables the mean is also the standard deviation so the standard deviation of X the time between successive calls is also X = 1 =4 minutes c) Find the probability that a call arrives in less than 3 minutes : P X 3=F 3=1 e.253 =.5276 d) Find the probability that no calls arrive in a 8 minute interval : P X 8=e.258 =e 2 =.1353 Note that this is also the probability of deviating by at least 1 standard deviation from the mean. e) Find the probability that the next call arrives sometime between the 2 nd and 3 rd minute after the last call P 2 X 3=F 3 F 2=1 e e.252 =e.252 e.253 = =.1342 EXAMPLE 8 Consider 4 identical components connected in series, each of which has an exponential lifetime X i with parameter =.1 independent of the lifetime of the other components The system fails as soon as any of the components fails. Let X = lifetime of the system = min X i ;i=1,2,3,4 = minimum of the lifetimes of each component a) express the event { X t } that the system is functioning at time t in terms of the events { X i t } ; i=1,2,3,4 { X t }={ X 1 t } { X 2 t } { X 3 t } { X 4 t } b) What is the probability that the system functions at time t? By independence and the identical nature of the components this is just P X t=p X 1 t P X 2 t P X 3 t P X 4 t =P X 1 t 4 =e t 4 =e 4 t =e.4 t which is exactly the tail probability of an exponential random variable with parameter 4. Thus the system life is exponential with parameter 4. (Note : There is nothing special about the number of components being 4 here. Moreover the above

15 discussion illustrates how to find the WEEK 6 page 15 distribution of the minimum of a collection of independent random variables from the distribution of each of them ) It can be shown that the sum of independent gamma random variables each with the same parameter but arbitrary values i of the parameter will also have a gamma distribution with the same and with parameter = i = the sum of the i 's. Thus the i sum of n independent exponential random variables with the same parameter =1/ (which are gamma with =1 ) is not exponential but rather a special case of the gamma distribution known as the Erlang distribution (gamma with parameters =n and =1/ ). The chi-squared distribution with parameter corresponds to the special case of the gamma distribution with =/2 and =2 and is the distribution of the X 2 random variable X 2 n 1 S2 = when S 2 = 1 n X 2 n 1 i x 2 i =1 is the sample variance of a sample of size n drawn from a normal population having variance 2. Here the parameter =n 1 is called the number of degrees of freedom. The chi-squared distribution is thus essentially the distribution of the sum of squares of normally distributed random variables and can easily be used to give the distribution of the sample variance of a sample drawn from a normally distributed population. We only mention here its relation to the gamma distribution but will postpone further discussion until chapter 6.

Random variables, probability distributions, binomial random variable

Random variables, probability distributions, binomial random variable Week 4 lecture notes. WEEK 4 page 1 Random variables, probability distributions, binomial random variable Eample 1 : Consider the eperiment of flipping a fair coin three times. The number of tails that

More information

Notes on Continuous Random Variables

Notes on Continuous Random Variables Notes on Continuous Random Variables Continuous random variables are random quantities that are measured on a continuous scale. They can usually take on any value over some interval, which distinguishes

More information

5. Continuous Random Variables

5. Continuous Random Variables 5. Continuous Random Variables Continuous random variables can take any value in an interval. They are used to model physical characteristics such as time, length, position, etc. Examples (i) Let X be

More information

Probability and Statistics Prof. Dr. Somesh Kumar Department of Mathematics Indian Institute of Technology, Kharagpur

Probability and Statistics Prof. Dr. Somesh Kumar Department of Mathematics Indian Institute of Technology, Kharagpur Probability and Statistics Prof. Dr. Somesh Kumar Department of Mathematics Indian Institute of Technology, Kharagpur Module No. #01 Lecture No. #15 Special Distributions-VI Today, I am going to introduce

More information

Section 5.1 Continuous Random Variables: Introduction

Section 5.1 Continuous Random Variables: Introduction Section 5. Continuous Random Variables: Introduction Not all random variables are discrete. For example:. Waiting times for anything (train, arrival of customer, production of mrna molecule from gene,

More information

Chapter 3 RANDOM VARIATE GENERATION

Chapter 3 RANDOM VARIATE GENERATION Chapter 3 RANDOM VARIATE GENERATION In order to do a Monte Carlo simulation either by hand or by computer, techniques must be developed for generating values of random variables having known distributions.

More information

Important Probability Distributions OPRE 6301

Important Probability Distributions OPRE 6301 Important Probability Distributions OPRE 6301 Important Distributions... Certain probability distributions occur with such regularity in real-life applications that they have been given their own names.

More information

FEGYVERNEKI SÁNDOR, PROBABILITY THEORY AND MATHEmATICAL

FEGYVERNEKI SÁNDOR, PROBABILITY THEORY AND MATHEmATICAL FEGYVERNEKI SÁNDOR, PROBABILITY THEORY AND MATHEmATICAL STATIsTICs 4 IV. RANDOm VECTORs 1. JOINTLY DIsTRIBUTED RANDOm VARIABLEs If are two rom variables defined on the same sample space we define the joint

More information

Normal distribution. ) 2 /2σ. 2π σ

Normal distribution. ) 2 /2σ. 2π σ Normal distribution The normal distribution is the most widely known and used of all distributions. Because the normal distribution approximates many natural phenomena so well, it has developed into a

More information

Lecture 7: Continuous Random Variables

Lecture 7: Continuous Random Variables Lecture 7: Continuous Random Variables 21 September 2005 1 Our First Continuous Random Variable The back of the lecture hall is roughly 10 meters across. Suppose it were exactly 10 meters, and consider

More information

The Exponential Distribution

The Exponential Distribution 21 The Exponential Distribution From Discrete-Time to Continuous-Time: In Chapter 6 of the text we will be considering Markov processes in continuous time. In a sense, we already have a very good understanding

More information

6.4 Normal Distribution

6.4 Normal Distribution Contents 6.4 Normal Distribution....................... 381 6.4.1 Characteristics of the Normal Distribution....... 381 6.4.2 The Standardized Normal Distribution......... 385 6.4.3 Meaning of Areas under

More information

Math 461 Fall 2006 Test 2 Solutions

Math 461 Fall 2006 Test 2 Solutions Math 461 Fall 2006 Test 2 Solutions Total points: 100. Do all questions. Explain all answers. No notes, books, or electronic devices. 1. [105+5 points] Assume X Exponential(λ). Justify the following two

More information

CHAPTER 6: Continuous Uniform Distribution: 6.1. Definition: The density function of the continuous random variable X on the interval [A, B] is.

CHAPTER 6: Continuous Uniform Distribution: 6.1. Definition: The density function of the continuous random variable X on the interval [A, B] is. Some Continuous Probability Distributions CHAPTER 6: Continuous Uniform Distribution: 6. Definition: The density function of the continuous random variable X on the interval [A, B] is B A A x B f(x; A,

More information

Statistics 100A Homework 7 Solutions

Statistics 100A Homework 7 Solutions Chapter 6 Statistics A Homework 7 Solutions Ryan Rosario. A television store owner figures that 45 percent of the customers entering his store will purchase an ordinary television set, 5 percent will purchase

More information

Chapter 4 Lecture Notes

Chapter 4 Lecture Notes Chapter 4 Lecture Notes Random Variables October 27, 2015 1 Section 4.1 Random Variables A random variable is typically a real-valued function defined on the sample space of some experiment. For instance,

More information

Sums of Independent Random Variables

Sums of Independent Random Variables Chapter 7 Sums of Independent Random Variables 7.1 Sums of Discrete Random Variables In this chapter we turn to the important question of determining the distribution of a sum of independent random variables

More information

e.g. arrival of a customer to a service station or breakdown of a component in some system.

e.g. arrival of a customer to a service station or breakdown of a component in some system. Poisson process Events occur at random instants of time at an average rate of λ events per second. e.g. arrival of a customer to a service station or breakdown of a component in some system. Let N(t) be

More information

Summary of Formulas and Concepts. Descriptive Statistics (Ch. 1-4)

Summary of Formulas and Concepts. Descriptive Statistics (Ch. 1-4) Summary of Formulas and Concepts Descriptive Statistics (Ch. 1-4) Definitions Population: The complete set of numerical information on a particular quantity in which an investigator is interested. We assume

More information

Master s Theory Exam Spring 2006

Master s Theory Exam Spring 2006 Spring 2006 This exam contains 7 questions. You should attempt them all. Each question is divided into parts to help lead you through the material. You should attempt to complete as much of each problem

More information

Math 120 Final Exam Practice Problems, Form: A

Math 120 Final Exam Practice Problems, Form: A Math 120 Final Exam Practice Problems, Form: A Name: While every attempt was made to be complete in the types of problems given below, we make no guarantees about the completeness of the problems. Specifically,

More information

MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.436J/15.085J Fall 2008 Lecture 5 9/17/2008 RANDOM VARIABLES

MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.436J/15.085J Fall 2008 Lecture 5 9/17/2008 RANDOM VARIABLES MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.436J/15.085J Fall 2008 Lecture 5 9/17/2008 RANDOM VARIABLES Contents 1. Random variables and measurable functions 2. Cumulative distribution functions 3. Discrete

More information

correct-choice plot f(x) and draw an approximate tangent line at x = a and use geometry to estimate its slope comment The choices were:

correct-choice plot f(x) and draw an approximate tangent line at x = a and use geometry to estimate its slope comment The choices were: Topic 1 2.1 mode MultipleSelection text How can we approximate the slope of the tangent line to f(x) at a point x = a? This is a Multiple selection question, so you need to check all of the answers that

More information

Solutions to Homework 10

Solutions to Homework 10 Solutions to Homework 1 Section 7., exercise # 1 (b,d): (b) Compute the value of R f dv, where f(x, y) = y/x and R = [1, 3] [, 4]. Solution: Since f is continuous over R, f is integrable over R. Let x

More information

For a partition B 1,..., B n, where B i B j = for i. A = (A B 1 ) (A B 2 ),..., (A B n ) and thus. P (A) = P (A B i ) = P (A B i )P (B i )

For a partition B 1,..., B n, where B i B j = for i. A = (A B 1 ) (A B 2 ),..., (A B n ) and thus. P (A) = P (A B i ) = P (A B i )P (B i ) Probability Review 15.075 Cynthia Rudin A probability space, defined by Kolmogorov (1903-1987) consists of: A set of outcomes S, e.g., for the roll of a die, S = {1, 2, 3, 4, 5, 6}, 1 1 2 1 6 for the roll

More information

6.3 Conditional Probability and Independence

6.3 Conditional Probability and Independence 222 CHAPTER 6. PROBABILITY 6.3 Conditional Probability and Independence Conditional Probability Two cubical dice each have a triangle painted on one side, a circle painted on two sides and a square painted

More information

Lecture 2: Discrete Distributions, Normal Distributions. Chapter 1

Lecture 2: Discrete Distributions, Normal Distributions. Chapter 1 Lecture 2: Discrete Distributions, Normal Distributions Chapter 1 Reminders Course website: www. stat.purdue.edu/~xuanyaoh/stat350 Office Hour: Mon 3:30-4:30, Wed 4-5 Bring a calculator, and copy Tables

More information

Statistics 100A Homework 4 Solutions

Statistics 100A Homework 4 Solutions Problem 1 For a discrete random variable X, Statistics 100A Homework 4 Solutions Ryan Rosario Note that all of the problems below as you to prove the statement. We are proving the properties of epectation

More information

( ) is proportional to ( 10 + x)!2. Calculate the

( ) is proportional to ( 10 + x)!2. Calculate the PRACTICE EXAMINATION NUMBER 6. An insurance company eamines its pool of auto insurance customers and gathers the following information: i) All customers insure at least one car. ii) 64 of the customers

More information

An Introduction to Basic Statistics and Probability

An Introduction to Basic Statistics and Probability An Introduction to Basic Statistics and Probability Shenek Heyward NCSU An Introduction to Basic Statistics and Probability p. 1/4 Outline Basic probability concepts Conditional probability Discrete Random

More information

VISUALIZATION OF DENSITY FUNCTIONS WITH GEOGEBRA

VISUALIZATION OF DENSITY FUNCTIONS WITH GEOGEBRA VISUALIZATION OF DENSITY FUNCTIONS WITH GEOGEBRA Csilla Csendes University of Miskolc, Hungary Department of Applied Mathematics ICAM 2010 Probability density functions A random variable X has density

More information

Microeconomic Theory: Basic Math Concepts

Microeconomic Theory: Basic Math Concepts Microeconomic Theory: Basic Math Concepts Matt Van Essen University of Alabama Van Essen (U of A) Basic Math Concepts 1 / 66 Basic Math Concepts In this lecture we will review some basic mathematical concepts

More information

Overview of Monte Carlo Simulation, Probability Review and Introduction to Matlab

Overview of Monte Carlo Simulation, Probability Review and Introduction to Matlab Monte Carlo Simulation: IEOR E4703 Fall 2004 c 2004 by Martin Haugh Overview of Monte Carlo Simulation, Probability Review and Introduction to Matlab 1 Overview of Monte Carlo Simulation 1.1 Why use simulation?

More information

Principle of Data Reduction

Principle of Data Reduction Chapter 6 Principle of Data Reduction 6.1 Introduction An experimenter uses the information in a sample X 1,..., X n to make inferences about an unknown parameter θ. If the sample size n is large, then

More information

IEOR 6711: Stochastic Models I Fall 2012, Professor Whitt, Tuesday, September 11 Normal Approximations and the Central Limit Theorem

IEOR 6711: Stochastic Models I Fall 2012, Professor Whitt, Tuesday, September 11 Normal Approximations and the Central Limit Theorem IEOR 6711: Stochastic Models I Fall 2012, Professor Whitt, Tuesday, September 11 Normal Approximations and the Central Limit Theorem Time on my hands: Coin tosses. Problem Formulation: Suppose that I have

More information

LOGNORMAL MODEL FOR STOCK PRICES

LOGNORMAL MODEL FOR STOCK PRICES LOGNORMAL MODEL FOR STOCK PRICES MICHAEL J. SHARPE MATHEMATICS DEPARTMENT, UCSD 1. INTRODUCTION What follows is a simple but important model that will be the basis for a later study of stock prices as

More information

6.041/6.431 Spring 2008 Quiz 2 Wednesday, April 16, 7:30-9:30 PM. SOLUTIONS

6.041/6.431 Spring 2008 Quiz 2 Wednesday, April 16, 7:30-9:30 PM. SOLUTIONS 6.4/6.43 Spring 28 Quiz 2 Wednesday, April 6, 7:3-9:3 PM. SOLUTIONS Name: Recitation Instructor: TA: 6.4/6.43: Question Part Score Out of 3 all 36 2 a 4 b 5 c 5 d 8 e 5 f 6 3 a 4 b 6 c 6 d 6 e 6 Total

More information

TOPIC 4: DERIVATIVES

TOPIC 4: DERIVATIVES TOPIC 4: DERIVATIVES 1. The derivative of a function. Differentiation rules 1.1. The slope of a curve. The slope of a curve at a point P is a measure of the steepness of the curve. If Q is a point on the

More information

Math 1B, lecture 5: area and volume

Math 1B, lecture 5: area and volume Math B, lecture 5: area and volume Nathan Pflueger 6 September 2 Introduction This lecture and the next will be concerned with the computation of areas of regions in the plane, and volumes of regions in

More information

UNIT I: RANDOM VARIABLES PART- A -TWO MARKS

UNIT I: RANDOM VARIABLES PART- A -TWO MARKS UNIT I: RANDOM VARIABLES PART- A -TWO MARKS 1. Given the probability density function of a continuous random variable X as follows f(x) = 6x (1-x) 0

More information

E3: PROBABILITY AND STATISTICS lecture notes

E3: PROBABILITY AND STATISTICS lecture notes E3: PROBABILITY AND STATISTICS lecture notes 2 Contents 1 PROBABILITY THEORY 7 1.1 Experiments and random events............................ 7 1.2 Certain event. Impossible event............................

More information

Math 431 An Introduction to Probability. Final Exam Solutions

Math 431 An Introduction to Probability. Final Exam Solutions Math 43 An Introduction to Probability Final Eam Solutions. A continuous random variable X has cdf a for 0, F () = for 0 <

More information

4. Continuous Random Variables, the Pareto and Normal Distributions

4. Continuous Random Variables, the Pareto and Normal Distributions 4. Continuous Random Variables, the Pareto and Normal Distributions A continuous random variable X can take any value in a given range (e.g. height, weight, age). The distribution of a continuous random

More information

Review of Fundamental Mathematics

Review of Fundamental Mathematics Review of Fundamental Mathematics As explained in the Preface and in Chapter 1 of your textbook, managerial economics applies microeconomic theory to business decision making. The decision-making tools

More information

PYTHAGOREAN TRIPLES KEITH CONRAD

PYTHAGOREAN TRIPLES KEITH CONRAD PYTHAGOREAN TRIPLES KEITH CONRAD 1. Introduction A Pythagorean triple is a triple of positive integers (a, b, c) where a + b = c. Examples include (3, 4, 5), (5, 1, 13), and (8, 15, 17). Below is an ancient

More information

Homework 4 - KEY. Jeff Brenion. June 16, 2004. Note: Many problems can be solved in more than one way; we present only a single solution here.

Homework 4 - KEY. Jeff Brenion. June 16, 2004. Note: Many problems can be solved in more than one way; we present only a single solution here. Homework 4 - KEY Jeff Brenion June 16, 2004 Note: Many problems can be solved in more than one way; we present only a single solution here. 1 Problem 2-1 Since there can be anywhere from 0 to 4 aces, the

More information

4. How many integers between 2004 and 4002 are perfect squares?

4. How many integers between 2004 and 4002 are perfect squares? 5 is 0% of what number? What is the value of + 3 4 + 99 00? (alternating signs) 3 A frog is at the bottom of a well 0 feet deep It climbs up 3 feet every day, but slides back feet each night If it started

More information

3 Contour integrals and Cauchy s Theorem

3 Contour integrals and Cauchy s Theorem 3 ontour integrals and auchy s Theorem 3. Line integrals of complex functions Our goal here will be to discuss integration of complex functions = u + iv, with particular regard to analytic functions. Of

More information

ST 371 (IV): Discrete Random Variables

ST 371 (IV): Discrete Random Variables ST 371 (IV): Discrete Random Variables 1 Random Variables A random variable (rv) is a function that is defined on the sample space of the experiment and that assigns a numerical variable to each possible

More information

Lecture 6: Discrete & Continuous Probability and Random Variables

Lecture 6: Discrete & Continuous Probability and Random Variables Lecture 6: Discrete & Continuous Probability and Random Variables D. Alex Hughes Math Camp September 17, 2015 D. Alex Hughes (Math Camp) Lecture 6: Discrete & Continuous Probability and Random September

More information

Exponential Distribution

Exponential Distribution Exponential Distribution Definition: Exponential distribution with parameter λ: { λe λx x 0 f(x) = 0 x < 0 The cdf: F(x) = x Mean E(X) = 1/λ. f(x)dx = Moment generating function: φ(t) = E[e tx ] = { 1

More information

Discrete Mathematics and Probability Theory Fall 2009 Satish Rao, David Tse Note 18. A Brief Introduction to Continuous Probability

Discrete Mathematics and Probability Theory Fall 2009 Satish Rao, David Tse Note 18. A Brief Introduction to Continuous Probability CS 7 Discrete Mathematics and Probability Theory Fall 29 Satish Rao, David Tse Note 8 A Brief Introduction to Continuous Probability Up to now we have focused exclusively on discrete probability spaces

More information

36 CHAPTER 1. LIMITS AND CONTINUITY. Figure 1.17: At which points is f not continuous?

36 CHAPTER 1. LIMITS AND CONTINUITY. Figure 1.17: At which points is f not continuous? 36 CHAPTER 1. LIMITS AND CONTINUITY 1.3 Continuity Before Calculus became clearly de ned, continuity meant that one could draw the graph of a function without having to lift the pen and pencil. While this

More information

Statistics 100A Homework 8 Solutions

Statistics 100A Homework 8 Solutions Part : Chapter 7 Statistics A Homework 8 Solutions Ryan Rosario. A player throws a fair die and simultaneously flips a fair coin. If the coin lands heads, then she wins twice, and if tails, the one-half

More information

Math 370, Spring 2008 Prof. A.J. Hildebrand. Practice Test 2 Solutions

Math 370, Spring 2008 Prof. A.J. Hildebrand. Practice Test 2 Solutions Math 370, Spring 008 Prof. A.J. Hildebrand Practice Test Solutions About this test. This is a practice test made up of a random collection of 5 problems from past Course /P actuarial exams. Most of the

More information

1 Sufficient statistics

1 Sufficient statistics 1 Sufficient statistics A statistic is a function T = rx 1, X 2,, X n of the random sample X 1, X 2,, X n. Examples are X n = 1 n s 2 = = X i, 1 n 1 the sample mean X i X n 2, the sample variance T 1 =

More information

Algebra 2 Chapter 1 Vocabulary. identity - A statement that equates two equivalent expressions.

Algebra 2 Chapter 1 Vocabulary. identity - A statement that equates two equivalent expressions. Chapter 1 Vocabulary identity - A statement that equates two equivalent expressions. verbal model- A word equation that represents a real-life problem. algebraic expression - An expression with variables.

More information

The sample space for a pair of die rolls is the set. The sample space for a random number between 0 and 1 is the interval [0, 1].

The sample space for a pair of die rolls is the set. The sample space for a random number between 0 and 1 is the interval [0, 1]. Probability Theory Probability Spaces and Events Consider a random experiment with several possible outcomes. For example, we might roll a pair of dice, flip a coin three times, or choose a random real

More information

1.1 Introduction, and Review of Probability Theory... 3. 1.1.1 Random Variable, Range, Types of Random Variables... 3. 1.1.2 CDF, PDF, Quantiles...

1.1 Introduction, and Review of Probability Theory... 3. 1.1.1 Random Variable, Range, Types of Random Variables... 3. 1.1.2 CDF, PDF, Quantiles... MATH4427 Notebook 1 Spring 2016 prepared by Professor Jenny Baglivo c Copyright 2009-2016 by Jenny A. Baglivo. All Rights Reserved. Contents 1 MATH4427 Notebook 1 3 1.1 Introduction, and Review of Probability

More information

STAT 315: HOW TO CHOOSE A DISTRIBUTION FOR A RANDOM VARIABLE

STAT 315: HOW TO CHOOSE A DISTRIBUTION FOR A RANDOM VARIABLE STAT 315: HOW TO CHOOSE A DISTRIBUTION FOR A RANDOM VARIABLE TROY BUTLER 1. Random variables and distributions We are often presented with descriptions of problems involving some level of uncertainty about

More information

Binomial lattice model for stock prices

Binomial lattice model for stock prices Copyright c 2007 by Karl Sigman Binomial lattice model for stock prices Here we model the price of a stock in discrete time by a Markov chain of the recursive form S n+ S n Y n+, n 0, where the {Y i }

More information

Chapter 3: DISCRETE RANDOM VARIABLES AND PROBABILITY DISTRIBUTIONS. Part 3: Discrete Uniform Distribution Binomial Distribution

Chapter 3: DISCRETE RANDOM VARIABLES AND PROBABILITY DISTRIBUTIONS. Part 3: Discrete Uniform Distribution Binomial Distribution Chapter 3: DISCRETE RANDOM VARIABLES AND PROBABILITY DISTRIBUTIONS Part 3: Discrete Uniform Distribution Binomial Distribution Sections 3-5, 3-6 Special discrete random variable distributions we will cover

More information

The Method of Partial Fractions Math 121 Calculus II Spring 2015

The Method of Partial Fractions Math 121 Calculus II Spring 2015 Rational functions. as The Method of Partial Fractions Math 11 Calculus II Spring 015 Recall that a rational function is a quotient of two polynomials such f(x) g(x) = 3x5 + x 3 + 16x x 60. The method

More information

Practice problems for Homework 11 - Point Estimation

Practice problems for Homework 11 - Point Estimation Practice problems for Homework 11 - Point Estimation 1. (10 marks) Suppose we want to select a random sample of size 5 from the current CS 3341 students. Which of the following strategies is the best:

More information

Chapter 17. Orthogonal Matrices and Symmetries of Space

Chapter 17. Orthogonal Matrices and Symmetries of Space Chapter 17. Orthogonal Matrices and Symmetries of Space Take a random matrix, say 1 3 A = 4 5 6, 7 8 9 and compare the lengths of e 1 and Ae 1. The vector e 1 has length 1, while Ae 1 = (1, 4, 7) has length

More information

Errata and updates for ASM Exam C/Exam 4 Manual (Sixteenth Edition) sorted by page

Errata and updates for ASM Exam C/Exam 4 Manual (Sixteenth Edition) sorted by page Errata for ASM Exam C/4 Study Manual (Sixteenth Edition) Sorted by Page 1 Errata and updates for ASM Exam C/Exam 4 Manual (Sixteenth Edition) sorted by page Practice exam 1:9, 1:22, 1:29, 9:5, and 10:8

More information

1.7 Graphs of Functions

1.7 Graphs of Functions 64 Relations and Functions 1.7 Graphs of Functions In Section 1.4 we defined a function as a special type of relation; one in which each x-coordinate was matched with only one y-coordinate. We spent most

More information

Question: What is the probability that a five-card poker hand contains a flush, that is, five cards of the same suit?

Question: What is the probability that a five-card poker hand contains a flush, that is, five cards of the same suit? ECS20 Discrete Mathematics Quarter: Spring 2007 Instructor: John Steinberger Assistant: Sophie Engle (prepared by Sophie Engle) Homework 8 Hints Due Wednesday June 6 th 2007 Section 6.1 #16 What is the

More information

Mathematics Pre-Test Sample Questions A. { 11, 7} B. { 7,0,7} C. { 7, 7} D. { 11, 11}

Mathematics Pre-Test Sample Questions A. { 11, 7} B. { 7,0,7} C. { 7, 7} D. { 11, 11} Mathematics Pre-Test Sample Questions 1. Which of the following sets is closed under division? I. {½, 1,, 4} II. {-1, 1} III. {-1, 0, 1} A. I only B. II only C. III only D. I and II. Which of the following

More information

1 if 1 x 0 1 if 0 x 1

1 if 1 x 0 1 if 0 x 1 Chapter 3 Continuity In this chapter we begin by defining the fundamental notion of continuity for real valued functions of a single real variable. When trying to decide whether a given function is or

More information

CA200 Quantitative Analysis for Business Decisions. File name: CA200_Section_04A_StatisticsIntroduction

CA200 Quantitative Analysis for Business Decisions. File name: CA200_Section_04A_StatisticsIntroduction CA200 Quantitative Analysis for Business Decisions File name: CA200_Section_04A_StatisticsIntroduction Table of Contents 4. Introduction to Statistics... 1 4.1 Overview... 3 4.2 Discrete or continuous

More information

ECE302 Spring 2006 HW5 Solutions February 21, 2006 1

ECE302 Spring 2006 HW5 Solutions February 21, 2006 1 ECE3 Spring 6 HW5 Solutions February 1, 6 1 Solutions to HW5 Note: Most of these solutions were generated by R. D. Yates and D. J. Goodman, the authors of our textbook. I have added comments in italics

More information

SMT 2014 Algebra Test Solutions February 15, 2014

SMT 2014 Algebra Test Solutions February 15, 2014 1. Alice and Bob are painting a house. If Alice and Bob do not take any breaks, they will finish painting the house in 20 hours. If, however, Bob stops painting once the house is half-finished, then the

More information

Section 6.1 Joint Distribution Functions

Section 6.1 Joint Distribution Functions Section 6.1 Joint Distribution Functions We often care about more than one random variable at a time. DEFINITION: For any two random variables X and Y the joint cumulative probability distribution function

More information

The normal approximation to the binomial

The normal approximation to the binomial The normal approximation to the binomial In order for a continuous distribution (like the normal) to be used to approximate a discrete one (like the binomial), a continuity correction should be used. There

More information

Continued Fractions and the Euclidean Algorithm

Continued Fractions and the Euclidean Algorithm Continued Fractions and the Euclidean Algorithm Lecture notes prepared for MATH 326, Spring 997 Department of Mathematics and Statistics University at Albany William F Hammond Table of Contents Introduction

More information

Review of Random Variables

Review of Random Variables Chapter 1 Review of Random Variables Updated: January 16, 2015 This chapter reviews basic probability concepts that are necessary for the modeling and statistical analysis of financial data. 1.1 Random

More information

1. Prove that the empty set is a subset of every set.

1. Prove that the empty set is a subset of every set. 1. Prove that the empty set is a subset of every set. Basic Topology Written by Men-Gen Tsai email: b89902089@ntu.edu.tw Proof: For any element x of the empty set, x is also an element of every set since

More information

REPEATED TRIALS. The probability of winning those k chosen times and losing the other times is then p k q n k.

REPEATED TRIALS. The probability of winning those k chosen times and losing the other times is then p k q n k. REPEATED TRIALS Suppose you toss a fair coin one time. Let E be the event that the coin lands heads. We know from basic counting that p(e) = 1 since n(e) = 1 and 2 n(s) = 2. Now suppose we play a game

More information

Exploratory Data Analysis

Exploratory Data Analysis Exploratory Data Analysis Johannes Schauer johannes.schauer@tugraz.at Institute of Statistics Graz University of Technology Steyrergasse 17/IV, 8010 Graz www.statistics.tugraz.at February 12, 2008 Introduction

More information

www.mathsbox.org.uk ab = c a If the coefficients a,b and c are real then either α and β are real or α and β are complex conjugates

www.mathsbox.org.uk ab = c a If the coefficients a,b and c are real then either α and β are real or α and β are complex conjugates Further Pure Summary Notes. Roots of Quadratic Equations For a quadratic equation ax + bx + c = 0 with roots α and β Sum of the roots Product of roots a + b = b a ab = c a If the coefficients a,b and c

More information

Feb 28 Homework Solutions Math 151, Winter 2012. Chapter 6 Problems (pages 287-291)

Feb 28 Homework Solutions Math 151, Winter 2012. Chapter 6 Problems (pages 287-291) Feb 8 Homework Solutions Math 5, Winter Chapter 6 Problems (pages 87-9) Problem 6 bin of 5 transistors is known to contain that are defective. The transistors are to be tested, one at a time, until the

More information

You flip a fair coin four times, what is the probability that you obtain three heads.

You flip a fair coin four times, what is the probability that you obtain three heads. Handout 4: Binomial Distribution Reading Assignment: Chapter 5 In the previous handout, we looked at continuous random variables and calculating probabilities and percentiles for those type of variables.

More information

Metric Spaces. Chapter 7. 7.1. Metrics

Metric Spaces. Chapter 7. 7.1. Metrics Chapter 7 Metric Spaces A metric space is a set X that has a notion of the distance d(x, y) between every pair of points x, y X. The purpose of this chapter is to introduce metric spaces and give some

More information

STT315 Chapter 4 Random Variables & Probability Distributions KM. Chapter 4.5, 6, 8 Probability Distributions for Continuous Random Variables

STT315 Chapter 4 Random Variables & Probability Distributions KM. Chapter 4.5, 6, 8 Probability Distributions for Continuous Random Variables Chapter 4.5, 6, 8 Probability Distributions for Continuous Random Variables Discrete vs. continuous random variables Examples of continuous distributions o Uniform o Exponential o Normal Recall: A random

More information

THE CENTRAL LIMIT THEOREM TORONTO

THE CENTRAL LIMIT THEOREM TORONTO THE CENTRAL LIMIT THEOREM DANIEL RÜDT UNIVERSITY OF TORONTO MARCH, 2010 Contents 1 Introduction 1 2 Mathematical Background 3 3 The Central Limit Theorem 4 4 Examples 4 4.1 Roulette......................................

More information

Math 370/408, Spring 2008 Prof. A.J. Hildebrand. Actuarial Exam Practice Problem Set 2 Solutions

Math 370/408, Spring 2008 Prof. A.J. Hildebrand. Actuarial Exam Practice Problem Set 2 Solutions Math 70/408, Spring 2008 Prof. A.J. Hildebrand Actuarial Exam Practice Problem Set 2 Solutions About this problem set: These are problems from Course /P actuarial exams that I have collected over the years,

More information

Partial Fractions Examples

Partial Fractions Examples Partial Fractions Examples Partial fractions is the name given to a technique of integration that may be used to integrate any ratio of polynomials. A ratio of polynomials is called a rational function.

More information

2WB05 Simulation Lecture 8: Generating random variables

2WB05 Simulation Lecture 8: Generating random variables 2WB05 Simulation Lecture 8: Generating random variables Marko Boon http://www.win.tue.nl/courses/2wb05 January 7, 2013 Outline 2/36 1. How do we generate random variables? 2. Fitting distributions Generating

More information

MA107 Precalculus Algebra Exam 2 Review Solutions

MA107 Precalculus Algebra Exam 2 Review Solutions MA107 Precalculus Algebra Exam 2 Review Solutions February 24, 2008 1. The following demand equation models the number of units sold, x, of a product as a function of price, p. x = 4p + 200 a. Please write

More information

Probability Generating Functions

Probability Generating Functions page 39 Chapter 3 Probability Generating Functions 3 Preamble: Generating Functions Generating functions are widely used in mathematics, and play an important role in probability theory Consider a sequence

More information

5.3 Improper Integrals Involving Rational and Exponential Functions

5.3 Improper Integrals Involving Rational and Exponential Functions Section 5.3 Improper Integrals Involving Rational and Exponential Functions 99.. 3. 4. dθ +a cos θ =, < a

More information

What is Statistics? Lecture 1. Introduction and probability review. Idea of parametric inference

What is Statistics? Lecture 1. Introduction and probability review. Idea of parametric inference 0. 1. Introduction and probability review 1.1. What is Statistics? What is Statistics? Lecture 1. Introduction and probability review There are many definitions: I will use A set of principle and procedures

More information

Practice Problems #4

Practice Problems #4 Practice Problems #4 PRACTICE PROBLEMS FOR HOMEWORK 4 (1) Read section 2.5 of the text. (2) Solve the practice problems below. (3) Open Homework Assignment #4, solve the problems, and submit multiple-choice

More information

Algebra I Vocabulary Cards

Algebra I Vocabulary Cards Algebra I Vocabulary Cards Table of Contents Expressions and Operations Natural Numbers Whole Numbers Integers Rational Numbers Irrational Numbers Real Numbers Absolute Value Order of Operations Expression

More information

2.1 Increasing, Decreasing, and Piecewise Functions; Applications

2.1 Increasing, Decreasing, and Piecewise Functions; Applications 2.1 Increasing, Decreasing, and Piecewise Functions; Applications Graph functions, looking for intervals on which the function is increasing, decreasing, or constant, and estimate relative maxima and minima.

More information

Differentiation and Integration

Differentiation and Integration This material is a supplement to Appendix G of Stewart. You should read the appendix, except the last section on complex exponentials, before this material. Differentiation and Integration Suppose we have

More information

Real Roots of Univariate Polynomials with Real Coefficients

Real Roots of Univariate Polynomials with Real Coefficients Real Roots of Univariate Polynomials with Real Coefficients mostly written by Christina Hewitt March 22, 2012 1 Introduction Polynomial equations are used throughout mathematics. When solving polynomials

More information

Section 4.4. Using the Fundamental Theorem. Difference Equations to Differential Equations

Section 4.4. Using the Fundamental Theorem. Difference Equations to Differential Equations Difference Equations to Differential Equations Section 4.4 Using the Fundamental Theorem As we saw in Section 4.3, using the Fundamental Theorem of Integral Calculus reduces the problem of evaluating a

More information

Undergraduate Notes in Mathematics. Arkansas Tech University Department of Mathematics

Undergraduate Notes in Mathematics. Arkansas Tech University Department of Mathematics Undergraduate Notes in Mathematics Arkansas Tech University Department of Mathematics An Introductory Single Variable Real Analysis: A Learning Approach through Problem Solving Marcel B. Finan c All Rights

More information