Process Experimentation with a Single Factor
Experiment, and it will lead you to the light.
(Cole Porter, ‘Experiment’ from Nymph Errant, 1933)
This chapter deals with statistical tools that are relevant to the improve phase of Six Sigma projects. Having made changes to a process, how do we formally assess data from the modified process for evidence of improvement? Statistical inference techniques may be use to address questions such as:
- Has the change of supplier of the lens coating fluid led to a reduction in the proportion of nonconforming lenses?
- Has the appointment of specialist nurses, empowered to administer thrombolytic treatment to acute myocardial infarction patients on admission to hospital, led to a reduction in the mean door to needle time?
Estimation techniques provide point estimates of the population proportion and the population mean, respectively, for the modified processes in the above scenarios, i.e. of population parameters that are of interest. Estimation techniques provide intervals in which we can have confidence that the values of the parameters are located.
Some of the techniques are based on the normal distribution while others make no such assumption. Minitab is well equipped to deal with both classes of technique.
7.1 Fundamentals of Hypothesis Testing
In Chapter 1, the description of the improve phase in a Six Sigma project given by Roger Hoerl included the statement ‘determine how to intervene in the process to significantly ...