MIE 360: Systems Modeling and Simulation (Fall 2023)
Tutorial 3: Random Variate Generation and Input Modelling
1. Let the random variable X be Beta(1, 3) so that the p.d.f. of X is given by
3(1 − x)2 for x ∈ [0, 1]
f (x) =
0 otherwise.
(a) Propose an inversion algorithm to generate samples of X.
(b) Generate 1000 samples of X. Plot a histogram of the samples you generated and
compare it to the p.d.f.
2. It is hypothesized that the data on the accompanying spreadsheet are i.i.d. observations
from a continuous distribution with the p.d.f. f (·) given below:
k + 1 k
x if 0 ≤ x ≤ 2
f (x) = 2k+1
0 otherwise
where k ≥ 0.
(a) For the given data, compute the method of moments (MoM) estimators of k. (Hint:
You might want to consider the general case with N data points). Update: Since we
did not get to cover method of moments on Friday, assume k̂ = 0.491 and proceed to
part (b).
(b) Let the MoM estimator you computed in Part (a) be k̂. Check the fit between the given
data and the p.d.f. f (·) (with k = k̂) by using a Q-Q plot. Does the fit look good?
Additional Practice Question
3. The c.d.f. of the Weibull distribution is given by
β
F (x) = 1 − e−αx , 0 < x < ∞,
where α and β are parameters. Propose an inversion algorithm to generate samples of the
Weibull distribution.