Design of Experiments Flashcards
State the sequence of activities for an industrial experiment;
1) Hypothesis – an assumption that motivates the experiment
2) Experiment – a series of tests conducted to investigate the hypothesis
3) Analysis – understanding the nature of data and performing statistical analysis of the collected data from the experiment
4) Interpretation – understanding the results of the experimental analysis
5) Conclusion – stating whether or not the original set hypothesis is true or false
In a designed experiment, what is the definition of “responses”?
a. Responses are the input values as set by the experimenter.
b. Responses are the numerical values that an independent variable can take
during an experiment.
c. The degree to which the result of a measurement, calculation, or specification
conforms to the correct value or a standard.
d. The measured outcomes of an experiment.
e. Responses quantify the existing numerical links between factors and levels.
d. The measured outcomes of an experiment.
What are noise factors?
Noise factors are uncontrollable factors that induce variation under normal operating conditions.
How do causation and correlation differ?
Two factors that vary together may be highly correlated without one causing the other - they may both be caused by a third factor.
State the steps for Planning, conducting and analysing an experiment.
1) Recognition and statement of the problem
2) Choice of factors, levels, and ranges
3) Selection of the response variable(s)
4) Choice of design
5) Conducting the experiment
6) Statistical analysis
7) Drawing conclusions, and making recommendations
State the basic principles of the DOE.
1) Formulate question/goal in advance
2) Comparison/control
3) Replication
4) Randomization
5) Stratification (or blocking)
6) Factorial experiments
Define Control (Placebo) in the DOE.
A baseline case (No treatment case) that you can compare your results to.
Why is Replication important?
Replication is the basic issue behind every method we will use in order to get a handle on how precise our estimates are at the end.
How can you analyse replicated experiments?
With replicated measurements, we can characterise the variability within measurements and compare to that between measurements. This is called Analysis of Variance (ANOVA)
Why is a robust sampling design required?
If the samples size or method of collecting the data is wrong then you will not be able to undertake the anylsis that you plan to.
If the data are not of appropriate quality (precision, duration) then it will be difficult to reach robust conclusions.
What is randomization?
It is a process to eliminate potential biases from the conclusions, and random assignment is a critical step. Randomisation allows the later use of probability theory, and so gives a solid foundation for statistical analysis
What is blocking?
Blocking (or stratification) is a technique to include other factors in our experiment which contributes to undesirable variation. It avoids biases that might occur due to differences between the allocation of subjects to the treatments
What are confounding factors?
confounding factors are variables that influence both the inputs and the outputs causing a spurious association
Three simple rules of randomisation and blocking:
If you can (and want to), fix a variable
If you don’t fix a variable, stratify it
If you can neither fix nor stratify a variable, randomize it
What is a factorial experiment?
- an experiment where several independent factors are controlled and their effects are investigated at each of two or more levels
