note 5 - MA2216/ST2131 Probability Notes 5 Distribution of...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: MA2216/ST2131 Probability Notes 5 Distribution of a Function of a Random Variable We have seen that an “affine transformation” of a normal r.v. is still normally distributed. To be precise, let X ∼ N ( μ,σ 2 ). Put Y = aX + b . Then, it has been pointed out in § 8.8 of Notes 4 that, for a 6 = 0 , Y ∼ N ( aμ + b, a 2 σ 2 ) . Derivation. Recall that f X ( x ) = 1 √ 2 πσ 2 e- ( x- μ ) 2 2 σ 2 . To determine the distribution of Y , find F Y , the d.f. of Y , first. Consider the case a > 0 first. F Y ( y ) = IP( Y ≤ y ) = IP( aX + b ≤ y ) = IP( X ≤ y- b a ) = F X y- b a ¶ . To identify the distribution of Y , we need to find its p.d.f., f Y , which is the derivative of F Y : for y ∈ IR, f Y ( y ) = d dy F Y ( y ) = d dy F X y- b a ¶ = f X y- b a ¶ · 1 a = 1 a · 1 √ 2 πσ 2 e- ( y- b a- μ ) 2 2 σ 2 = 1 p 2 π ( aσ ) 2 e- ( y- aμ- b ) 2 2( aσ ) 2 . We recognize that it is the p.d.f. of N ( aμ + b, a 2 σ 2 ). 1 If a < 0, then F Y ( y ) = IP X ≥ y- b a ¶ = 1- F X y- b a ¶ . Hence, f Y ( y ) =- 1 a · 1 √ 2 πσ 2 e- ( y- b a- μ ) 2 2 σ 2 = 1 p 2 π ( aσ ) 2 e- ( y- aμ- b ) 2 2( aσ ) 2 , which is obviously the p.d.f. of the normal distribution N ( aμ + b, a 2 σ 2 ), and therefore, we are done. In particular, if we set Z = X- μ σ , then Z is a standard normal r.v., i.e., Z ∼ N (0 , 1). This is perhaps the most frequently used transformation. In the following, we will see a few additional examples on the derivation of the distribution of a transformed r.v. 2 1. Example. Let Z ∼ N (0 , 1). What are the d.f. and p.d.f. of Y , where Y = Z 2 ? Note that, Y is known in the literature as chi-square ( χ 2 ) r.v. of degree 1. Sol. First note that Y takes nonnegative values. Obviously, Y is con- tinuous, and hence we determine its c.d.f. first. For y > 0, we have F Y ( y ) = IP( Y ≤ y ) = IP( Z 2 ≤ y ) = IP(- √ y ≤ Z ≤ √ y ) = 1 √ 2 π Z √ y- √ y e- z 2 / 2 dz, = 2 √ 2 π Z √ y e- z 2 / 2 dz, hence f Y ( y ) = dF Y ( y ) dy = 2 √ 2 π 1 2 √ y e- y/ 2 = y- 1 / 2 e- y/ 2 √ 2 π = ( 1 2 ) 1 2 Γ( 1 2 ) y 1 2- 1 e- 1 2 y . We conclude that F Y ( y ) =    , for y ≤ 0, 2 √ 2 π R √ y e- u 2 / 2 du, for y > 0. and f Y ( y ) =      , for y ≤ 0, ( 1 2 ) 1 2 Γ( 1 2 ) y 1 2- 1 e- 1 2 y , for y > 0. Remark. Do you recognize the distribution of the above Y ? In fact, the distribution of Z 2 with Z ∼ N (0 , 1) is Γ( 1 2 , 1 2 ). Thus, χ 2 1 = Γ 1 2 , 1 2 ¶ . This is a very useful result, which will be quoted often throughout. 3 Addendum. * Refer to § 1.3 of Notes 7, in which the following property will be established: If X i , i = 1 , 2 ,...,n are independent gamma r.v.’s with respective pa- rameters ( α i ,λ ) , i = 1 , 2 ,...,n , then n X i =1 X i ∼ Γ ˆ n X i =1 α i , λ !...
View Full Document

This note was uploaded on 03/19/2012 for the course SCIENCE ST2131 taught by Professor Forgot during the Fall '08 term at National University of Singapore.

Page1 / 12

note 5 - MA2216/ST2131 Probability Notes 5 Distribution of...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online