rpra5 - Engineering Risk Benefit Analysis 1.155, 2.943,...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
RPRA 5. Data Analysis 1 Engineering Risk Benefit Analysis 1.155, 2.943, 3.577, 6.938, 10.816, 13.621, 16.862, 22.82, ESD.72, ESD.721 RPRA 5. Data Analysis George E. Apostolakis Massachusetts Institute of Technology Spring 2007
Background image of page 1

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

View Full DocumentRight Arrow Icon
RPRA 5. Data Analysis 2 Statistical Inference Theoretical Model Evidence Failure distribution, Sample, e.g., e.g., {t 1 ,…,t n } How do we estimate from the evidence? How confident are we in this estimate? Two methods: Classical (frequentist) statistics Bayesian statistics t e ) t ( f λ λ = λ
Background image of page 2
RPRA 5. Data Analysis 3 Random Samples The observed values are independent and the underlying distribution is constant. Sample mean: Sample variance: = n 1 i t n 1 t = n 1 2 i 2 ) t t ( ) 1 n ( 1 s
Background image of page 3

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

View Full DocumentRight Arrow Icon
RPRA 5. Data Analysis 4 The Method of Moments: Exponential Distribution Set the theoretical moments equal to the sample moments and determine the values of the parameters of the theoretical distribution. Exponential distribution: Sample: {10.2, 54.0, 23.3, 41.2, 73.2, 28.0} hrs t 1 = λ 32 . 38 6 9 . 229 ) 28 2 . 73 2 . 41 3 . 23 54 2 . 10 ( 6 1 t = = + + + + + = 1 hr 026 . 0 32 . 38 1 = = λ ; hrs 32 . 38 MTTF =
Background image of page 4
RPRA 5. Data Analysis 5 The Method of Moments: Normal Distribution Sample: {5.5, 4.7, 6.7, 5.6, 5.7} μ = = = + + + + = 68 . 5 5 4 . 28 5 ) 7 . 5 6 . 5 7 . 6 7 . 4 7 . 5 ( x 032 . 2 ) 68 . 5 7 . 5 ( ... ) 68 . 5 5 . 5 ( ) x x ( 5 1 2 2 2 i = + + = σ = = = = 713 . 0 s 508 . 0 ) 1 5 ( 032 . 2 s 2
Background image of page 5

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

View Full DocumentRight Arrow Icon
RPRA 5. Data Analysis 6 The Method of Moments: Poisson Distribution Sample: {r events in t} Average number of events: r {3 eqs in 7 years} t r r t = λ = λ 1 yr 43 . 0 7 3 = = λ
Background image of page 6
RPRA 5. Data Analysis 7 The Method of Moments: Binomial Distribution Sample: {k 1s in n trials} Average number of 1s: k qn = k {3 failures to start in 17 tests} n k q = 176 . 0 17 3 q = =
Background image of page 7

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

View Full DocumentRight Arrow Icon
8 Censored Samples and the Exponential Distribution Complete sample: All n components fail. Censored sample: Sampling is terminated at time t 0 (with k failures observed) or when the r th failure occurs. Define the total operational time as: It can be shown that: Valid for the exponential distribution only (no memory). + = k
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/08/2011 for the course AERO 16.851 taught by Professor Ldavidmiller during the Fall '03 term at MIT.

Page1 / 26

rpra5 - Engineering Risk Benefit Analysis 1.155, 2.943,...

This preview shows document pages 1 - 9. Sign up to view the full document.

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