Using a Manufacturer’s Specification as a Type B Error Contribution
White Papers
Manufacturers’ specifications are a complicated interplay of consumer demand, contractual agreement and definition of “fitness for use” warranty. To better understand the implications of using manufacturers’ specifications in an uncertainty analysis, we will explore technical topics such as the following
- How specifications are created and managed
- Advantage of using specification
- Statistic versus managed specification
- Stationary and non-stationary random processes
- GUM concepts like “safe”
- Issue and definition of pseudo systematic error
This exploration will be done using no advanced math or statistics. This paper examines these issues in the informal context of a Pachinko gambling device. As a result, it will become clear why an uncertainty analysis (employing TYPE B data) is a worst case analysis. This can affect how calibration laboratories use uncertainty data in the quality system and on customer facing documents and training.