TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Measurement Theory - Parameters
Holly Ott 1 Quality Engineering & Management Module 4
Using the understanding of the process, the parameters which influence the process and affect the quality can be identified.
In a process improvement program, these input parameters will be then prioritized based with respect to their degree of impact on desired output or outputs.
We now need to decide how to measure these parameters so that we obtain unbiased and meaningful measures in a cost-effective way that can then be applied in a quality improvement program.
TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Measurement Theory Sampling Plan
Holly Ott 2 Quality Engineering & Management Module 4
Measurements must be descriptive, selective and objective.
The conditions of the measurement must be controlled so that the data can be interpreted and the underlying relationships between inputs and outputs understood.
Next the sampling plan must be constructed such that the sample is sufficient to establish the effect of any input changes and to give an acceptable level of certainty about this effect.
The variability of the measured outputs will affect the sampling plan.
TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Measurement Error
Holly Ott 3 Quality Engineering & Management Module 4
Measurement Bias
Measured Process Variability
Sampling Errors Short-term Process Variation Measurement
Validity Measurement
Reliability Long-term
Process Variation
Inherent Process Variability Measurement Errors
Resolution
Stability
Linearity
Measurement Precision
Repeatability
Reproducibility
Reiner Hutwelker
TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Measurement Error - Repeatability
Holly Ott Quality Engineering & Management Module 4 4
Reiner Hutwelker
Repeatability is variation due to repeated tests of the same parts with the same operator using the same measrrement system
Variation from repeatability
Operator A Measurement Repetition
TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Measurement Error - Reproducibility
Holly Ott Quality Engineering & Management Module 4 5
Reproducibility is the variation due to repeated tests of the same parts with different operators using the same measurement system
Reiner Hutwelker
Streuung bei Nachvollziehbarkeit der Messung
Operator A Operator C
Operator B Reproducibility
TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Sampling Plans
Holly Ott 6 Quality Engineering & Management Module 4
Prioritized input and process parameters and outputs are specified exactly
Specification of the goal of the measurement, the sample size, the data type and the sampling frequency.
Necessity for a measurement system analysis or not. Identification of the hypotheses to be tested: what should be
tested and with which methods.
TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Sampling Plans
Holly Ott 7 Quality Engineering & Management Module 4
Two commonly used sampling techniques are: Simple random sampling Stratified random sampling
x x x
x x
x x
x x x x
x x
x x x
x
x
x x
x x x
Simple Random Sampling
Stratified Random Sampling
A A A
A A
A
B B B
B B
C C C C
C C C
D D
D D D D
Population
Population
Sample
Sample
x x x x x x
AABBCCDD
Each element in the population has an equal chance of being included
A fixed /proportionate amount will be randomly selected from each strata
Reiner Hutwelker
TUM School of Management Production and Supply Chain Management Prof Martin Grunow Technische Universitt Mnchen
Coming Up
Lecture 4.2: Descriptive vs. Inferential Statistics
Holly Ott 8 Quality Engineering & Management Module 4