Probability and Statistics Modelling Systems of Random Variables – Computer System – Traffic Systems – Financial System – Data System Linear – Weighted sums Non-Linear – Max/min; If-then; products ST Week 101 Forced by randomness, unpredictability
Systems Teams in league – Games won by N A N B N C – Sums of binary Student attendance at class – BinaryName Chosen/ Not Chosen – Given chosenPresence/Absence Sets of Dice – Scores X 1 X 2 X 3 Sums, Max S 3 M 3 ST Week 102 Model Decompose Splash Bean Machine
Approach 1.Consider simulation thought experiments – Columns and Random Variables – Define/articulate problem Possible Values Transforms, functions Event Identities 2.Define random vars – Algebra for random vars 3.Consider probabilities ST Week 103
Sums and Averages: Linear Systems Simple systems – Dice sums, Travel times, Pill Boxes Convergence in simulations – Form running sum; divide by n Estimation by sample survey – Sum; divide by n – Count; divide by n Finance – Accumulation of % changes – Sum, in log scale ST Week 104 Comparisons
Max and Min Combinations A system has 3 components A, B and C, with redundancy. It is designed such that it will work if either (C is working) or (both A and B are working). If the lifetimes of A, B and C are 10, 15 and 8 hours, resp, then it will work for 10 hours. ST Week 105
Systems of Random Variables Input Output – Simulation Joint Uncertainty (Input) Uncertainty(Output) – Prob Dist – Expected Values and Variances ST Week 106 Independent Dependent Linear Non-linear
Linear Combs & Normal Distribution Linear Combinations – weighted sums – counts Simple for Normal Normal a useful approx – Central Limit Theorem – SE(mean&prop) n Convergence 7ST Week 10 Dice sum Dice max
Dice: Sums ST Week 108
Prob Rules Prob Dist ExpVal etc 9ST Week 10
10ST Week 10 Prob Rules Prob Dist ExpVal etc
cdf for Max Min indep rvs 11ST Week 10
Max and Min Combinations A system has 3 components A, B and C, with redundancy. It is designed such that it will work if either (C is working) or (both A and B are working). If the lifetimes of A, B and C are 10, 15 and 8 hours, resp, then it will work for 10 hours. ST Week 1012
System Lifetime ST Week 1013 See SystemLife.xlsx
Max/min indep random vars cdf(system) via prods based on cdf(comps) – pmf by subtraction, if discrete – pdf by calculus, if continuous Expected Value & Var sumproduct, if discrete calculus, if continuous ST Week 1014
Sum/Diff/Lin Comb indep random vars Expected Value & Var simple rules, based on – E[aX+bY]=aE[X] + bE[Y] – Var[aX+bY]=a 2 Var[X] + b 2 E[Y] cdf(system) pmf(system) – by tabulation, enumeration if discrete some special cases – intricate calculus, if continuous some special cases – but often, Normal approx ST Week 1015
Theory: Distributions and Lin Combs ST Week 1016
17 Theory: Linear Combinations X,Y random variables a,b constants Z = aX+bY Seek E[Z] and Var[Z] Using Normal (approx) for dist Z? E[Z] and Var[Z] fully specify D iscrete dists only in these notes; extension to continuous dists only a matter of notation; joint pdf instead of joint pmf; integrals instead of sums. ST Week 10
18 Approach via dist Z =Y+X ST Week 10 E[Y]E[X] Var[Y]Var[X] E[Z] Var[Z] In Fill in given Indep
19 Approach via dist Z =Y+X ST Week 10 E[Y] = 2E[X]=4 Var[Y]=2/3Var[X]=4/3 E[Z]= 6Var[Z]=6/3 Cov(X,Y)=0
20 Direct approach: when X,Y indep ST Week 10
21 Approach via dist Z =X+Y ST Week 10 E[Y]E[X] Var[Y]Var[X] Cov[X,Y] E[Z]Var[Z]
22 Approach via dist(Y+X) ST Week 10
23 Direct approach: when X,Y not indep ST Week 10
24ST Week 10 Theory: Expected values for linear combs
25 App: Travel Times ST Week 10
Travel Time by Simulation ST Week 1026 T_ABT_BCT_AC
27 App: Travel Times ST Week 10
28 Travel Times mean var Probs ST Week 10
29 Times Different? Pr = ST Week 10
30 Correlated Travel Times Prob = ST Week 10
31 Correlation Prob = ST Week 10
Proof: discrete case 32ST Week 10
Proof: discrete case 33ST Week 10
34 Packing a pillbox ST Week 10
Approach by Simulation ST Week 1035
Extension 36ST Week 10
37 Pr = 0.32 ST Week 10 Packing a pillbox
38 Common Error ST Week 10
Important Special Cases 39ST Week 10
Sampling Dists of Avg (S4) ST Week 1040 Convergence at 1/ n Central Limit Theorem Section 5.3,4
Simulation Convergence ST Week 1041 Confidence Intervals for Simulations Sec5.7
Law of Large Numbers rate of convergence ST Week 1042
Theory: Normal Approximation via Central Limit Theorem ST Week 1043
44 Application: sums and averages ST Week 10
45 Application: precision ST Week 10
46 Application: sample size for mean ST Week 10
47 Application: sample size for prop ST Week 10
Homework Tijms Q5.2 Someone has written a simulation programme to estimate a probability. 500 runs estimate of If the prob p 0.451, what are SE(est prob)? 95% Conf Int? 1000 runs estimate of 0.453, what are SE, 95% CI? Is there reason to suspect problem? ST Week 1048
Homework Tijms Q5.2 Someone has written a simulation programme to estimate a probability. 500 runs estimate of If the prob = p 0.451, what are EstSE(est prob)? 95% Conf Int? 1000 runs estimate of 0.453, what are EstSE, 95% CI? Is there reason to suspect problem? No: the difference is very small compared to the uncertainties involved ST Week 1049