5/27/2021

2.2 Useful statistical models 3. Reliability and maintainability

 In this section, statistical models appropriate to some application  Time to failure (TTF)
areas are presented. ― Exponential: failures are random
 The areas include: ― Gamma: for standby redundancy where each component has an
1) Queueing systems exponential TTF
― Weibull: failure is due to the most serious of a large number of defects in a
2) Inventory and supply-chain systems system of components
3) Reliability and maintainability ― Normal: failures are due to wear
4) Limited data

16 19

1. Queueing Systems 4. Other areas

 In a queueing system, inter-arrival and service-time patterns can be
probabilistic.  For cases with limited data, some useful distributions are uniform,
triangular and beta
 Sample statistical models for inter-arrival or service time distribution:
― Exponential distribution: if inter-arrival and service times are completely  Other distribution: Bernoulli, binomial and hyper-exponential.
random
― Normal distribution: fairly constant but with some random variability (either
positive or negative)
― Truncated normal distribution: similar to normal distribution but with
restricted value.
― Gamma and Weibull distribution: more general than exponential (involving
location of the modes of pdf’s and the shapes of tails.)

17 20

2. Inventory and supply chain 2.3 Discrete distributions

 In realistic inventory and supply-chain systems, there are at least three random
variables:  Discrete random variables are used to describe random phenomena
― The number of units demand per time period in which only integer values can occur, e.g. number of arrivals,
― The time between demands (orders) or order cycle time
number of units demanded, etc. in a certain period of time
― The lead time (time between the placing of an order for stocking the
inventory system and the receipt of that order)  Four distribution will be elaborated in this section.
 Sample statistical models for lead time distribution: 1) Bernoulli trials and Bernoulli distribution
• Gamma 2) Binomial distribution
 Sample statistical models for demand distribution:
3) Geometric and negative binomial distribution
―Poisson: simple and extensively tabulated.
―Negative binomial distribution: longer tail than Poisson (more large 4) Poisson distribution
demands).
―Geometric: special case of negative binomial given at least one demand has
occurred.
18 21