Quantitative Process Analysis

20 important questions on Quantitative Process Analysis

What are three quantitative analysis techniques? And what are these about?

- Quantitative Flow Analysis: cycle time analysis, cost-per-process, error rates at the process level, capacity requirements
- Queuing Theory
- Process Simulation

What are the three process performance measures? And mention some things they measure.

- Cost: cost per execution, resource utilization, waste
- Time: cycle time, waiting time/time spent in non-value-added tasks
- Quality: error rates, missed promise

What is cycle time analysis?

The task of calculating the average cycle time for an entire process or process fragment. It assumes that the average activity times for all involved activities are available (activity time = waiting time + processing time)
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

What is the cycle time?

The difference between a job's start and end time
Cycle time = waiting time + actual processing time

How to calculate cycle time for a sequence? A XOR-split? A AND-split? A loop?

For a sequence it is just adding the cycle times.

For a XOR-split you take the probability for the branch * the cycle time. And do this for each branch and add them. Cycle time = p1T1 + p2T2 + ... + pnTn

For a AND-split you take the maximum for all activities in the two paths. CTparallel = Max{T1, T2, ..., Tn}

For loops you take the activity and divide it by 1 - the probability that it will be retuned back. CT = T /  (1-r)

What is the cycle time efficiency and how do you calculate it.

The percentage of the total cycle time spent on value adding activities
Cycle Time Efficiency = Theoretical Cycle Time / CT

What is the Theoretical Cycle Time (TCT)?

The TCT is the cycle time if we only counted value-adding activities and excluded any waiting time or handover time, so it counts only processing times.

What is WIP and how do you calulate it?

Work-in-process (WIP) is the (average) work-in-process.
WIP = labda * CT
Labda = the arrival rate (number of new cases per time unit)

What are the limitations of the Quantitative Flow Analysis?

- Not all models are structured: so this makes it hard to calculate cycle times
- Fixed load + fixed resource capacity: cycle time analysis does not consider waiting times due to resource contention

Why is queuing analysis important?

- Capacity problems are very common in industry and one of the main drivers of process redesign.
- Queuing and waiting time analysis is particulary important in service systems

When is there a queuing delay?

- Bursty interarrival intervals
- Job size variation
- High utilization

There is NO queuing delay when the arrivals are regular (deterministic traffic) or sufficiently spaced apart (variable but spaced apart traffic).

What are the basic concepts in the queuing theory and what do they mean? And what can you calculate with these?

- this is the mean arrival rate = the average number of arrivals per time unit
- this is the mean service rate = the average number of jobs that can be handled by one server per time unit
- c = the number of servers

With these you can calculate
- Occupation rate:   
- Wq : average time in queue
- W : average time in system (i.e. cycle time)
- Lq : average number in queue (i.e. length of queue)
- L : average number in system average (i.e. WIP)

What is the most basic system in the queuing theory? Explain it.

The M/M/1 queue.
The time between arrivals and service time follow a negative exponential distribution is assumed.
There is one server (c =1)
First in is first out.

What is the Poisson process?

This is a common arrival assumption in many queuing and simulation models.
The times between arrivals are independent, identically distributed and exponential.
A key property is the fact that a certain event has not happened does not tell us something about how long it will take before it happens.

What are the drawback of the queuing theory?

- It is often not applicable when the system includes parallel activities
- It requires case-by-case mathematical analysis
- Assumes "steady-state" (valid only for "long-term" analysis)

What are the advantages of process simulation (compared to the queuing theory)?

- It is more versatile (veelzijdig)
- It makes use of a large number of process instances, it gathers data and calculates statistics from the output

What are the steps in evaluating a process with simulation?

- Model the process
- Enhance the process model with simulation info (this makes up a simulation model)
- Run the simulation
- Analyze the simulation outputs
- Repeat for alternative scenarios

What are the elements of a simulation model?

- The process model
- Resource assignment: mapping from activities to resource classes
- Processing times: per activity or per acitivity-resource pair
- Costs: per activity and/or per activity-resource pair
- Arrival rate of process instances
- Conditional branching probabilities (for XOR gateways)

What are the difficulties of simulation?

- Numerous choices need to be made.
- Simplifying assumptions is necessary
- Reliability is largely dependent on the accuracy of the inputs
- Multiple validation loops are necessary with process stakeholders to verify validity
- Sensitivity analysis

Give an example of a more versatile simulation technique and tool.

Technique: Discrete Event Simulation
Accompanying tools: Arena, CPN tools

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo