The negative exponential (or just exponential)
distribution has only one parameter, the mean.
• It is derived from the characteristics of purely
random arrival processes.
• As a result, it is used to sample time between events,
such as the inter-arrival time of customers and the time between failure of machines.
• Note that there is a close relationship between the
negative exponential distribution and the Poisson
distribution, which can be used to sample the
number of events in an interval of time.
The Erlang distribution is used to represent the time
to complete a task.
• For values of k greater than one it overcomes the
limitation of the negative exponential distribution by
giving a very low probability of near zero times.
• It is also used for modelling inter-arrival times,
particularly if the arrivals cannot occur in very close
succession, such as the arrival of ships into a
harbour.
• It should be noted that the Erlang distribution is a
special case of the gamma distribution.
• Typically values of k between 2 and 5 are used
Discrete distributions
• The binomial distribution describes the number of
successes, or failures, in a specified number of trials.
• It can be used, for instance, to model the number of
defects in a batch of items.
• The distribution has two parameters, the number of
trials and the probability of success.
Discrete distributions
• The binomial distribution describes the number of
successes, or failures, in a specified number of trials.
• It can be used, for instance, to model the number of
defects in a batch of items.
• The distribution has two parameters, the number of
trials and the probability of success.
The Poisson distribution is closely related to the
negative exponential distribution in that it can be
used to represent arrival rates (λ), whereas the
negative exponential distribution is used to represent
inter-arrival times (1/λ).
Approximate distributions are not based on strong
theoretical underpinnings, but they provide a useful
approximation in the absence of data.
• As such they are useful in providing a first pass
distribution, particularly when dealing with category
C data.
• The simplest form of approximate distribution is the
uniform distribution, which can either be discrete or
continuous.
• This distribution is useful when all that is known is
the likely minimum and maximum of a value
Triangular Distribution
• The triangular distribution provides a slightly more
sophisticated approximation than the uniform
distribution by including a third parameter, the
mode, or most likely value.
• The triangular shape can be quite similar to the
shape of an Erlang distribution.
• As such, the triangular distribution can be used,
among other things, as an approximation for task
times and possibly inter-arrival times.
• It is important to note that, depending on the
parameters, the mean of the triangular distribution
can be quite different from the mode.