Theoretical Basis for the EDA Concept - Good Cascade Impactor Practices, AIM and EDA for Orally Inhaled Products - page 147

The first bullet relies on risk assessment, i.e., what can go wrong that will impact
APSD and if it did would the QC test detect the resulting abnormality (see Chap. 9
for a more complete discussion of risk assessment). This present chapter will briefly
introduce the latter two considerations. A detailed discussion of the evaluation of
measurements and the decision-making process will follow in Chap. 8 .

7.2 Measurement Theory and Evaluation

In the design and implementation of any measurement, it is important to consider
the purpose of the measurement as this informs both the design and evaluation of
the effectiveness of the measurement. For example, there are different consider-
ations for a measurement intended to characterize or describe an attribute of a par-
ticular object versus one intended to make a decision about a batch of objects with
respect to a particular characteristic based on representative samples. Wheeler has
described this concept in more detail [ 12 ].
Measurements can be classified into four categories based on the general purpose
of measurement:

1. Description
2. Characterization
3. Representation
4. Prediction

Description refers to measurements that inform about the attributes of the item
being measured. Characterization is similar to description except that it also
involves comparison of the measurements to some expectation for the particular
object studied, i.e., a requirement or limit. Representation involves using measure-
ments on a representative sample to make inference about the population the sample
is intended to represent. This is in essence the QC application where a batch is
released or rejected on the basis of testing performed on a sample(s) taken from the
batch in question and comparing the measurement results to some requirement.
Finally, prediction is based on using measurements of samples from current batches
to predict the attributes of future batches. Since EDA is proposed for QC purposes
where batch disposition is decided based on a representative sample, it is classified
as a representation measurement.
The adequacy of a particular measurement with respect to precision should
inherently consider the variability of the measurement versus the variability of
product being measured or the tolerances imposed on the product. This is the fun-
damental essence of measurement system analysis (MSA) [ 13 ], which typically
employs ANOVA designs to estimate measurement and product variances. These
types of designs are also collectively known as gage repeatability and reproducibil-
ity (Gage R&R) studies [ 14 ]. Application of MSA concepts to compare the relative
performance of the EDA metrics with CI stage groupings in the assessment of OIP
APSDs is covered in Chap. 8 .