Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Block 5 Stochastic & Dynamic Systems There is no longer a need now to be discrete! Lesson 17 – Stochastic Models Continuous Random Variables and their Probability Distributions Charles Ebeling University of Dayton 1 Continuous Random Variables Examples T = a continuous random variable, time to failure X = a continuous random variable, the distance in miles between cable defects Z = a continuous random variable, the monthly consumption of power in watts T = a continuous random variable, the repair time of a failed machine Y = a continuous random variable, the time between arrivals of customers at City National Bank X = a continuous random variable, the procurement lead-time for a critical part 2 The Probability Density Function (PDF) Let X = a continuous random variable f ( x) is a probability density function if : is never negative 1. f ( x) 0 2. f ( x) dx 1 area under the curve = 1 The graph of f(x) provides the shape of the probability distribution 3 A real, honest-to-goodness PDF f ( x) .1e.1x ; x 0 1. f ( x) 0 .1 x .1e .1x 2. .1e dx .1 0 0 .1 .1e0 lim 0 1 1 .1 x x .1e .1 0.12 0.1 0.08 0.06 0.04 0.02 area = 1 0 -5 5 15 25 35 45 55 4 Yet another one… 0.2 0.02t 0 t 10 f (t ) 0 elsewhere 1. f (t ) 0 10 2. 0.2 0.02t dt .2t .01t 2 2 1 1 0 10 0 0.25 1 area 10 f (0) 5 .2 1 2 0.2 0.15 0.1 0.05 0 -1 1 3 5 7 9 11 5 Finding Probabilities b P(a X b) f ( x) dx a given : f ( x) .1e.1x ; x 0 15 P(5 X 15) .1e .1 x dx e .1 x 15 5 e1.5 e.5 .3834 5 0.12 0.1 0.08 0.06 0.04 0.02 0 -5 5 15 25 35 45 55 6 Finding More Probabilities b P(a X b) f ( x) dx a f (t ) 0.2 0.02t 3 P(1 X 3) 0.2 0.02t dt .2t .01t 2 3 .51 .19 .32 1 1 0.25 0.2 0.15 0.1 0.05 0 -1 1 3 5 7 9 11 7 The Cumulative Distribution Function (CDF) x Define: F ( x) P( X x) f (t )dt t is the variable of integration Then: P(a X b) F (b) F (a) and: P( X x) 1 F ( x) f(x) F(b) complementary cumulative F(a) a b x 8 Our real, honest-to-goodness PDF revisited f ( x) .1e.1x ; x 0 x .1t x .1e F ( x) .1e dt .1 0 .1t e 0.1 x 1 1 e 0.1 x 0 P(5 X 15) F (15) F (5) 1 e 1.5 1 e .5 .3834 P( X 10) 1 F (10) e1 .367879 9 Let’s do it one more time… 0.2 0.02t 0 t 10 f (t ) 0 elsewhere t F (t ) 0.2 0.02 y dy .2 y .01y 2 t .2t .01t 2 0 0 2 2 P(1 X 3) F (3) F (1) .2 3 .01 3 .2 1 .011 .51 .19 .32 2 P( X 4) 1 F (4) 1 .2 4 .01 4 1 .64 .36 10 The Expected Value E[ X ] xf ( x)dx f ( x) .1e .1x ; x 0 E X .1te 0 .1t dt .1 te 0 .1t dt .1 .1 2 10 From our little table of improper definite integrals: xe 0 ax 1 dx 2 a 11 Even More Expectation 0.2 0.02t 0 t 10 f (t ) 0 elsewhere 10 10 0 0 E[T ] t 0.2 0.02t dt 0.2t 0.02t 2 dt 10 .2t .02t 20 30 20 10 1 .1100 3 3 0 3 3 3 3 3 2 2 3 E[ X ] xf ( x)dx 12 A Bonus Moment The Median Defined The median of a probability distribution is that value of the random variable X such that P(X< xmed) = F(xmed) = .5 0.12 0.1 0.08 area = .5 0.06 0.04 0.02 0 -5 5 15 xmed 25 35 45 55 13 Let’s find a median… f ( x) .1e .1 x F ( x) 1 e e 0.1 x xmed ; x0 0.1 x .5 1 .5 .5 1 ln .5 6.9315 .1 recall E[X] = 10 14 Another median… 0.2 0.02t 0 t 10 f (t ) 0 elsewhere 1 and E[T ] 3 3 F (t ) .2t .01t 2 .5 .01t 2 .2t .5 0 t 2 20t 50 0 b b 2 4ac 20 400 4 50 t 2.9289, 17.071 2a 2 tmed 2.9289 15 The Mode The mode of a probability distribution is its most likely value. Specifically, xmode is the mode of the distribution if f ( xmod e ) max f ( x) 0.12 0.25 0.1 xmode = 0 0.08 0.2 xmode = 0 0.15 0.06 0.1 0.04 0.05 0.02 0 0 -5 5 15 25 35 45 55 -1 1 3 5 7 9 11 16 Much More Mode Methods Professor I. M. Brite has determined that the driving time in minutes to the University from her home has the following probability density function: I shall be f ( x) .025ln( x) .0011881x , 10 x 30 .025 f '( x) .0011881 0 x .025 xmode 21.042 .0011881 .025 f ''( x) 2 0 x arriving in 21.042 minutes. 17 Let’s explore this very interesting density function f ( x) .025ln( x) .0011881x , 10 x 30 2 x x t F ( x) .025ln(t ) .0011881t dt .025 t ln t t .0011881 2 10 10 x2 .025 x ln x x .0011881 0.266239773 2 30 E[ X ] .025 x ln( x) .0011881x dx 2 10 x x .025 ln x 4 2 2 2 .0011881x 3 3 30 21.94557 1.8572 20.09 10 18 What’s this strange PDF look like? That is a strange one all right. median = 20.12 minutes 0.052 f(x) 0.051 0.05 0.049 0.048 0.047 0.046 0.045 0 5 10 15 20 25 30 x 35 19 This has been Adventures with Continuous Random Variables Presented by the Department of Engineering Management & Systems 20