Sum of Independent Binomial RVs Sum of Independent Poisson RVs • Let X and Y be independent random variables • Let X and Y be independent random variables X ~ Poi( l 1 ) and Y ~ Poi( l 2 ) X ~ Bin(n 1 , p) and Y ~ Bin(n 2 , p) X + Y ~ Bin(n 1 + n 2 , p) X + Y ~ Poi( l 1 + l 2 ) • Intuition: • Proof: (just for reference) X has n 1 trials and Y has n 2 trials Rewrite (X + Y = n ) as (X = k , Y = n – k ) where 0 k n o Each trial has same “success” probability p n n P ( X Y n ) P ( X k , Y n k ) P ( X k ) P ( Y n k ) Define Z to be n 1 + n 2 trials, each with success prob. p k 0 k 0 Z ~ Bin(n 1 + n 2 , p), and also Z = X + Y l l l l l l k n k k n k ( ) n n e n n ! 1 2 l l l l l l 1 2 ( ) 1 2 k n k e 1 e 2 e 1 2 • More generally: X i ~ Bin(n i , p) for 1 i N 1 2 k ! ( n k )! k ! ( n k )! n ! k ! ( n k )! k 0 k 0 k 0 n N n n ! l l l l ~ Bin , Noting Binomial coefficient: ( ) n k n k X n p i i 1 2 1 2 k ! ( n k )! i 1 i 1 l l k 0 ( ) e 1 2 l l n so, X + Y = n ~ Poi( l 1 + l 2 ) P ( X Y n ) 1 2 ! n Dance, Dance, Convolution Sum of Independent Uniform RVs • Let X and Y be independent random variables • Let X and Y be independent random variables X ~ Uni(0, 1) and Y ~ Uni(0, 1) f ( a ) = 1 for 0 a 1 Cumulative Distribution Function (CDF) of X + Y: F ( a ) P ( X Y a ) What is PDF of X + Y? X Y a y 1 1 f ( x ) f ( y ) dx dy f ( x ) dx f ( y ) dy ( ) ( ) ( ) ( ) X Y X Y f a f a y f y dy f a y dy X Y X Y X x y a y x y 0 y 0 When 0 a 1 and 0 y a , 0 a – y 1 f X ( a – y ) = 1 ( ) ( ) F a y f y dy a X Y ( ) f a dy a y X Y y 0 F X+Y is called convolution of F X and F Y When 1 < a < 2 and a – 1 y 1, 0 a – y 1 f X ( a – y ) = 1 Probability Density Function (PDF) of X + Y, analogous: 1 ( a ) f f ( a ) dy 2 a X Y X Y f ( a ) f ( a y ) f ( y ) dy y a 1 1 X Y X Y a 0 a 1 y Combining: f ( a ) 2 a 1 a 2 In discrete case, replace with , and f ( y ) with p ( y ) X Y a 0 otherwise 1 2 y y Sum of Independent Normal RVs Virus Infections • Let X and Y be independent random variables • Say your RCC checks dorm machines for viruses X ~ N( m 1 , s 1 2 ) and Y ~ N( m 2 , s 2 2 ) 50 Macs, each independently infected with p = 0.1 100 PCs, each independently infected with p = 0.4 X + Y ~ N( m 1 + m 2 , s 1 2 + s 2 2 ) A ~ Bin(50, 0.1) X ~ N(5, 4.5) A = # infected Macs B ~ Bin(100, 0.4) Y ~ N(40, 24) B = # infected PCs • Generally, have n independent random variables What is P(≥ 40 machine infected)? X i ~ N( m i , s i 2 ) for i = 1, 2, ..., n : P(A + B ≥ 40) P(X + Y ≥ 39.5) n n n X + Y = W ~ N(5 + 40 = 45, 4.5 + 24 = 28.5) m s 2 ~ , X N i i i W 45 39 . 5 45 i 1 i 1 i 1 P ( W 39 . 5 ) P 1 ( 1 . 03 ) 0 . 8485 28 . 5 28 . 5 • Be glad it’s not swine flu! 1
Discrete Conditional Distributions Operating System Loyalty • Recall that for events E and F: • Consider person buying 2 computers (over time) ( ) P EF X = 1st computer bought is a PC (1 if it is, 0 if it is not) P ( E | F ) where P ( F ) 0 P ( F ) Y = 2nd computer bought is a PC (1 if it is, 0 if it is not) • Now, have X and Y as discrete random variables Joint probability mass function (PMF): What is P(Y = 0 | X = 0)? Conditional PMF of X given Y (where p Y ( y ) > 0): X 0 1 p Y (y) Y p ( x , y ) P ( X x , Y y ) ( 0 , 0 ) p 0 . 2 2 , ( | ) ( | ) X Y X , Y P x y P X x Y y P ( Y 0 | X 0 ) X | Y 0 0.2 0.3 0.5 ( ) ( ) p ( 0 ) 0 . 3 3 P Y y p y X Y What is P(Y = 1 | X = 0)? Conditional CDF of X given Y (where p Y ( y ) > 0): 1 0.1 0.4 0.5 p ( 0 , 1 ) 0 . 1 1 X , Y P ( X a , Y y ) P ( Y 1 | X 0 ) p X (x) 0.3 0.7 1.0 ( 0 ) 0 . 3 3 F ( a | y ) P ( X a | Y y ) p X X | Y P ( Y y ) What is P(X = 0 | Y = 1)? p ( x , y ) X , Y ( 0 , 1 ) x a p 0 . 1 1 p ( x | y ) X , Y P ( X 0 | Y 1 ) X | Y p ( y ) p ( 1 ) 0 . 5 5 Y x a Y And It Applies to Books Too… Web Server Requests Redux • Requests received at web server in a day X ~ Poi( l 1 ) X = # requests from humans/day Y ~ Poi( l 2 ) Y = # requests from bots/day X and Y are independent X + Y ~ Poi( l 1 + l 2 ) What is P(X = k | X + Y = n )? P ( X k , Y n k ) P ( X k ) P ( Y n k ) P ( X k | X Y n ) P ( X Y n ) P ( X Y n ) l l l l l l k n k ! ! k n k e 1 e 2 n n 1 2 1 2 l l l l l l ( ) n n k ! ( n k )! e ( ) k ! ( n k )! ( ) 1 2 1 2 1 2 k n k l l n 1 2 l l l l k 1 2 1 2 l 1 X | X + Y ~ Bin X Y , l l P(Buy Book Y | Bought Book X) 1 2 Let’s Do an Example Continuous Conditional Distributions • Let X and Y be continuous random variables • X and Y are continuous RVs with PDF: 12 x ( 2 x y ) wh ere 0 x,y 1 Conditional PDF of X given Y (where f Y ( y ) > 0): 5 f ( x , y ) 0 otherwise f ( x , y ) , ( | ) X Y f x y X | Y ( ) f y Y Compute conditional density: f ( x | y ) X | Y f ( x , y ) dx dy X , Y f ( x | y ) dx ( , ) ( , ) f x y f x y X | Y f ( y ) dy X , Y X , Y f ( x | y ) Y | X Y 1 f ( y ) P ( x X x dx , y Y y dy ) Y f ( x , y ) dx P ( x X x dx | y Y y dy ) , X Y P ( y Y y dy ) 0 12 Conditional CDF of X given Y (where f Y ( y ) > 0): x ( 2 x y ) x ( 2 x y ) x ( 2 x y ) 5 a 1 1 ( | ) ( | ) ( | ) 1 F a y P X a Y y f x y dx 12 3 2 x x y x ( 2 x y ) dx x ( 2 x y ) dx 2 | | x X Y X Y 5 3 2 0 0 0 Note: Even though P(Y = a ) = 0, can condition on Y = a x ( 2 x y ) 6 x ( 2 x y ) a / 2 2 y o Really considering: P ( a Y a ) f ( y ) dy f ( a ) 4 3 y 2 2 Y 3 2 a / 2 2
Recommend
More recommend